{"total":224,"rows":[{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579,"area":null},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803,"area":null},{"id":"2107.14795","title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","created":"2021-07-30","cited_by_count":629,"area":null},{"id":"2204.00598","title":"Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language","created":"2022-04-01","cited_by_count":513,"area":"lr"},{"id":"2211.09788","title":"DiffusionDet: Diffusion Model for Object Detection","created":"2022-11-17","cited_by_count":354,"area":"diffusion"},{"id":"2106.07139","title":"Pre-Trained Models: Past, Present and Future","created":"2021-06-14","cited_by_count":319,"area":null},{"id":"2101.09671","title":"Pruning and Quantization for Deep Neural Network Acceleration: A Survey","created":"2021-01-24","cited_by_count":263,"area":null},{"id":"2108.07755","title":"TOOD: Task-aligned One-stage Object Detection","created":"2021-08-17","cited_by_count":218,"area":null},{"id":"2202.09741","title":"Visual Attention Network","created":"2022-02-20","cited_by_count":210,"area":null},{"id":"2205.13543","title":"Revealing the Dark Secrets of Masked Image Modeling","created":"2022-05-26","cited_by_count":117,"area":null},{"id":"2103.04505","title":"Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challenges","created":"2021-03-08","cited_by_count":115,"area":"inference"},{"id":"2105.13381","title":"Recent advances and clinical applications of deep learning in medical image analysis","created":"2021-05-27","cited_by_count":104,"area":null},{"id":"2103.04379","title":"Repurposing GANs for One-shot Semantic Part Segmentation","created":"2021-03-07","cited_by_count":88,"area":null},{"id":"2203.16507","title":"AdaMixer: A Fast-Converging Query-Based Object Detector","created":"2022-03-30","cited_by_count":79,"area":null},{"id":"2107.11279","title":"Re-distributing Biased Pseudo Labels for Semi-supervised Semantic Segmentation: A Baseline Investigation","created":"2021-07-23","cited_by_count":78,"area":null},{"id":"2101.11282","title":"Deep Learning for Instance Retrieval: A Survey","created":"2021-01-27","cited_by_count":70,"area":null},{"id":"2205.07877","title":"A Comprehensive Survey on Model Quantization for Deep Neural Networks in Image Classification","created":"2022-05-14","cited_by_count":65,"area":null},{"id":"2101.09336","title":"A Comprehensive Survey on Hardware-Aware Neural Architecture Search","created":"2021-01-22","cited_by_count":61,"area":null},{"id":"2105.06804","title":"Locate and Label: A Two-stage Identifier for Nested Named Entity Recognition","created":"2021-05-14","cited_by_count":61,"area":null},{"id":"2303.02936","title":"UniHCP: A Unified Model for Human-Centric Perceptions","created":"2023-03-06","cited_by_count":59,"area":null},{"id":"2201.05867","title":"Transferability in Deep Learning: A Survey","created":"2022-01-15","cited_by_count":57,"area":null},{"id":"2301.04944","title":"ViTs for SITS: Vision Transformers for Satellite Image Time Series","created":"2023-01-12","cited_by_count":56,"area":null},{"id":"2306.02572","title":"Introduction to Latent Variable Energy-Based Models: A Path Towards Autonomous Machine Intelligence","created":"2023-06-05","cited_by_count":56,"area":null},{"id":"2312.15172","title":"Pre-trained Trojan Attacks for Visual Recognition","created":"2023-12-23","cited_by_count":39,"area":"safety"},{"id":"2101.07422","title":"SOSD-Net: Joint Semantic Object Segmentation and Depth Estimation from Monocular images","created":"2021-01-19","cited_by_count":33,"area":null},{"id":"2111.08687","title":"INTERN: A New Learning Paradigm Towards General Vision","created":"2021-11-16","cited_by_count":33,"area":null},{"id":"2108.12102","title":"FOVEA: Foveated Image Magnification for Autonomous Navigation","created":"2021-08-27","cited_by_count":32,"area":null},{"id":"2109.02832","title":"Besov Function Approximation and Binary Classification on Low-Dimensional Manifolds Using Convolutional Residual Networks","created":"2021-09-07","cited_by_count":32,"area":null},{"id":"2108.07020","title":"Towards Real-World Prohibited Item Detection: A Large-Scale X-ray Benchmark","created":"2021-08-16","cited_by_count":31,"area":null},{"id":"2312.12664","title":"UnionDet: Union-Level Detector Towards Real-Time Human-Object Interaction Detection","created":"2023-12-19","cited_by_count":31,"area":null},{"id":"2211.04324","title":"Machine Learning-Aided Operations and Communications of Unmanned Aerial Vehicles: A Contemporary Survey","created":"2022-11-07","cited_by_count":28,"area":null},{"id":"2107.14110","title":"Enhancing Adversarial Robustness via Test-time Transformation Ensembling","created":"2021-07-29","cited_by_count":27,"area":null},{"id":"2110.03861","title":"QTN-VQC: An End-to-End Learning framework for Quantum Neural Networks","created":"2021-10-06","cited_by_count":27,"area":null},{"id":"2103.13933","title":"Unmanned Aerial Vehicle Visual Detection and Tracking using Deep Neural Networks: A Performance Benchmark","created":"2021-03-25","cited_by_count":25,"area":null},{"id":"2208.10244","title":"Unit Testing for Concepts in Neural Networks","created":"2022-07-28","cited_by_count":23,"area":null},{"id":"2105.07140","title":"NeuroGen: activation optimized image synthesis for discovery neuroscience","created":"2021-05-15","cited_by_count":22,"area":null},{"id":"2106.09748","title":"DeepLab2: A TensorFlow Library for Deep Labeling","created":"2021-06-17","cited_by_count":22,"area":null},{"id":"2108.01344","title":"Adaptive Affinity Loss and Erroneous Pseudo-Label Refinement for Weakly Supervised Semantic Segmentation","created":"2021-08-03","cited_by_count":22,"area":null},{"id":"2308.06173","title":"Physical Adversarial Attacks For Camera-based Smart Systems: Current Trends, Categorization, Applications, Research Challenges, and Future Outlook","created":"2023-08-11","cited_by_count":20,"area":null},{"id":"2208.08741","title":"Quantifying the Knowledge in a DNN to Explain Knowledge Distillation for Classification","created":"2022-08-18","cited_by_count":19,"area":"distill"},{"id":"2304.07574","title":"Exploring Incompatible Knowledge Transfer in Few-shot Image Generation","created":"2023-04-15","cited_by_count":19,"area":null},{"id":"2106.06418","title":"Scale-invariant scale-channel networks: Deep networks that generalise to previously unseen scales","created":"2021-06-11","cited_by_count":17,"area":null},{"id":"2211.10763","title":"PIDray: A Large-scale X-ray Benchmark for Real-World Prohibited Item Detection","created":"2022-11-19","cited_by_count":17,"area":null},{"id":"2404.12699","title":"SOPHON: Non-Fine-Tunable Learning to Restrain Task Transferability For Pre-trained Models","created":"2024-04-19","cited_by_count":17,"area":null},{"id":"2102.04738","title":"End-to-End Deep Learning of Lane Detection and Path Prediction for Real-Time Autonomous Driving","created":"2021-02-09","cited_by_count":16,"area":"driving"},{"id":"2107.04419","title":"Form2Seq : A Framework for Higher-Order Form Structure Extraction","created":"2021-07-09","cited_by_count":16,"area":null},{"id":"2109.11906","title":"RSDet++: Point-based Modulated Loss for More Accurate Rotated Object Detection","created":"2021-09-24","cited_by_count":16,"area":null},{"id":"2106.15287","title":"Tackling Catastrophic Forgetting and Background Shift in Continual Semantic Segmentation","created":"2021-06-29","cited_by_count":15,"area":null},{"id":"2504.03724","title":"CrowdVLM-R1: Expanding R1 Ability to Vision Language Model for Crowd Counting using Fuzzy Group Relative Policy Reward","created":"2025-03-31","cited_by_count":15,"area":"lr"},{"id":"2104.00613","title":"The surprising impact of mask-head architecture on novel class segmentation","created":"2021-04-01","cited_by_count":13,"area":null},{"id":"2103.04032","title":"CAM-GAN: Continual Adaptation Modules for Generative Adversarial Networks","created":"2021-03-06","cited_by_count":12,"area":null},{"id":"2105.03148","title":"A State-of-the-art Survey of Object Detection Techniques in Microorganism Image Analysis: From Classical Methods to Deep Learning Approaches","created":"2021-05-07","cited_by_count":12,"area":null},{"id":"2106.03487","title":"Exploiting Emotional Dependencies with Graph Convolutional Networks for Facial Expression Recognition","created":"2021-06-07","cited_by_count":12,"area":null},{"id":"2202.02245","title":"Personalized visual encoding model construction with small data","created":"2022-02-04","cited_by_count":12,"area":null},{"id":"2303.01734","title":"AdvART: Adversarial Art for Camouflaged Object Detection Attacks","created":"2023-03-03","cited_by_count":12,"area":null},{"id":"2310.03295","title":"Can pre-trained models assist in dataset distillation?","created":"2023-10-05","cited_by_count":12,"area":null},{"id":"2106.00116","title":"Effect of Pre-Training Scale on Intra- and Inter-Domain Full and Few-Shot Transfer Learning for Natural and Medical X-Ray Chest Images","created":"2021-05-31","cited_by_count":11,"area":null},{"id":"2108.00584","title":"Congested Crowd Instance Localization with Dilated Convolutional Swin Transformer","created":"2021-08-02","cited_by_count":11,"area":null},{"id":"2111.09957","title":"Rethinking Dilated Convolution for Real-time Semantic Segmentation","created":"2021-11-18","cited_by_count":11,"area":null},{"id":"2204.12974","title":"CapOnImage: Context-driven Dense-Captioning on Image","created":"2022-04-27","cited_by_count":11,"area":null},{"id":"2402.08823","title":"Random Representations Outperform Online Continually Learned Representations","created":"2024-02-13","cited_by_count":11,"area":null},{"id":"2102.03602","title":"Gated3D: Monocular 3D Object Detection From Temporal Illumination Cues","created":"2021-02-06","cited_by_count":10,"area":null},{"id":"2109.00962","title":"You Only Hear Once: A YOLO-like Algorithm for Audio Segmentation and Sound Event Detection","created":"2021-09-01","cited_by_count":10,"area":null},{"id":"2212.03465","title":"MEDIAR: Harmony of Data-Centric and Model-Centric for Multi-Modality Microscopy","created":"2022-12-07","cited_by_count":10,"area":null},{"id":"2502.20361","title":"OpenTAD: A Unified Framework and Comprehensive Study of Temporal Action Detection","created":"2025-02-27","cited_by_count":10,"area":null},{"id":"2103.08894","title":"Distributed Deep Learning Using Volunteer Computing-Like Paradigm","created":"2021-03-16","cited_by_count":9,"area":null},{"id":"2207.13050","title":"Efficient High-Resolution Deep Learning: A Survey","created":"2022-07-26","cited_by_count":9,"area":null},{"id":"2302.02234","title":"Revisiting Image Deblurring with an Efficient ConvNet","created":"2023-02-04","cited_by_count":9,"area":null},{"id":"2109.01123","title":"Benchmarking the Robustness of Instance Segmentation Models","created":"2021-09-02","cited_by_count":8,"area":null},{"id":"2109.15177","title":"You Cannot Easily Catch Me: A Low-Detectable Adversarial Patch for Object Detectors","created":"2021-09-30","cited_by_count":8,"area":null},{"id":"2301.09056","title":"Performance Study of YOLOv5 and Faster R-CNN for Autonomous Navigation around Non-Cooperative Targets","created":"2023-01-22","cited_by_count":8,"area":null},{"id":"2411.13150","title":"RAW-Diffusion: RGB-Guided Diffusion Models for High-Fidelity RAW Image Generation","created":"2024-11-20","cited_by_count":8,"area":"diffusion"},{"id":"2604.14090","title":"From Weights to Activations: Is Steering the Next Frontier of Adaptation?","created":"2026-04-15","cited_by_count":8,"area":null},{"id":"2111.04204","title":"Natural Adversarial Objects","created":"2021-11-07","cited_by_count":7,"area":null},{"id":"2206.08605","title":"On Efficient Real-Time Semantic Segmentation: A Survey","created":"2022-06-17","cited_by_count":7,"area":null},{"id":"2303.10422","title":"Identification of Novel Classes for Improving Few-Shot Object Detection","created":"2023-03-18","cited_by_count":7,"area":null},{"id":"2408.09332","title":"YOLOv1 to YOLOv10: The fastest and most accurate real-time object detection systems","created":"2024-08-18","cited_by_count":7,"area":null},{"id":"2411.17000","title":"SatVision-TOA: A Geospatial Foundation Model for Coarse-Resolution All-Sky Remote Sensing Imagery","created":"2024-11-26","cited_by_count":7,"area":null},{"id":"2103.00430","title":"Training Generative Adversarial Networks in One Stage","created":"2021-02-28","cited_by_count":6,"area":null},{"id":"2107.04396","title":"Multi-Modal Association based Grouping for Form Structure Extraction","created":"2021-07-09","cited_by_count":6,"area":null},{"id":"2109.00707","title":"Cross-Model Consensus of Explanations and Beyond for Image Classification Models: An Empirical Study","created":"2021-09-02","cited_by_count":6,"area":null},{"id":"2203.08764","title":"X-Learner: Learning Cross Sources and Tasks for Universal Visual Representation","created":"2022-03-16","cited_by_count":6,"area":null},{"id":"2210.11318","title":"A Survey of Computer Vision Technologies In Urban and Controlled-environment Agriculture","created":"2022-10-20","cited_by_count":6,"area":null},{"id":"2211.02043","title":"Could Giant Pretrained Image Models Extract Universal Representations?","created":"2022-11-03","cited_by_count":6,"area":null},{"id":"2312.00313","title":"Improving Normalization with the James-Stein Estimator","created":"2023-12-01","cited_by_count":6,"area":null},{"id":"2405.15916","title":"Recasting Generic Pretrained Vision Transformers As Object-Centric Scene Encoders For Manipulation Policies","created":"2024-05-24","cited_by_count":6,"area":null},{"id":"2101.07347","title":"Object Detection and Pose Estimation from RGB and Depth Data for Real-time, Adaptive Robotic Grasping","created":"2021-01-18","cited_by_count":5,"area":null},{"id":"2103.14785","title":"A Comprehensive Review of the Video-to-Text Problem","created":"2021-03-27","cited_by_count":5,"area":null},{"id":"2104.00432","title":"Anchor Pruning for Object Detection","created":"2021-04-01","cited_by_count":5,"area":null},{"id":"2112.09569","title":"CPPE-5: Medical Personal Protective Equipment Dataset","created":"2021-12-15","cited_by_count":5,"area":null},{"id":"2201.12861","title":"Neural-PIM: Efficient Processing-In-Memory with Neural Approximation of Peripherals","created":"2022-01-30","cited_by_count":5,"area":null},{"id":"2202.11279","title":"An End-to-End Cascaded Image Deraining and Object Detection Neural Network","created":"2022-02-23","cited_by_count":5,"area":null},{"id":"2205.14410","title":"Multi-Source Transfer Learning for Deep Model-Based Reinforcement Learning","created":"2022-05-28","cited_by_count":5,"area":null},{"id":"2301.04494","title":"Multi-label Image Classification using Adaptive Graph Convolutional Networks: from a Single Domain to Multiple Domains","created":"2023-01-11","cited_by_count":5,"area":null},{"id":"2307.15427","title":"Deep Learning Pipeline for Automated Visual Moth Monitoring: Insect Localization and Species Classification","created":"2023-07-28","cited_by_count":5,"area":null},{"id":"2308.07535","title":"Improved Region Proposal Network for Enhanced Few-Shot Object Detection","created":"2023-08-15","cited_by_count":5,"area":null},{"id":"2404.12403","title":"Multi-Objective Hardware Aware Neural Architecture Search using Hardware Cost Diversity","created":"2024-04-15","cited_by_count":5,"area":null},{"id":"2107.13757","title":"Bridging Gap between Image Pixels and Semantics via Supervision: A Survey","created":"2021-07-29","cited_by_count":4,"area":null},{"id":"2201.11231","title":"Gap Minimization for Knowledge Sharing and Transfer","created":"2022-01-26","cited_by_count":4,"area":null},{"id":"2202.10124","title":"Multi-Task Conditional Imitation Learning for Autonomous Navigation at Crowded Intersections","created":"2022-02-21","cited_by_count":4,"area":"offlinerl"}],"next_cursor":"100"}