BZPEERReading, trust and collaboration for research
Menu

Discover

GraphFollow connections around a paper, topic or saved view.

Workspaces

HomePick up where your research flow left off.InboxHandle requests, replies and notifications from one place.CollectionsCurate reading lists, evidence sets and shareable dossiers.ResearchSee your private provenance graph, trail and imports.CollaborationMove from discovery into focused discussion rooms.PublishDraft, preview and publish full-text research articles.

Network

ExpertsFind specialists worth following or asking for help.CommunitiesJoin research circles organized around shared work.PartnersSee external organizations active around the same topics.

Opportunities

ListingsBrowse roles, calls and collaborations with clearer fit signals.

Account

Log inReturn to your reading and collaboration workspace.Create accountStart saving work, following people and joining teams.
Log inCreate account

Researcher profile

Rui Ma

Rui Ma contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Computer VisionArtificial IntelligenceMachine Learningmath.NANumerical AnalysisComputation and Languageeess.IVeess.SPHardware Architecturecond-mat.softDistributed, Parallel, and Cluster Computingeess.ASGraphicsInformation RetrievalNetworking and Internet ArchitectureRoboticsSound

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
22works
0followers
17topics
4close collaborators

Actions

Decide how to stay connected

Follow researcher0

Identity and collaboration

How to connect with this researcher

Claiming links this public author record to a researcher profile and unlocks direct collaboration workflows.

Log in to claim

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

Research graph

See the researcher in context

Open full explorer

Inspect adjacent work, topics, institutions and collaborators without jumping out to a separate graph page.

Building this graph slice

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

Published work

22 published item(s)

preprint2026arXiv

MiMo-V2-Flash Technical Report

We present MiMo-V2-Flash, a Mixture-of-Experts (MoE) model with 309B total parameters and 15B active parameters, designed for fast, strong reasoning and agentic capabilities. MiMo-V2-Flash adopts a hybrid attention architecture that interleaves Sliding Window Attention (SWA) with global attention, with a 128-token sliding window under a 5:1 hybrid ratio. The model is pre-trained on 27 trillion tokens with Multi-Token Prediction (MTP), employing a native 32k context length and subsequently extended to 256k. To efficiently scale post-training compute, MiMo-V2-Flash introduces a novel Multi-Teacher On-Policy Distillation (MOPD) paradigm. In this framework, domain-specialized teachers (e.g., trained via large-scale reinforcement learning) provide dense and token-level reward, enabling the student model to perfectly master teacher expertise. MiMo-V2-Flash rivals top-tier open-weight models such as DeepSeek-V3.2 and Kimi-K2, despite using only 1/2 and 1/3 of their total parameters, respectively. During inference, by repurposing MTP as a draft model for speculative decoding, MiMo-V2-Flash achieves up to 3.6 acceptance length and 2.6x decoding speedup with three MTP layers. We open-source both the model weights and the three-layer MTP weights to foster open research and community collaboration.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

TeleCom-Bench: How Far Are Large Language Models from Industrial Telecommunication Applications?

While Large Language Models have achieved remarkable integration in various vertical scenarios, their deployment in the telecommunications domain remains exploratory due to the lack of a standardized evaluation framework. Current telecom benchmarks primarily focus on static, foundational knowledge and isolated atomic skills, neglecting the equipment-specific documentation and end-to-end industrial workflows essential for real-world production systems. To bridge this gap, we present TeleCom-Bench, a comprehensive benchmark comprising 12 evaluation sets with 22,678 curated samples, which evaluates LLMs across a synergistic hierarchy: (1) Multi-dimensional Knowledge Comprehension, which integrates telecommunication fundamentals, 3GPP protocols, and 5G network architecture with proprietary product knowledge across wired, core, and wireless networks via knowledge graph-driven synthesis; and (2)End-to-End Knowledge Application, which formalizes six core tasks on authentic trajectories from live network agent workflows, including intent recognition, entity extraction, event verification, tool invocation, root cause analysis, and solution generation-across network optimization and fault maintenance scenarios. Evaluations of eight state-of-the-art LLMs reveal a universal Execution Wall: while models achieve 90% accuracy in linguistic interface tasks such as intent recognition and entity extraction, performance collapses to approximately 30% in procedural execution tasks like solution generation. This capability gap demonstrates that current LLMs function competently as diagnosticians but fail as field engineers. TeleCom-Bench provides standardized diagnostics to precisely pinpoint this deficit, offering actionable guidance for domain-specific alignment toward production-ready telecom agents. The dataset and evaluation code have been released at https://github.com/ZTE-AICloud/TeleCom-Bench.

0 citations0 reviewsNo code linkedOpen access
preprint2025arXiv

MiMo-Audio: Audio Language Models are Few-Shot Learners

Existing audio language models typically rely on task-specific fine-tuning to accomplish particular audio tasks. In contrast, humans are able to generalize to new audio tasks with only a few examples or simple instructions. GPT-3 has shown that scaling next-token prediction pretraining enables strong generalization capabilities in text, and we believe this paradigm is equally applicable to the audio domain. By scaling MiMo-Audio's pretraining data to over one hundred million of hours, we observe the emergence of few-shot learning capabilities across a diverse set of audio tasks. We develop a systematic evaluation of these capabilities and find that MiMo-Audio-7B-Base achieves SOTA performance on both speech intelligence and audio understanding benchmarks among open-source models. Beyond standard metrics, MiMo-Audio-7B-Base generalizes to tasks absent from its training data, such as voice conversion, style transfer, and speech editing. MiMo-Audio-7B-Base also demonstrates powerful speech continuation capabilities, capable of generating highly realistic talk shows, recitations, livestreaming and debates. At the post-training stage, we curate a diverse instruction-tuning corpus and introduce thinking mechanisms into both audio understanding and generation. MiMo-Audio-7B-Instruct achieves open-source SOTA on audio understanding benchmarks (MMSU, MMAU, MMAR, MMAU-Pro), spoken dialogue benchmarks (Big Bench Audio, MultiChallenge Audio) and instruct-TTS evaluations, approaching or surpassing closed-source models. Model checkpoints and full evaluation suite are available at https://github.com/XiaomiMiMo/MiMo-Audio.

0 citations0 reviewsNo code linkedOpen access
preprint2024arXiv

3D-SSGAN: Lifting 2D Semantics for 3D-Aware Compositional Portrait Synthesis

Existing 3D-aware portrait synthesis methods can generate impressive high-quality images while preserving strong 3D consistency. However, most of them cannot support the fine-grained part-level control over synthesized images. Conversely, some GAN-based 2D portrait synthesis methods can achieve clear disentanglement of facial regions, but they cannot preserve view consistency due to a lack of 3D modeling abilities. To address these issues, we propose 3D-SSGAN, a novel framework for 3D-aware compositional portrait image synthesis. First, a simple yet effective depth-guided 2D-to-3D lifting module maps the generated 2D part features and semantics to 3D. Then, a volume renderer with a novel 3D-aware semantic mask renderer is utilized to produce the composed face features and corresponding masks. The whole framework is trained end-to-end by discriminating between real and synthesized 2D images and their semantic masks. Quantitative and qualitative evaluations demonstrate the superiority of 3D-SSGAN in controllable part-level synthesis while preserving 3D view consistency.

0 citations0 reviewsNo code linkedOpen access
preprint2023arXiv

P2M2-Net: Part-Aware Prompt-Guided Multimodal Point Cloud Completion

Inferring missing regions from severely occluded point clouds is highly challenging. Especially for 3D shapes with rich geometry and structure details, inherent ambiguities of the unknown parts are existing. Existing approaches either learn a one-to-one mapping in a supervised manner or train a generative model to synthesize the missing points for the completion of 3D point cloud shapes. These methods, however, lack the controllability for the completion process and the results are either deterministic or exhibiting uncontrolled diversity. Inspired by the prompt-driven data generation and editing, we propose a novel prompt-guided point cloud completion framework, coined P2M2-Net, to enable more controllable and more diverse shape completion. Given an input partial point cloud and a text prompt describing the part-aware information such as semantics and structure of the missing region, our Transformer-based completion network can efficiently fuse the multimodal features and generate diverse results following the prompt guidance. We train the P2M2-Net on a new large-scale PartNet-Prompt dataset and conduct extensive experiments on two challenging shape completion benchmarks. Quantitative and qualitative results show the efficacy of incorporating prompts for more controllable part-aware point cloud completion and generation. Code and data are available at https://github.com/JLU-ICL/P2M2-Net.

0 citations0 reviewsNo code linkedOpen access
preprint2023arXiv

P3DC-Shot: Prior-Driven Discrete Data Calibration for Nearest-Neighbor Few-Shot Classification

Nearest-Neighbor (NN) classification has been proven as a simple and effective approach for few-shot learning. The query data can be classified efficiently by finding the nearest support class based on features extracted by pretrained deep models. However, NN-based methods are sensitive to the data distribution and may produce false prediction if the samples in the support set happen to lie around the distribution boundary of different classes. To solve this issue, we present P3DC-Shot, an improved nearest-neighbor based few-shot classification method empowered by prior-driven data calibration. Inspired by the distribution calibration technique which utilizes the distribution or statistics of the base classes to calibrate the data for few-shot tasks, we propose a novel discrete data calibration operation which is more suitable for NN-based few-shot classification. Specifically, we treat the prototypes representing each base class as priors and calibrate each support data based on its similarity to different base prototypes. Then, we perform NN classification using these discretely calibrated support data. Results from extensive experiments on various datasets show our efficient non-learning based method can outperform or at least comparable to SOTA methods which need additional learning steps.

0 citations0 reviewsNo code linkedOpen access
preprint2023arXiv

Wrapping dynamics and full uptake conditions for nonspherical active nanoparticles

The cellular uptake of self-propelled nanoparticles (NPs) or viruses, usually nonspherical, by cell membrane is crucial in many biological processes. In this study, using Onsager variational principle, we obtain a general wrapping equation for nonspherical self-propelled nanoparticles. Two analytical critical conditions are theoretically derived, one for the continuous full uptake of prolate particles and the other for snapthrough full wrapping of oblate particles. They capture considerably well the full uptake critical boundaries in the phase diagrams constructed in terms of active force, aspect ratio, adhesion energy density, and membrane tension based on numerical calculations. It is found that enhancing activity (active force), reducing effective dynamic viscosity, increasing adhesion energy density, and decreasing membrane tension, can significantly improve the wrapping efficiency for the self-propelled particles. These results elucidate some of the previous specific investigations conclusively and may offer novel possibilities for designing an effective active NP-based vehicle for controlled drug delivery.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

CAEN: A Hierarchically Attentive Evolution Network for Item-Attribute-Change-Aware Recommendation in the Growing E-commerce Environment

Traditional recommendation systems mainly focus on modeling user interests. However, the dynamics of recommended items caused by attribute modifications (e.g. changes in prices) are also of great importance in real systems, especially in the fast-growing e-commerce environment, which may cause the users' demands to emerge, shift and disappear. Recent studies that make efforts on dynamic item representations treat the item attributes as side information but ignore its temporal dependency, or model the item evolution with a sequence of related users but do not consider item attributes. In this paper, we propose Core Attribute Evolution Network (CAEN), which partitions the user sequence according to the attribute value and thus models the item evolution over attribute dynamics with these users. Under this framework, we further devise a hierarchical attention mechanism that applies attribute-aware attention for user aggregation under each attribute, as well as personalized attention for activating similar users in assessing the matching degree between target user and item. Results from the extensive experiments over actual e-commerce datasets show that our approach outperforms the state-of-art methods and achieves significant improvements on the items with rapid changes over attributes, therefore helping the item recommendation to adapt to the growth of the e-commerce platform.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Domain Knowledge-Based Automated Analog Circuit Design with Deep Reinforcement Learning

The design automation of analog circuits is a longstanding challenge in the integrated circuit field. This paper presents a deep reinforcement learning method to expedite the design of analog circuits at the pre-layout stage, where the goal is to find device parameters to fulfill desired circuit specifications. Our approach is inspired by experienced human designers who rely on domain knowledge of analog circuit design (e.g., circuit topology and couplings between circuit specifications) to tackle the problem. Unlike all prior methods, our method originally incorporates such key domain knowledge into policy learning with a graph-based policy network, thereby best modeling the relations between circuit parameters and design targets. Experimental results on exemplary circuits show it achieves human-level design accuracy (~99%) with 1.5x efficiency of existing best-performing methods. Our method also shows better generalization ability to unseen specifications and optimality in circuit performance optimization. Moreover, it applies to designing diverse analog circuits across different semiconductor technologies, breaking the limitations of prior ad-hoc methods in designing one particular type of analog circuits with conventional semiconductor technology.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Domain Knowledge-Infused Deep Learning for Automated Analog/Radio-Frequency Circuit Parameter Optimization

The design automation of analog circuits is a longstanding challenge. This paper presents a reinforcement learning method enhanced by graph learning to automate the analog circuit parameter optimization at the pre-layout stage, i.e., finding device parameters to fulfill desired circuit specifications. Unlike all prior methods, our approach is inspired by human experts who rely on domain knowledge of analog circuit design (e.g., circuit topology and couplings between circuit specifications) to tackle the problem. By originally incorporating such key domain knowledge into policy training with a multimodal network, the method best learns the complex relations between circuit parameters and design targets, enabling optimal decisions in the optimization process. Experimental results on exemplary circuits show it achieves human-level design accuracy (99%) 1.5X efficiency of existing best-performing methods. Our method also shows better generalization ability to unseen specifications and optimality in circuit performance optimization. Moreover, it applies to design radio-frequency circuits on emerging semiconductor technologies, breaking the limitations of prior learning methods in designing conventional analog circuits.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Coding

Recently, learned image compression techniques have achieved remarkable performance, even surpassing the best manually designed lossy image coders. They are promising to be large-scale adopted. For the sake of practicality, a thorough investigation of the architecture design of learned image compression, regarding both compression performance and running speed, is essential. In this paper, we first propose uneven channel-conditional adaptive coding, motivated by the observation of energy compaction in learned image compression. Combining the proposed uneven grouping model with existing context models, we obtain a spatial-channel contextual adaptive model to improve the coding performance without damage to running speed. Then we study the structure of the main transform and propose an efficient model, ELIC, to achieve state-of-the-art speed and compression ability. With superior performance, the proposed model also supports extremely fast preview decoding and progressive decoding, which makes the coming application of learning-based image compression more promising.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

FD-CAM: Improving Faithfulness and Discriminability of Visual Explanation for CNNs

Class activation map (CAM) has been widely studied for visual explanation of the internal working mechanism of convolutional neural networks. The key of existing CAM-based methods is to compute effective weights to combine activation maps in the target convolution layer. Existing gradient and score based weighting schemes have shown superiority in ensuring either the discriminability or faithfulness of the CAM, but they normally cannot excel in both properties. In this paper, we propose a novel CAM weighting scheme, named FD-CAM, to improve both the faithfulness and discriminability of the CAM-based CNN visual explanation. First, we improve the faithfulness and discriminability of the score-based weights by performing a grouped channel switching operation. Specifically, for each channel, we compute its similarity group and switch the group of channels on or off simultaneously to compute changes in the class prediction score as the weights. Then, we combine the improved score-based weights with the conventional gradient-based weights so that the discriminability of the final CAM can be further improved. We perform extensive comparisons with the state-of-the-art CAM algorithms. The quantitative and qualitative results show our FD-CAM can produce more faithful and more discriminative visual explanations of the CNNs. We also conduct experiments to verify the effectiveness of the proposed grouped channel switching and weight combination scheme on improving the results. Our code is available at https://github.com/crishhh1998/FD-CAM.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

FPGA-based AI Smart NICs for Scalable Distributed AI Training Systems

Rapid advances in artificial intelligence (AI) technology have led to significant accuracy improvements in a myriad of application domains at the cost of larger and more compute-intensive models. Training such models on massive amounts of data typically requires scaling to many compute nodes and relies heavily on collective communication algorithms, such as all-reduce, to exchange the weight gradients between different nodes. The overhead of these collective communication operations in a distributed AI training system can bottleneck its performance, with more pronounced effects as the number of nodes increases. In this paper, we first characterize the all-reduce operation overhead by profiling distributed AI training. Then, we propose a new smart network interface card (NIC) for distributed AI training systems using field-programmable gate arrays (FPGAs) to accelerate all-reduce operations and optimize network bandwidth utilization via data compression. The AI smart NIC frees up the system's compute resources to perform the more compute-intensive tensor operations and increases the overall node-to-node communication efficiency. We perform real measurements on a prototype distributed AI training system comprised of 6 compute nodes to evaluate the performance gains of our proposed FPGA-based AI smart NIC compared to a baseline system with regular NICs. We also use these measurements to validate an analytical model that we formulate to predict performance when scaling to larger systems. Our proposed FPGA-based AI smart NIC enhances overall training performance by 1.6x at 6 nodes, with an estimated 2.5x performance improvement at 32 nodes, compared to the baseline system using conventional NICs.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

New conforming finite element divdiv complexes in three dimensions

In this paper, the first family of conforming finite element divdiv complexes on cuboid grids in three dimensions is constructed. Besides, a new family of conforming finite element divdiv complexes with enhanced smoothness on tetrahedral grids is presented. These complexes are exact in the sense that the range of each discrete map is the kernel space of the succeeding one.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Phase-SLAM: Phase Based Simultaneous Localization and Mapping for Mobile Structured Light Illumination Systems

Structured Light Illumination (SLI) systems have been used for reliable indoor dense 3D scanning via phase triangulation. However, mobile SLI systems for 360 degree 3D reconstruction demand 3D point cloud registration, involving high computational complexity. In this paper, we propose a phase based Simultaneous Localization and Mapping (Phase-SLAM) framework for fast and accurate SLI sensor pose estimation and 3D object reconstruction. The novelty of this work is threefold: (1) developing a reprojection model from 3D points to 2D phase data towards phase registration with low computational complexity; (2) developing a local optimizer to achieve SLI sensor pose estimation (odometry) using the derived Jacobian matrix for the 6 DoF variables; (3) developing a compressive phase comparison method to achieve high-efficiency loop closure detection. The whole Phase-SLAM pipeline is then exploited using existing global pose graph optimization techniques. We build datasets from both the unreal simulation platform and a robotic arm based SLI system in real-world to verify the proposed approach. The experiment results demonstrate that the proposed Phase-SLAM outperforms other state-of-the-art methods in terms of the efficiency and accuracy of pose estimation and 3D reconstruction. The open-source code is available at https://github.com/ZHENGXi-git/Phase-SLAM.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Practical Learned Lossless JPEG Recompression with Multi-Level Cross-Channel Entropy Model in the DCT Domain

JPEG is a popular image compression method widely used by individuals, data center, cloud storage and network filesystems. However, most recent progress on image compression mainly focuses on uncompressed images while ignoring trillions of already-existing JPEG images. To compress these JPEG images adequately and restore them back to JPEG format losslessly when needed, we propose a deep learning based JPEG recompression method that operates on DCT domain and propose a Multi-Level Cross-Channel Entropy Model to compress the most informative Y component. Experiments show that our method achieves state-of-the-art performance compared with traditional JPEG recompression methods including Lepton, JPEG XL and CMIX. To the best of our knowledge, this is the first learned compression method that losslessly transcodes JPEG images to more storage-saving bitstreams.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

A Modular 1D-CNN Architecture for Real-time Digital Pre-distortion

This study reports a novel hardware-friendly modular architecture for implementing one dimensional convolutional neural network (1D-CNN) digital predistortion (DPD) technique to linearize RF power amplifier (PA) real-time.The modular nature of our design enables DPD system adaptation for variable resource and timing constraints.Our work also presents a co-simulation architecture to verify the DPD performance with an actual power amplifier hardware-in-the-loop.The experimental results with 100 MHz signals show that the proposed 1D-CNN obtains superior performance compared with other neural network architectures for real-time DPD application.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Closed-loop Feedback Registration for Consecutive Images of Moving Flexible Targets

Advancement of imaging techniques enables consecutive image sequences to be acquired for quality monitoring of manufacturing production lines. Registration for these image sequences is essential for in-line pattern inspection and metrology, e.g., in the printing process of flexible electronics. However, conventional image registration algorithms cannot produce accurate results when the images contain many similar and deformable patterns in the manufacturing process. Such a failure originates from a fact that the conventional algorithms only use the spatial and pixel intensity information for registration. Considering the nature of temporal continuity and consecution of the product images, in this paper, we propose a closed-loop feedback registration algorithm for matching and stitching the deformable printed patterns on a moving flexible substrate. The algorithm leverages the temporal and spatial relationships of the consecutive images and the continuity of the image sequence for fast, accurate, and robust point matching. Our experimental results show that our algorithm can find more matching point pairs with a lower root mean squared error (RMSE) compared to other state-of-the-art algorithms while offering significant improvements to running time.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Conforming finite element DIVDIV complexes and the application for the linearized Einstein-Bianchi system

This paper presents the first family of conforming finite element divdiv complexes on tetrahedral grids in three dimensions. In these complexes, finite element spaces of $H(\text{divdiv},Ω;\mathbb{S})$ are from a current preprint [Chen and Huang, arXiv: 2007.12399, 2020] while finite element spaces of both $H(\text{symcurl},Ω;\mathbb{T})$ and $H^1(Ω;\mathbb{R}^3)$ are newly constructed here. It is proved that these finite element complexes are exact. As a result, they can be used to discretize the linearized Einstein-Bianchi system within the dual formulation.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

An adaptive finite element scheme for the Hellinger--Reissner elasticity mixed eigenvalue problem

In this paper we study the approximation of eigenvalues arising from the mixed Hellinger--Reissner elasticity problem by using the simple finite element using partial relaxation of $C^0$ vertex continuity of stresses introduced recently by Jun Hu and Rui Ma. We prove that the method converge when a residual type error estimator is considered and that the estimator decays optimally with respect to the number of degrees of freedom.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Energy Efficient Software Matching in Distributed Vehicular Fog Based Architecture with Cloud and Fixed Fog Nodes

The rapid development of vehicles on-board units and the proliferation of autonomous vehicles in modern cities create a potential for a new fog computing paradigm, referred to as vehicular fog computing (VFC). In this paper, we propose an architecture that integrates a vehicular fog (VF) composed of vehicles clustered in a parking lot with a fixed fog node at the access network and the central cloud. We investigate the problem of energy efficient software matching in the VF considering different approaches to deploy software packages in vehicles.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

MDSSD: Multi-scale Deconvolutional Single Shot Detector for Small Objects

For most of the object detectors based on multi-scale feature maps, the shallow layers are rich in fine spatial information and thus mainly responsible for small object detection. The performance of small object detection, however, is still less than satisfactory because of the deficiency of semantic information on shallow feature maps. In this paper, we design a Multi-scale Deconvolutional Single Shot Detector (MDSSD), especially for small object detection. In MDSSD, multiple high-level feature maps at different scales are upsampled simultaneously to increase the spatial resolution. Afterwards, we implement the skip connections with low-level feature maps via Fusion Block. The fusion feature maps, named Fusion Module, are of strong feature representational power of small instances. It is noteworthy that these high-level feature maps utilized in Fusion Block preserve both strong semantic information and some fine details of small instances, rather than the top-most layer where the representation of fine details for small objects are potentially wiped out. The proposed framework achieves 77.6% mAP for small object detection on the challenging dataset TT100K with 512 x 512 input, outperforming other detectors with a large margin. Moreover, it can also achieve state-of-the-art results for general object detection on PASCAL VOC2007 test and MS COCO test-dev2015, especially achieving 2 to 5 points improvement on small object categories.

0 citations0 reviewsNo code linkedOpen access