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

Hervé Jégou

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

ResearcherUnclaimed source record
Computer VisionMachine LearningInformation RetrievalInformation Theorymath.ITComputation and LanguageCryptography and SecurityDatabaseseess.IVNetworking and Internet Architecture

Catalog footprint

What is connected

20works
10topics
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

20 published item(s)

preprint2026arXiv

Self-Pruned Key-Value Attention: Learning When to Write by Predicting Future Utility

Under modern test-time compute and agentic paradigms, language models process ever-longer sequences. Efficient text generation with transformer architectures is increasingly constrained by the Key-Value cache memory footprint and bandwidth. To address this limitation, we introduce Self-Pruned Key-Value Attention (SP-KV), a mechanism designed to predict future KV utility in order to reduce the size of the long-term KV cache. This strategy operates at a fine granularity: a lightweight utility predictor scores each key-value pair, and while recent KVs are always available via a local window, older pairs are written in the cache and used in global attention only if their predicted utility surpasses a given threshold. The LLM and the utility predictor are trained jointly end-to-end exclusively through next-token prediction loss, and are adapted from pretrained LLM checkpoints. Rather than enforcing a fixed compression ratio, SP-KV performs dynamic sparsification: the mechanism adapts to the input and typically reduces the KV cache size by a factor of $3$ to $10\times$, longer sequences often being more compressible. This leads to vast improvements in memory usage and decoding speed, with little to no degradation of validation loss nor performance on a broad set of downstream tasks. Beyond serving as an effective KV-cache reduction mechanism, our method reveals structured layer- and head-specific sparsity patterns that we can use to guide the design of hybrid local-global attention architectures.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

DeiT III: Revenge of the ViT

A Vision Transformer (ViT) is a simple neural architecture amenable to serve several computer vision tasks. It has limited built-in architectural priors, in contrast to more recent architectures that incorporate priors either about the input data or of specific tasks. Recent works show that ViTs benefit from self-supervised pre-training, in particular BerT-like pre-training like BeiT. In this paper, we revisit the supervised training of ViTs. Our procedure builds upon and simplifies a recipe introduced for training ResNet-50. It includes a new simple data-augmentation procedure with only 3 augmentations, closer to the practice in self-supervised learning. Our evaluations on Image classification (ImageNet-1k with and without pre-training on ImageNet-21k), transfer learning and semantic segmentation show that our procedure outperforms by a large margin previous fully supervised training recipes for ViT. It also reveals that the performance of our ViT trained with supervision is comparable to that of more recent architectures. Our results could serve as better baselines for recent self-supervised approaches demonstrated on ViT.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Fixing the train-test resolution discrepancy

Data-augmentation is key to the training of neural networks for image classification. This paper first shows that existing augmentations induce a significant discrepancy between the typical size of the objects seen by the classifier at train and test time. We experimentally validate that, for a target test resolution, using a lower train resolution offers better classification at test time. We then propose a simple yet effective and efficient strategy to optimize the classifier performance when the train and test resolutions differ. It involves only a computationally cheap fine-tuning of the network at the test resolution. This enables training strong classifiers using small training images. For instance, we obtain 77.1% top-1 accuracy on ImageNet with a ResNet-50 trained on 128x128 images, and 79.8% with one trained on 224x224 image. In addition, if we use extra training data we get 82.5% with the ResNet-50 train with 224x224 images. Conversely, when training a ResNeXt-101 32x48d pre-trained in weakly-supervised fashion on 940 million public images at resolution 224x224 and further optimizing for test resolution 320x320, we obtain a test top-1 accuracy of 86.4% (top-5: 98.0%) (single-crop). To the best of our knowledge this is the highest ImageNet single-crop, top-1 and top-5 accuracy to date.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Three things everyone should know about Vision Transformers

After their initial success in natural language processing, transformer architectures have rapidly gained traction in computer vision, providing state-of-the-art results for tasks such as image classification, detection, segmentation, and video analysis. We offer three insights based on simple and easy to implement variants of vision transformers. (1) The residual layers of vision transformers, which are usually processed sequentially, can to some extent be processed efficiently in parallel without noticeably affecting the accuracy. (2) Fine-tuning the weights of the attention layers is sufficient to adapt vision transformers to a higher resolution and to other classification tasks. This saves compute, reduces the peak memory consumption at fine-tuning time, and allows sharing the majority of weights across tasks. (3) Adding MLP-based patch pre-processing layers improves Bert-like self-supervised training based on patch masking. We evaluate the impact of these design choices using the ImageNet-1k dataset, and confirm our findings on the ImageNet-v2 test set. Transfer performance is measured across six smaller datasets.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Watermarking Images in Self-Supervised Latent Spaces

We revisit watermarking techniques based on pre-trained deep networks, in the light of self-supervised approaches. We present a way to embed both marks and binary messages into their latent spaces, leveraging data augmentation at marking time. Our method can operate at any resolution and creates watermarks robust to a broad range of transformations (rotations, crops, JPEG, contrast, etc). It significantly outperforms the previous zero-bit methods, and its performance on multi-bit watermarking is on par with state-of-the-art encoder-decoder architectures trained end-to-end for watermarking. The code is available at github.com/facebookresearch/ssl_watermarking

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Training data-efficient image transformers & distillation through attention

Recently, neural networks purely based on attention were shown to address image understanding tasks such as image classification. However, these visual transformers are pre-trained with hundreds of millions of images using an expensive infrastructure, thereby limiting their adoption. In this work, we produce a competitive convolution-free transformer by training on Imagenet only. We train them on a single computer in less than 3 days. Our reference vision transformer (86M parameters) achieves top-1 accuracy of 83.1% (single-crop evaluation) on ImageNet with no external data. More importantly, we introduce a teacher-student strategy specific to transformers. It relies on a distillation token ensuring that the student learns from the teacher through attention. We show the interest of this token-based distillation, especially when using a convnet as a teacher. This leads us to report results competitive with convnets for both Imagenet (where we obtain up to 85.2% accuracy) and when transferring to other tasks. We share our code and models.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Training Vision Transformers for Image Retrieval

Transformers have shown outstanding results for natural language understanding and, more recently, for image classification. We here extend this work and propose a transformer-based approach for image retrieval: we adopt vision transformers for generating image descriptors and train the resulting model with a metric learning objective, which combines a contrastive loss with a differential entropy regularizer. Our results show consistent and significant improvements of transformers over convolution-based approaches. In particular, our method outperforms the state of the art on several public benchmarks for category-level retrieval, namely Stanford Online Product, In-Shop and CUB-200. Furthermore, our experiments on ROxford and RParis also show that, in comparable settings, transformers are competitive for particular object retrieval, especially in the regime of short vector representations and low-resolution images.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Powers of layers for image-to-image translation

We propose a simple architecture to address unpaired image-to-image translation tasks: style or class transfer, denoising, deblurring, deblocking, etc. We start from an image autoencoder architecture with fixed weights. For each task we learn a residual block operating in the latent space, which is iteratively called until the target domain is reached. A specific training schedule is required to alleviate the exponentiation effect of the iterations. At test time, it offers several advantages: the number of weight parameters is limited and the compositional design allows one to modulate the strength of the transformation with the number of iterations. This is useful, for instance, when the type or amount of noise to suppress is not known in advance. Experimentally, we provide proofs of concepts showing the interest of our method for many transformations. The performance of our model is comparable or better than CycleGAN with significantly fewer parameters.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Radioactive data: tracing through training

We want to detect whether a particular image dataset has been used to train a model. We propose a new technique, \emph{radioactive data}, that makes imperceptible changes to this dataset such that any model trained on it will bear an identifiable mark. The mark is robust to strong variations such as different architectures or optimization methods. Given a trained model, our technique detects the use of radioactive data and provides a level of confidence (p-value). Our experiments on large-scale benchmarks (Imagenet), using standard architectures (Resnet-18, VGG-16, Densenet-121) and training procedures, show that we can detect usage of radioactive data with high confidence (p<10^-4) even when only 1% of the data used to trained our model is radioactive. Our method is robust to data augmentation and the stochasticity of deep network optimization. As a result, it offers a much higher signal-to-noise ratio than data poisoning and backdoor methods.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

Approximate search with quantized sparse representations

This paper tackles the task of storing a large collection of vectors, such as visual descriptors, and of searching in it. To this end, we propose to approximate database vectors by constrained sparse coding, where possible atom weights are restricted to belong to a finite subset. This formulation encompasses, as particular cases, previous state-of-the-art methods such as product or residual quantization. As opposed to traditional sparse coding methods, quantized sparse coding includes memory usage as a design constraint, thereby allowing us to index a large collection such as the BIGANN billion-sized benchmark. Our experiments, carried out on standard benchmarks, show that our formulation leads to competitive solutions when considering different trade-offs between learning/coding time, index size and search quality.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

Interferences in match kernels

We consider the design of an image representation that embeds and aggregates a set of local descriptors into a single vector. Popular representations of this kind include the bag-of-visual-words, the Fisher vector and the VLAD. When two such image representations are compared with the dot-product, the image-to-image similarity can be interpreted as a match kernel. In match kernels, one has to deal with interference, i.e. with the fact that even if two descriptors are unrelated, their matching score may contribute to the overall similarity. We formalise this problem and propose two related solutions, both aimed at equalising the individual contributions of the local descriptors in the final representation. These methods modify the aggregation stage by including a set of per-descriptor weights. They differ by the objective function that is optimised to compute those weights. The first is a "democratisation" strategy that aims at equalising the relative importance of each descriptor in the set comparison metric. The second one involves equalising the match of a single descriptor to the aggregated vector. These concurrent methods give a substantial performance boost over the state of the art in image search with short or mid-size vectors, as demonstrated by our experiments on standard public image retrieval benchmarks.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

Particular object retrieval with integral max-pooling of CNN activations

Recently, image representation built upon Convolutional Neural Network (CNN) has been shown to provide effective descriptors for image search, outperforming pre-CNN features as short-vector representations. Yet such models are not compatible with geometry-aware re-ranking methods and still outperformed, on some particular object retrieval benchmarks, by traditional image search systems relying on precise descriptor matching, geometric re-ranking, or query expansion. This work revisits both retrieval stages, namely initial search and re-ranking, by employing the same primitive information derived from the CNN. We build compact feature vectors that encode several image regions without the need to feed multiple inputs to the network. Furthermore, we extend integral images to handle max-pooling on convolutional layer activations, allowing us to efficiently localize matching objects. The resulting bounding box is finally used for image re-ranking. As a result, this paper significantly improves existing CNN-based recognition pipeline: We report for the first time results competing with traditional methods on the challenging Oxford5k and Paris6k datasets.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

Tubelets: Unsupervised action proposals from spatiotemporal super-voxels

This paper considers the problem of localizing actions in videos as a sequences of bounding boxes. The objective is to generate action proposals that are likely to include the action of interest, ideally achieving high recall with few proposals. Our contributions are threefold. First, inspired by selective search for object proposals, we introduce an approach to generate action proposals from spatiotemporal super-voxels in an unsupervised manner, we call them Tubelets. Second, along with the static features from individual frames our approach advantageously exploits motion. We introduce independent motion evidence as a feature to characterize how the action deviates from the background and explicitly incorporate such motion information in various stages of the proposal generation. Finally, we introduce spatiotemporal refinement of Tubelets, for more precise localization of actions, and pruning to keep the number of Tubelets limited. We demonstrate the suitability of our approach by extensive experiments for action proposal quality and action localization on three public datasets: UCF Sports, MSR-II and UCF101. For action proposal quality, our unsupervised proposals beat all other existing approaches on the three datasets. For action localization, we show top performance on both the trimmed videos of UCF Sports and UCF101 as well as the untrimmed videos of MSR-II.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

A comparison of dense region detectors for image search and fine-grained classification

We consider a pipeline for image classification or search based on coding approaches like Bag of Words or Fisher vectors. In this context, the most common approach is to extract the image patches regularly in a dense manner on several scales. This paper proposes and evaluates alternative choices to extract patches densely. Beyond simple strategies derived from regular interest region detectors, we propose approaches based on super-pixels, edges, and a bank of Zernike filters used as detectors. The different approaches are evaluated on recent image retrieval and fine-grain classification benchmarks. Our results show that the regular dense detector is outperformed by other methods in most situations, leading us to improve the state of the art in comparable setups on standard retrieval and fined-grain benchmarks. As a byproduct of our study, we show that existing methods for blob and super-pixel extraction achieve high accuracy if the patches are extracted along the edges and not around the detected regions.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

Circulant temporal encoding for video retrieval and temporal alignment

We address the problem of specific video event retrieval. Given a query video of a specific event, e.g., a concert of Madonna, the goal is to retrieve other videos of the same event that temporally overlap with the query. Our approach encodes the frame descriptors of a video to jointly represent their appearance and temporal order. It exploits the properties of circulant matrices to efficiently compare the videos in the frequency domain. This offers a significant gain in complexity and accurately localizes the matching parts of videos. The descriptors can be compressed in the frequency domain with a product quantizer adapted to complex numbers. In this case, video retrieval is performed without decompressing the descriptors. We also consider the temporal alignment of a set of videos. We exploit the matching confidence and an estimate of the temporal offset computed for all pairs of videos by our retrieval approach. Our robust algorithm aligns the videos on a global timeline by maximizing the set of temporally consistent matches. The global temporal alignment enables synchronous playback of the videos of a given scene.

0 citations0 reviewsNo code linkedOpen access
preprint2014arXiv

Orientation covariant aggregation of local descriptors with embeddings

Image search systems based on local descriptors typically achieve orientation invariance by aligning the patches on their dominant orientations. Albeit successful, this choice introduces too much invariance because it does not guarantee that the patches are rotated consistently. This paper introduces an aggregation strategy of local descriptors that achieves this covariance property by jointly encoding the angle in the aggregation stage in a continuous manner. It is combined with an efficient monomial embedding to provide a codebook-free method to aggregate local descriptors into a single vector representation. Our strategy is also compatible and employed with several popular encoding methods, in particular bag-of-words, VLAD and the Fisher vector. Our geometric-aware aggregation strategy is effective for image search, as shown by experiments performed on standard benchmarks for image and particular object retrieval, namely Holidays and Oxford buildings.

0 citations0 reviewsNo code linkedOpen access
preprint2011arXiv

Anti-sparse coding for approximate nearest neighbor search

This paper proposes a binarization scheme for vectors of high dimension based on the recent concept of anti-sparse coding, and shows its excellent performance for approximate nearest neighbor search. Unlike other binarization schemes, this framework allows, up to a scaling factor, the explicit reconstruction from the binary representation of the original vector. The paper also shows that random projections which are used in Locality Sensitive Hashing algorithms, are significantly outperformed by regular frames for both synthetic and real data if the number of bits exceeds the vector dimensionality, i.e., when high precision is required.

0 citations0 reviewsNo code linkedOpen access
preprint2011arXiv

Searching in one billion vectors: re-rank with source coding

Recent indexing techniques inspired by source coding have been shown successful to index billions of high-dimensional vectors in memory. In this paper, we propose an approach that re-ranks the neighbor hypotheses obtained by these compressed-domain indexing methods. In contrast to the usual post-verification scheme, which performs exact distance calculation on the short-list of hypotheses, the estimated distances are refined based on short quantization codes, to avoid reading the full vectors from disk. We have released a new public dataset of one billion 128-dimensional vectors and proposed an experimental setup to evaluate high dimensional indexing algorithms on a realistic scale. Experiments show that our method accurately and efficiently re-ranks the neighbor hypotheses using little memory compared to the full vectors representation.

0 citations0 reviewsNo code linkedOpen access
preprint2010arXiv

Balancing clusters to reduce response time variability in large scale image search

Many algorithms for approximate nearest neighbor search in high-dimensional spaces partition the data into clusters. At query time, in order to avoid exhaustive search, an index selects the few (or a single) clusters nearest to the query point. Clusters are often produced by the well-known $k$-means approach since it has several desirable properties. On the downside, it tends to produce clusters having quite different cardinalities. Imbalanced clusters negatively impact both the variance and the expectation of query response times. This paper proposes to modify $k$-means centroids to produce clusters with more comparable sizes without sacrificing the desirable properties. Experiments with a large scale collection of image descriptors show that our algorithm significantly reduces the variance of response times without seriously impacting the search quality.

0 citations0 reviewsNo code linkedOpen access
preprint2006arXiv

Synchronization recovery and state model reduction for soft decoding of variable length codes

Variable length codes exhibit de-synchronization problems when transmitted over noisy channels. Trellis decoding techniques based on Maximum A Posteriori (MAP) estimators are often used to minimize the error rate on the estimated sequence. If the number of symbols and/or bits transmitted are known by the decoder, termination constraints can be incorporated in the decoding process. All the paths in the trellis which do not lead to a valid sequence length are suppressed. This paper presents an analytic method to assess the expected error resilience of a VLC when trellis decoding with a sequence length constraint is used. The approach is based on the computation, for a given code, of the amount of information brought by the constraint. It is then shown that this quantity as well as the probability that the VLC decoder does not re-synchronize in a strict sense, are not significantly altered by appropriate trellis states aggregation. This proves that the performance obtained by running a length-constrained Viterbi decoder on aggregated state models approaches the one obtained with the bit/symbol trellis, with a significantly reduced complexity. It is then shown that the complexity can be further decreased by projecting the state model on two state models of reduced size.

0 citations0 reviewsNo code linkedOpen access