BZPEERPapers, people, evidence and research paths
Menu

Discover

SearchFind papers, people, topics, institutions and opportunities from one place.GraphSee how papers, authors, topics and evidence connect.

Research tools

HomeContinue from the papers, people and topics that matter now.CollectionsTurn saved papers into reading lists, evidence maps and shareable context.ResearchReconstruct the path that led you from search to paper to question.CollaborationMove from a paper, topic or expert request into a focused thread.PublishCreate full-text research articles with metadata, formulas and versions.

Network

ExpertsFind specialists whose work and reviews explain why they can help.CommunitiesJoin research groups organized around papers, topics and shared evidence.

Opportunities

ListingsBrowse roles, calls and collaborations connected to real research context.

Account

Log inReturn to your saved papers, graph views and active threads.Create accountStart saving papers, building a research trail and joining teams.
Log inCreate account

Source author record

Stefano Soatto

Stefano Soatto appears in the imported research catalog. Authorship, coauthor and topic links are available while profile ownership is still unclaimed.

ResearcherUnclaimed source record
Computer VisionMachine LearningArtificial IntelligenceComputation and LanguageCryptography and SecurityInformation Theorymath.ITRoboticsGraphicsmath.NAmath.OCNeural and Evolutionary ComputingSocial and Information Networks

Catalog footprint

What is connected

46works
13topics
4close collaborators

Actions

Connect this record

Log in to claim
Open graphBrowse works

Research graph

See the researcher in context

Open full explorer

Inspect adjacent papers, topics, institutions and collaborators without losing the researcher page.

Building this map preview

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

46 published item(s)

preprint2026arXiv

Experience Sharing in Mutual Reinforcement Learning for Heterogeneous Language Models

We introduce Mutual Reinforcement Learning, a framework for concurrent RL post-training in which heterogeneous LLM policies exchange typed experience while keeping separate parameters, objectives, and tokenizers. The framework combines a Shared Experience Exchange (SEE), Multi-Worker Resource Allocation (MWRA), and a Tokenizer Heterogeneity Layer (THL) that retokenizes text and aligns token-level traces across incompatible vocabularies. This substrate makes the experience-sharing design question operational across model families. We instantiate three controlled probes on top of GRPO: data-level rollout sharing via Peer Rollout Pooling (PRP), value-level advantage sharing via Cross-Policy GRPO Advantage Sharing (XGRPO), and outcome-level success transfer via Success-Gated Transfer (SGT). A contextual-bandit analysis characterizes their structural positions on a stability-support trade-off: PRP pays density-ratio variance and THL residual costs, XGRPO preserves on-policy actor support while changing scalar baselines, and SGT supplies a rescue-set score direction toward verified peer successes. In the evaluated regime, outcome-level sharing occupies the favorable point of this trade-off.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Priming: Hybrid State Space Models From Pre-trained Transformers

Hybrid State-Space models combine Attention with recurrent State-Space Model (SSM) layers, balancing eidetic memory from Attention with compressed fading memory from SSMs. This yields smaller Key-Value caches and faster decoding than Transformers, along with a richer architectural design space. Exploring that design space at scale has so far required training from scratch, a barrier that has kept most large-model Hybrid research within a narrow range of architectures. We introduce Priming, a method that turns Hybrid architecture design from a pre-training problem into a knowledge transfer one. Priming initializes a Hybrid model from a pre-trained Transformer and, through short alignment and post-training phases, recovers downstream quality using less than 0.5% of the source model's pre-training token budget. Priming is agnostic to the source Transformer family (e.g., Qwen, Llama, Mistral), model class (dense or Mixture-of-Experts), and model scale. Priming enables us to run the first controlled comparison of SSM layer types at scale under identical conditions. We evaluate, Gated KalmaNet (GKA), Gated DeltaNet (GDN), and Mamba-2, and show that their expressiveness hierarchy, GKA>GDN>Mamba-2, directly predicts downstream performance on long-context reasoning tasks. We scale Priming to 8B/32B reasoning models with native 128K contexts. Our Hybrid GKA 32B improves over its source Qwen3-32B by +3.8 average reasoning points, while staying within 1% of a Transformer post-trained on the same data and enabling up to 2.3x higher decode throughput. To foster research on Hybrid architectures, we release a model zoo of primed Hybrid models for long-context reasoning and instruction following, together with the Priming training and inference code (Sequence Parallelism algorithms for long-context training, optimized GKA kernels, and vLLM serving plugin), all under Apache~2.0 License.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Talk2Move: Reinforcement Learning for Text-Instructed Object-Level Geometric Transformation in Scenes

We introduce Talk2Move, a reinforcement learning (RL) based diffusion framework for text-instructed spatial transformation of objects within scenes. Spatially manipulating objects in a scene through natural language poses a challenge for multimodal generation systems. While existing text-based manipulation methods can adjust appearance or style, they struggle to perform object-level geometric transformations-such as translating, rotating, or resizing objects-due to scarce paired supervision and pixel-level optimization limits. Talk2Move employs Group Relative Policy Optimization (GRPO) to explore geometric actions through diverse rollouts generated from input images and lightweight textual variations, removing the need for costly paired data. A spatial reward guided model aligns geometric transformations with linguistic description, while off-policy step evaluation and active step sampling improve learning efficiency by focusing on informative transformation stages. Furthermore, we design object-centric spatial rewards that evaluate displacement, rotation, and scaling behaviors directly, enabling interpretable and coherent transformations. Experiments on curated benchmarks demonstrate that Talk2Move achieves precise, consistent, and semantically faithful object transformations, outperforming existing text-guided editing approaches in both spatial accuracy and scene coherence.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

ARCH++: Animation-Ready Clothed Human Reconstruction Revisited

We present ARCH++, an image-based method to reconstruct 3D avatars with arbitrary clothing styles. Our reconstructed avatars are animation-ready and highly realistic, in both the visible regions from input views and the unseen regions. While prior work shows great promise of reconstructing animatable clothed humans with various topologies, we observe that there exist fundamental limitations resulting in sub-optimal reconstruction quality. In this paper, we revisit the major steps of image-based avatar reconstruction and address the limitations with ARCH++. First, we introduce an end-to-end point based geometry encoder to better describe the semantics of the underlying 3D human body, in replacement of previous hand-crafted features. Second, in order to address the occupancy ambiguity caused by topological changes of clothed humans in the canonical pose, we propose a co-supervising framework with cross-space consistency to jointly estimate the occupancy in both the posed and canonical spaces. Last, we use image-to-image translation networks to further refine detailed geometry and texture on the reconstructed surface, which improves the fidelity and consistency across arbitrary viewpoints. In the experiments, we demonstrate improvements over the state of the art on both public benchmarks and user studies in reconstruction quality and realism.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Class-Incremental Learning with Strong Pre-trained Models

Class-incremental learning (CIL) has been widely studied under the setting of starting from a small number of classes (base classes). Instead, we explore an understudied real-world setting of CIL that starts with a strong model pre-trained on a large number of base classes. We hypothesize that a strong base model can provide a good representation for novel classes and incremental learning can be done with small adaptations. We propose a 2-stage training scheme, i) feature augmentation -- cloning part of the backbone and fine-tuning it on the novel data, and ii) fusion -- combining the base and novel classifiers into a unified classifier. Experiments show that the proposed method significantly outperforms state-of-the-art CIL methods on the large-scale ImageNet dataset (e.g. +10% overall accuracy than the best). We also propose and analyze understudied practical CIL scenarios, such as base-novel overlap with distribution shift. Our proposed method is robust and generalizes to all analyzed CIL settings. Code is available at https://github.com/amazon-research/sp-cil.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Contrastive Neighborhood Alignment

We present Contrastive Neighborhood Alignment (CNA), a manifold learning approach to maintain the topology of learned features whereby data points that are mapped to nearby representations by the source (teacher) model are also mapped to neighbors by the target (student) model. The target model aims to mimic the local structure of the source representation space using a contrastive loss. CNA is an unsupervised learning algorithm that does not require ground-truth labels for the individual samples. CNA is illustrated in three scenarios: manifold learning, where the model maintains the local topology of the original data in a dimension-reduced space; model distillation, where a small student model is trained to mimic a larger teacher; and legacy model update, where an older model is replaced by a more powerful one. Experiments show that CNA is able to capture the manifold in a high-dimensional space and improves performance compared to the competing methods in their domains.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Graph Spectral Embedding using the Geodesic Betweeness Centrality

We introduce the Graph Sylvester Embedding (GSE), an unsupervised graph representation of local similarity, connectivity, and global structure. GSE uses the solution of the Sylvester equation to capture both network structure and neighborhood proximity in a single representation. Unlike embeddings based on the eigenvectors of the Laplacian, GSE incorporates two or more basis functions, for instance using the Laplacian and the affinity matrix. Such basis functions are constructed not from the original graph, but from one whose weights measure the centrality of an edge (the fraction of the number of shortest paths that pass through that edge) in the original graph. This allows more flexibility and control to represent complex network structure and shows significant improvements over the state of the art when used for data analysis tasks such as predicting failed edges in material science and network alignment in the human-SARS CoV-2 protein-protein interactome.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

MeMOT: Multi-Object Tracking with Memory

We propose an online tracking algorithm that performs the object detection and data association under a common framework, capable of linking objects after a long time span. This is realized by preserving a large spatio-temporal memory to store the identity embeddings of the tracked objects, and by adaptively referencing and aggregating useful information from the memory as needed. Our model, called MeMOT, consists of three main modules that are all Transformer-based: 1) Hypothesis Generation that produce object proposals in the current video frame; 2) Memory Encoding that extracts the core information from the memory for each tracked object; and 3) Memory Decoding that solves the object detection and data association tasks simultaneously for multi-object tracking. When evaluated on widely adopted MOT benchmark datasets, MeMOT observes very competitive performance.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Mixed Differential Privacy in Computer Vision

We introduce AdaMix, an adaptive differentially private algorithm for training deep neural network classifiers using both private and public image data. While pre-training language models on large public datasets has enabled strong differential privacy (DP) guarantees with minor loss of accuracy, a similar practice yields punishing trade-offs in vision tasks. A few-shot or even zero-shot learning baseline that ignores private data can outperform fine-tuning on a large private dataset. AdaMix incorporates few-shot training, or cross-modal zero-shot learning, on public data prior to private fine-tuning, to improve the trade-off. AdaMix reduces the error increase from the non-private upper bound from the 167-311\% of the baseline, on average across 6 datasets, to 68-92\% depending on the desired privacy level selected by the user. AdaMix tackles the trade-off arising in visual classification, whereby the most privacy sensitive data, corresponding to isolated points in representation space, are also critical for high classification accuracy. In addition, AdaMix comes with strong theoretical privacy guarantees and convergence analysis.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Omni-DETR: Omni-Supervised Object Detection with Transformers

We consider the problem of omni-supervised object detection, which can use unlabeled, fully labeled and weakly labeled annotations, such as image tags, counts, points, etc., for object detection. This is enabled by a unified architecture, Omni-DETR, based on the recent progress on student-teacher framework and end-to-end transformer based object detection. Under this unified architecture, different types of weak labels can be leveraged to generate accurate pseudo labels, by a bipartite matching based filtering mechanism, for the model to learn. In the experiments, Omni-DETR has achieved state-of-the-art results on multiple datasets and settings. And we have found that weak annotations can help to improve detection performance and a mixture of them can achieve a better trade-off between annotation cost and accuracy than the standard complete annotation. These findings could encourage larger object detection datasets with mixture annotations. The code is available at https://github.com/amazon-research/omni-detr.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

On Leave-One-Out Conditional Mutual Information For Generalization

We derive information theoretic generalization bounds for supervised learning algorithms based on a new measure of leave-one-out conditional mutual information (loo-CMI). Contrary to other CMI bounds, which are black-box bounds that do not exploit the structure of the problem and may be hard to evaluate in practice, our loo-CMI bounds can be computed easily and can be interpreted in connection to other notions such as classical leave-one-out cross-validation, stability of the optimization algorithm, and the geometry of the loss-landscape. It applies both to the output of training algorithms as well as their predictions. We empirically validate the quality of the bound by evaluating its predicted generalization gap in scenarios for deep learning. In particular, our bounds are non-vacuous on large-scale image-classification tasks.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

On the Learnability of Physical Concepts: Can a Neural Network Understand What's Real?

We revisit the classic signal-to-symbol barrier in light of the remarkable ability of deep neural networks to generate realistic synthetic data. DeepFakes and spoofing highlight the feebleness of the link between physical reality and its abstract representation, whether learned by a digital computer or a biological agent. Starting from a widely applicable definition of abstract concept, we show that standard feed-forward architectures cannot capture but trivial concepts, regardless of the number of weights and the amount of training data, despite being extremely effective classifiers. On the other hand, architectures that incorporate recursion can represent a significantly larger class of concepts, but may still be unable to learn them from a finite dataset. We qualitatively describe the class of concepts that can be "understood" by modern architectures trained with variants of stochastic gradient descent, using a (free energy) Lagrangian to measure information complexity. Even if a concept has been understood, however, a network has no means of communicating its understanding to an external agent, except through continuous interaction and validation. We then characterize physical objects as abstract concepts and use the previous analysis to show that physical objects can be encoded by finite architectures. However, to understand physical concepts, sensors must provide persistently exciting observations, for which the ability to control the data acquisition process is essential (active perception). The importance of control depends on the modality, benefiting visual more than acoustic or chemical perception. Finally, we conclude that binding physical entities to digital identities is possible in finite time with finite resources, solving in principle the signal-to-symbol barrier problem, but we highlight the need for continuous validation.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Semi-supervised Vision Transformers at Scale

We study semi-supervised learning (SSL) for vision transformers (ViT), an under-explored topic despite the wide adoption of the ViT architectures to different tasks. To tackle this problem, we propose a new SSL pipeline, consisting of first un/self-supervised pre-training, followed by supervised fine-tuning, and finally semi-supervised fine-tuning. At the semi-supervised fine-tuning stage, we adopt an exponential moving average (EMA)-Teacher framework instead of the popular FixMatch, since the former is more stable and delivers higher accuracy for semi-supervised vision transformers. In addition, we propose a probabilistic pseudo mixup mechanism to interpolate unlabeled samples and their pseudo labels for improved regularization, which is important for training ViTs with weak inductive bias. Our proposed method, dubbed Semi-ViT, achieves comparable or better performance than the CNN counterparts in the semi-supervised classification setting. Semi-ViT also enjoys the scalability benefits of ViTs that can be readily scaled up to large-size models with increasing accuracies. For example, Semi-ViT-Huge achieves an impressive 80% top-1 accuracy on ImageNet using only 1% labels, which is comparable with Inception-v4 using 100% ImageNet labels.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Stereoscopic Universal Perturbations across Different Architectures and Datasets

We study the effect of adversarial perturbations of images on deep stereo matching networks for the disparity estimation task. We present a method to craft a single set of perturbations that, when added to any stereo image pair in a dataset, can fool a stereo network to significantly alter the perceived scene geometry. Our perturbation images are "universal" in that they not only corrupt estimates of the network on the dataset they are optimized for, but also generalize to different architectures trained on different datasets. We evaluate our approach on multiple benchmark datasets where our perturbations can increase the D1-error (akin to fooling rate) of state-of-the-art stereo networks from 1% to as much as 87%. We investigate the effect of perturbations on the estimated scene geometry and identify object classes that are most vulnerable. Our analysis on the activations of registered points between left and right images led us to find architectural components that can increase robustness against adversaries. By simply designing networks with such components, one can reduce the effect of adversaries by up to 60.5%, which rivals the robustness of networks fine-tuned with costly adversarial data augmentation. Our design principle also improves their robustness against common image corruptions by an average of 70%.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Task Adaptive Parameter Sharing for Multi-Task Learning

Adapting pre-trained models with broad capabilities has become standard practice for learning a wide range of downstream tasks. The typical approach of fine-tuning different models for each task is performant, but incurs a substantial memory cost. To efficiently learn multiple downstream tasks we introduce Task Adaptive Parameter Sharing (TAPS), a general method for tuning a base model to a new task by adaptively modifying a small, task-specific subset of layers. This enables multi-task learning while minimizing resources used and competition between tasks. TAPS solves a joint optimization problem which determines which layers to share with the base model and the value of the task-specific weights. Further, a sparsity penalty on the number of active layers encourages weight sharing with the base model. Compared to other methods, TAPS retains high accuracy on downstream tasks while introducing few task-specific parameters. Moreover, TAPS is agnostic to the model architecture and requires only minor changes to the training scheme. We evaluate our method on a suite of fine-tuning tasks and architectures (ResNet, DenseNet, ViT) and show that it achieves state-of-the-art performance while being simple to implement.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Towards Differential Relational Privacy and its use in Question Answering

Memorization of the relation between entities in a dataset can lead to privacy issues when using a trained model for question answering. We introduce Relational Memorization (RM) to understand, quantify and control this phenomenon. While bounding general memorization can have detrimental effects on the performance of a trained model, bounding RM does not prevent effective learning. The difference is most pronounced when the data distribution is long-tailed, with many queries having only few training examples: Impeding general memorization prevents effective learning, while impeding only relational memorization still allows learning general properties of the underlying concepts. We formalize the notion of Relational Privacy (RP) and, inspired by Differential Privacy (DP), we provide a possible definition of Differential Relational Privacy (DrP). These notions can be used to describe and compute bounds on the amount of RM in a trained model. We illustrate Relational Privacy concepts in experiments with large-scale models for Question Answering.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Uniform Sampling over Episode Difficulty

Episodic training is a core ingredient of few-shot learning to train models on tasks with limited labelled data. Despite its success, episodic training remains largely understudied, prompting us to ask the question: what is the best way to sample episodes? In this paper, we first propose a method to approximate episode sampling distributions based on their difficulty. Building on this method, we perform an extensive analysis and find that sampling uniformly over episode difficulty outperforms other sampling schemes, including curriculum and easy-/hard-mining. As the proposed sampling method is algorithm agnostic, we can leverage these insights to improve few-shot learning accuracies across many episodic training algorithms. We demonstrate the efficacy of our method across popular few-shot learning datasets, algorithms, network architectures, and protocols.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

X-DETR: A Versatile Architecture for Instance-wise Vision-Language Tasks

In this paper, we study the challenging instance-wise vision-language tasks, where the free-form language is required to align with the objects instead of the whole image. To address these tasks, we propose X-DETR, whose architecture has three major components: an object detector, a language encoder, and vision-language alignment. The vision and language streams are independent until the end and they are aligned using an efficient dot-product operation. The whole network is trained end-to-end, such that the detector is optimized for the vision-language tasks instead of an off-the-shelf component. To overcome the limited size of paired object-language annotations, we leverage other weak types of supervision to expand the knowledge coverage. This simple yet effective architecture of X-DETR shows good accuracy and fast speeds for multiple instance-wise vision-language tasks, e.g., 16.4 AP on LVIS detection of 1.2K categories at ~20 frames per second without using any LVIS annotation during training.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

A linearized framework and a new benchmark for model selection for fine-tuning

Fine-tuning from a collection of models pre-trained on different domains (a "model zoo") is emerging as a technique to improve test accuracy in the low-data regime. However, model selection, i.e. how to pre-select the right model to fine-tune from a model zoo without performing any training, remains an open topic. We use a linearized framework to approximate fine-tuning, and introduce two new baselines for model selection -- Label-Gradient and Label-Feature Correlation. Since all model selection algorithms in the literature have been tested on different use-cases and never compared directly, we introduce a new comprehensive benchmark for model selection comprising of: i) A model zoo of single and multi-domain models, and ii) Many target tasks. Our benchmark highlights accuracy gain with model zoo compared to fine-tuning Imagenet models. We show our model selection baseline can select optimal models to fine-tune in few selections and has the highest ranking correlation to fine-tuning accuracy compared to existing algorithms.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Robustness of classifiers to universal perturbations: a geometric perspective

Deep networks have recently been shown to be vulnerable to universal perturbations: there exist very small image-agnostic perturbations that cause most natural images to be misclassified by such classifiers. In this paper, we propose the first quantitative analysis of the robustness of classifiers to universal perturbations, and draw a formal link between the robustness to universal perturbations, and the geometry of the decision boundary. Specifically, we establish theoretical bounds on the robustness of classifiers under two decision boundary models (flat and curved models). We show in particular that the robustness of deep networks to universal perturbations is driven by a key property of their curvature: there exists shared directions along which the decision boundary of deep networks is systematically positively curved. Under such conditions, we prove the existence of small universal perturbations. Our analysis further provides a novel geometric method for computing universal perturbations, in addition to explaining their properties.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Towards Backward-Compatible Representation Learning

We propose a way to learn visual features that are compatible with previously computed ones even when they have different dimensions and are learned via different neural network architectures and loss functions. Compatible means that, if such features are used to compare images, then "new" features can be compared directly to "old" features, so they can be used interchangeably. This enables visual search systems to bypass computing new features for all previously seen images when updating the embedding models, a process known as backfilling. Backward compatibility is critical to quickly deploy new embedding models that leverage ever-growing large-scale training datasets and improvements in deep learning architectures and training methods. We propose a framework to train embedding models, called backward-compatible training (BCT), as a first step towards backward compatible representation learning. In experiments on learning embeddings for face recognition, models trained with BCT successfully achieve backward compatibility without sacrificing accuracy, thus enabling backfill-free model updates of visual embeddings.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks

We explore the problem of selectively forgetting a particular subset of the data used for training a deep neural network. While the effects of the data to be forgotten can be hidden from the output of the network, insights may still be gleaned by probing deep into its weights. We propose a method for "scrubbing'" the weights clean of information about a particular set of training data. The method does not require retraining from scratch, nor access to the data originally used for training. Instead, the weights are modified so that any probing function of the weights is indistinguishable from the same function applied to the weights of a network trained without the data to be forgotten. This condition is a generalized and weaker form of Differential Privacy. Exploiting ideas related to the stability of stochastic gradient descent, we introduce an upper-bound on the amount of information remaining in the weights, which can be estimated efficiently even for deep neural networks.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

FDA: Fourier Domain Adaptation for Semantic Segmentation

We describe a simple method for unsupervised domain adaptation, whereby the discrepancy between the source and target distributions is reduced by swapping the low-frequency spectrum of one with the other. We illustrate the method in semantic segmentation, where densely annotated images are aplenty in one domain (synthetic data), but difficult to obtain in another (real images). Current state-of-the-art methods are complex, some requiring adversarial optimization to render the backbone of a neural network invariant to the discrete domain selection variable. Our method does not require any training to perform the domain alignment, just a simple Fourier Transform and its inverse. Despite its simplicity, it achieves state-of-the-art performance in the current benchmarks, when integrated into a relatively standard semantic segmentation model. Our results indicate that even simple procedures can discount nuisance variability in the data that more sophisticated methods struggle to learn away.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Few-Shot Learning with Embedded Class Models and Shot-Free Meta Training

We propose a method for learning embeddings for few-shot learning that is suitable for use with any number of ways and any number of shots (shot-free). Rather than fixing the class prototypes to be the Euclidean average of sample embeddings, we allow them to live in a higher-dimensional space (embedded class models) and learn the prototypes along with the model parameters. The class representation function is defined implicitly, which allows us to deal with a variable number of shots per each class with a simple constant-size architecture. The class embedding encompasses metric learning, that facilitates adding new classes without crowding the class representation space. Despite being general and not tuned to the benchmark, our approach achieves state-of-the-art performance on the standard few-shot benchmark datasets.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Incremental Meta-Learning via Indirect Discriminant Alignment

Majority of the modern meta-learning methods for few-shot classification tasks operate in two phases: a meta-training phase where the meta-learner learns a generic representation by solving multiple few-shot tasks sampled from a large dataset and a testing phase, where the meta-learner leverages its learnt internal representation for a specific few-shot task involving classes which were not seen during the meta-training phase. To the best of our knowledge, all such meta-learning methods use a single base dataset for meta-training to sample tasks from and do not adapt the algorithm after meta-training. This strategy may not scale to real-world use-cases where the meta-learner does not potentially have access to the full meta-training dataset from the very beginning and we need to update the meta-learner in an incremental fashion when additional training data becomes available. Through our experimental setup, we develop a notion of incremental learning during the meta-training phase of meta-learning and propose a method which can be used with multiple existing metric-based meta-learning algorithms. Experimental results on benchmark dataset show that our approach performs favorably at test time as compared to training a model with the full meta-training set and incurs negligible amount of catastrophic forgetting

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Learning to Manipulate Individual Objects in an Image

We describe a method to train a generative model with latent factors that are (approximately) independent and localized. This means that perturbing the latent variables affects only local regions of the synthesized image, corresponding to objects. Unlike other unsupervised generative models, ours enables object-centric manipulation, without requiring object-level annotations, or any form of annotation for that matter. The key to our method is the combination of spatial disentanglement, enforced by a Contextual Information Separation loss, and perceptual cycle-consistency, enforced by a loss that penalizes changes in the image partition in response to perturbations of the latent factors. We test our method's ability to allow independent control of spatial and semantic factors of variability on existing datasets and also introduce two new ones that highlight the limitations of current methods.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Meta-Q-Learning

This paper introduces Meta-Q-Learning (MQL), a new off-policy algorithm for meta-Reinforcement Learning (meta-RL). MQL builds upon three simple ideas. First, we show that Q-learning is competitive with state-of-the-art meta-RL algorithms if given access to a context variable that is a representation of the past trajectory. Second, a multi-task objective to maximize the average reward across the training tasks is an effective method to meta-train RL policies. Third, past data from the meta-training replay buffer can be recycled to adapt the policy on a new task using off-policy updates. MQL draws upon ideas in propensity estimation to do so and thereby amplifies the amount of available data for adaptation. Experiments on standard continuous-control benchmarks suggest that MQL compares favorably with the state of the art in meta-RL.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Phase Consistent Ecological Domain Adaptation

We introduce two criteria to regularize the optimization involved in learning a classifier in a domain where no annotated data are available, leveraging annotated data in a different domain, a problem known as unsupervised domain adaptation. We focus on the task of semantic segmentation, where annotated synthetic data are aplenty, but annotating real data is laborious. The first criterion, inspired by visual psychophysics, is that the map between the two image domains be phase-preserving. This restricts the set of possible learned maps, while enabling enough flexibility to transfer semantic information. The second criterion aims to leverage ecological statistics, or regularities in the scene which are manifest in any image of it, regardless of the characteristics of the illuminant or the imaging sensor. It is implemented using a deep neural network that scores the likelihood of each possible segmentation given a single un-annotated image. Incorporating these two priors in a standard domain adaptation framework improves performance across the board in the most common unsupervised domain adaptation benchmarks for semantic segmentation.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Predicting Training Time Without Training

We tackle the problem of predicting the number of optimization steps that a pre-trained deep network needs to converge to a given value of the loss function. To do so, we leverage the fact that the training dynamics of a deep network during fine-tuning are well approximated by those of a linearized model. This allows us to approximate the training loss and accuracy at any point during training by solving a low-dimensional Stochastic Differential Equation (SDE) in function space. Using this result, we are able to predict the time it takes for Stochastic Gradient Descent (SGD) to fine-tune a model to a given loss without having to perform any training. In our experiments, we are able to predict training time of a ResNet within a 20% error margin on a variety of datasets and hyper-parameters, at a 30 to 45-fold reduction in cost compared to actual training. We also discuss how to further reduce the computational and memory cost of our method, and in particular we show that by exploiting the spectral properties of the gradients' matrix it is possible predict training time on a large dataset while processing only a subset of the samples.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Rethinking the Hyperparameters for Fine-tuning

Fine-tuning from pre-trained ImageNet models has become the de-facto standard for various computer vision tasks. Current practices for fine-tuning typically involve selecting an ad-hoc choice of hyperparameters and keeping them fixed to values normally used for training from scratch. This paper re-examines several common practices of setting hyperparameters for fine-tuning. Our findings are based on extensive empirical evaluation for fine-tuning on various transfer learning benchmarks. (1) While prior works have thoroughly investigated learning rate and batch size, momentum for fine-tuning is a relatively unexplored parameter. We find that the value of momentum also affects fine-tuning performance and connect it with previous theoretical findings. (2) Optimal hyperparameters for fine-tuning, in particular, the effective learning rate, are not only dataset dependent but also sensitive to the similarity between the source domain and target domain. This is in contrast to hyperparameters for training from scratch. (3) Reference-based regularization that keeps models close to the initial model does not necessarily apply for "dissimilar" datasets. Our findings challenge common practices of fine-tuning and encourages deep learning practitioners to rethink the hyperparameters for fine-tuning.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Stochastic batch size for adaptive regularization in deep network optimization

We propose a first-order stochastic optimization algorithm incorporating adaptive regularization applicable to machine learning problems in deep learning framework. The adaptive regularization is imposed by stochastic process in determining batch size for each model parameter at each optimization iteration. The stochastic batch size is determined by the update probability of each parameter following a distribution of gradient norms in consideration of their local and global properties in the neural network architecture where the range of gradient norms may vary within and across layers. We empirically demonstrate the effectiveness of our algorithm using an image classification task based on conventional network models applied to commonly used benchmark datasets. The quantitative evaluation indicates that our algorithm outperforms the state-of-the-art optimization algorithms in generalization while providing less sensitivity to the selection of batch size which often plays a critical role in optimization, thus achieving more robustness to the selection of regularity.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

The Information Complexity of Learning Tasks, their Structure and their Distance

We introduce an asymmetric distance in the space of learning tasks, and a framework to compute their complexity. These concepts are foundational for the practice of transfer learning, whereby a parametric model is pre-trained for a task, and then fine-tuned for another. The framework we develop is non-asymptotic, captures the finite nature of the training dataset, and allows distinguishing learning from memorization. It encompasses, as special cases, classical notions from Kolmogorov complexity, Shannon, and Fisher Information. However, unlike some of those frameworks, it can be applied to large-scale models and real-world datasets. Our framework is the first to measure complexity in a way that accounts for the effect of the optimization scheme, which is critical in Deep Learning.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Where is the Information in a Deep Neural Network?

Whatever information a deep neural network has gleaned from training data is encoded in its weights. How this information affects the response of the network to future data remains largely an open question. Indeed, even defining and measuring information entails some subtleties, since a trained network is a deterministic map, so standard information measures can be degenerate. We measure information in a neural network via the optimal trade-off between accuracy of the response and complexity of the weights, measured by their coding length. Depending on the choice of code, the definition can reduce to standard measures such as Shannon Mutual Information and Fisher Information. However, the more general definition allows us to relate information to generalization and invariance, through a novel notion of effective information in the activations of a deep network. We establish a novel relation between the information in the weights and the effective information in the activations, and use this result to show that models with low (information) complexity not only generalize better, but are bound to learn invariant representations of future inputs. These relations hinge not only on the architecture of the model, but also on how it is trained, highlighting the complex inter-dependency between the class of functions implemented by deep neural networks, the loss function used for training them from finite data, and the inductive bias implicit in the optimization.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

A Theory of Local Matching: SIFT and Beyond

Why has SIFT been so successful? Why its extension, DSP-SIFT, can further improve SIFT? Is there a theory that can explain both? How can such theory benefit real applications? Can it suggest new algorithms with reduced computational complexity or new descriptors with better accuracy for matching? We construct a general theory of local descriptors for visual matching. Our theory relies on concepts in energy minimization and heat diffusion. We show that SIFT and DSP-SIFT approximate the solution the theory suggests. In particular, DSP-SIFT gives a better approximation to the theoretical solution; justifying why DSP-SIFT outperforms SIFT. Using the developed theory, we derive new descriptors that have fewer parameters and are potentially better in handling affine deformations.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

An Empirical Evaluation of Current Convolutional Architectures' Ability to Manage Nuisance Location and Scale Variability

We conduct an empirical study to test the ability of Convolutional Neural Networks (CNNs) to reduce the effects of nuisance transformations of the input data, such as location, scale and aspect ratio. We isolate factors by adopting a common convolutional architecture either deployed globally on the image to compute class posterior distributions, or restricted locally to compute class conditional distributions given location, scale and aspect ratios of bounding boxes determined by proposal heuristics. In theory, averaging the latter should yield inferior performance compared to proper marginalization. Yet empirical evidence suggests the converse, leading us to conclude that - at the current level of complexity of convolutional architectures and scale of the data sets used to train them - CNNs are not very effective at marginalizing nuisance variability. We also quantify the effects of context on the overall classification task and its impact on the performance of CNNs, and propose improved sampling techniques for heuristic proposal schemes that improve end-to-end performance to state-of-the-art levels. We test our hypothesis on a classification task using the ImageNet Challenge benchmark and on a wide-baseline matching task using the Oxford and Fischer's datasets.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

ShapeFit and ShapeKick for Robust, Scalable Structure from Motion

We introduce a new method for location recovery from pair-wise directions that leverages an efficient convex program that comes with exact recovery guarantees, even in the presence of adversarial outliers. When pairwise directions represent scaled relative positions between pairs of views (estimated for instance with epipolar geometry) our method can be used for location recovery, that is the determination of relative pose up to a single unknown scale. For this task, our method yields performance comparable to the state-of-the-art with an order of magnitude speed-up. Our proposed numerical framework is flexible in that it accommodates other approaches to location recovery and can be used to speed up other methods. These properties are demonstrated by extensively testing against state-of-the-art methods for location recovery on 13 large, irregular collections of images of real scenes in addition to simulated data with ground truth.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

Visual Representations: Defining Properties and Deep Approximations

Visual representations are defined in terms of minimal sufficient statistics of visual data, for a class of tasks, that are also invariant to nuisance variability. Minimal sufficiency guarantees that we can store a representation in lieu of raw data with smallest complexity and no performance loss on the task at hand. Invariance guarantees that the statistic is constant with respect to uninformative transformations of the data. We derive analytical expressions for such representations and show they are related to feature descriptors commonly used in computer vision, as well as to convolutional neural networks. This link highlights the assumptions and approximations tacitly assumed by these methods and explains empirical practices such as clamping, pooling and joint normalization.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

Boosting Convolutional Features for Robust Object Proposals

Deep Convolutional Neural Networks (CNNs) have demonstrated excellent performance in image classification, but still show room for improvement in object-detection tasks with many categories, in particular for cluttered scenes and occlusion. Modern detection algorithms like Regions with CNNs (Girshick et al., 2014) rely on Selective Search (Uijlings et al., 2013) to propose regions which with high probability represent objects, where in turn CNNs are deployed for classification. Selective Search represents a family of sophisticated algorithms that are engineered with multiple segmentation, appearance and saliency cues, typically coming with a significant run-time overhead. Furthermore, (Hosang et al., 2014) have shown that most methods suffer from low reproducibility due to unstable superpixels, even for slight image perturbations. Although CNNs are subsequently used for classification in top-performing object-detection pipelines, current proposal methods are agnostic to how these models parse objects and their rich learned representations. As a result they may propose regions which may not resemble high-level objects or totally miss some of them. To overcome these drawbacks we propose a boosting approach which directly takes advantage of hierarchical CNN features for detecting regions of interest fast. We demonstrate its performance on ImageNet 2013 detection benchmark and compare it with state-of-the-art methods.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

Domain-Size Pooling in Local Descriptors: DSP-SIFT

We introduce a simple modification of local image descriptors, such as SIFT, based on pooling gradient orientations across different domain sizes, in addition to spatial locations. The resulting descriptor, which we call DSP-SIFT, outperforms other methods in wide-baseline matching benchmarks, including those based on convolutional neural networks, despite having the same dimension of SIFT and requiring no training.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

Observability, Identifiability and Sensitivity of Vision-Aided Navigation

We analyze the observability of motion estimates from the fusion of visual and inertial sensors. Because the model contains unknown parameters, such as sensor biases, the problem is usually cast as a mixed identification/filtering, and the resulting observability analysis provides a necessary condition for any algorithm to converge to a unique point estimate. Unfortunately, most models treat sensor bias rates as noise, independent of other states including biases themselves, an assumption that is patently violated in practice. When this assumption is lifted, the resulting model is not observable, and therefore past analyses cannot be used to conclude that the set of states that are indistinguishable from the measurements is a singleton. In other words, the resulting model is not observable. We therefore re-cast the analysis as one of sensitivity: Rather than attempting to prove that the indistinguishable set is a singleton, which is not the case, we derive bounds on its volume, as a function of characteristics of the input and its sufficient excitation. This provides an explicit characterization of the indistinguishable set that can be used for analysis and validation purposes.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

Visual Scene Representations: Contrast, Scaling and Occlusion

We study the structure of representations, defined as approximations of minimal sufficient statistics that are maximal invariants to nuisance factors, for visual data subject to scaling and occlusion of line-of-sight. We derive analytical expressions for such representations and show that, under certain restrictive assumptions, they are related to features commonly in use in the computer vision community. This link highlights the condition tacitly assumed by these descriptors, and also suggests ways to improve and generalize them. This new interpretation draws connections to the classical theories of sampling, hypothesis testing and group invariance.

0 citations0 reviewsNo code linkedOpen access
preprint2014arXiv

Cavlectometry: Towards Holistic Reconstruction of Large Mirror Objects

We introduce a method based on the deflectometry principle for the reconstruction of specular objects exhibiting significant size and geometric complexity. A key feature of our approach is the deployment of an Automatic Virtual Environment (CAVE) as pattern generator. To unfold the full power of this extraordinary experimental setup, an optical encoding scheme is developed which accounts for the distinctive topology of the CAVE. Furthermore, we devise an algorithm for detecting the object of interest in raw deflectometric images. The segmented foreground is used for single-view reconstruction, the background for estimation of the camera pose, necessary for calibrating the sensor system. Experiments suggest a significant gain of coverage in single measurements compared to previous methods. To facilitate research on specular surface reconstruction, we will make our data set publicly available.

0 citations0 reviewsNo code linkedOpen access
preprint2014arXiv

Robust Inference for Visual-Inertial Sensor Fusion

Inference of three-dimensional motion from the fusion of inertial and visual sensory data has to contend with the preponderance of outliers in the latter. Robust filtering deals with the joint inference and classification task of selecting which data fits the model, and estimating its state. We derive the optimal discriminant and propose several approximations, some used in the literature, others new. We compare them analytically, by pointing to the assumptions underlying their approximations, and empirically. We show that the best performing method improves the performance of state-of-the-art visual-inertial sensor fusion systems, while retaining the same computational complexity.

0 citations0 reviewsNo code linkedOpen access
preprint2013arXiv

On the Design and Analysis of Multiple View Descriptors

We propose an extension of popular descriptors based on gradient orientation histograms (HOG, computed in a single image) to multiple views. It hinges on interpreting HOG as a conditional density in the space of sampled images, where the effects of nuisance factors such as viewpoint and illumination are marginalized. However, such marginalization is performed with respect to a very coarse approximation of the underlying distribution. Our extension leverages on the fact that multiple views of the same scene allow separating intrinsic from nuisance variability, and thus afford better marginalization of the latter. The result is a descriptor that has the same complexity of single-view HOG, and can be compared in the same manner, but exploits multiple views to better trade off insensitivity to nuisance variability with specificity to intrinsic variability. We also introduce a novel multi-view wide-baseline matching dataset, consisting of a mixture of real and synthetic objects with ground truthed camera motion and dense three-dimensional geometry.

0 citations0 reviewsNo code linkedOpen access
preprint2012arXiv

Information Forests

We describe Information Forests, an approach to classification that generalizes Random Forests by replacing the splitting criterion of non-leaf nodes from a discriminative one -- based on the entropy of the label distribution -- to a generative one -- based on maximizing the information divergence between the class-conditional distributions in the resulting partitions. The basic idea consists of deferring classification until a measure of "classification confidence" is sufficiently high, and instead breaking down the data so as to maximize this measure. In an alternative interpretation, Information Forests attempt to partition the data into subsets that are "as informative as possible" for the purpose of the task, which is to classify the data. Classification confidence, or informative content of the subsets, is quantified by the Information Divergence. Our approach relates to active learning, semi-supervised learning, mixed generative/discriminative learning.

0 citations0 reviewsNo code linkedOpen access
preprint2011arXiv

Detachable Object Detection: Segmentation and Depth Ordering From Short-Baseline Video

We describe an approach for segmenting an image into regions that correspond to surfaces in the scene that are partially surrounded by the medium. It integrates both appearance and motion statistics into a cost functional, that is seeded with occluded regions and minimized efficiently by solving a linear programming problem. Where a short observation time is insufficient to determine whether the object is detachable, the results of the minimization can be used to seed a more costly optimization based on a longer sequence of video data. The result is an entirely unsupervised scheme to detect and segment an arbitrary and unknown number of objects. We test our scheme to highlight the potential, as well as limitations, of our approach.

0 citations0 reviewsNo code linkedOpen access