{"total":431,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744,"area":"wm"},{"id":"2105.05633","title":"Segmenter: Transformer for Semantic Segmentation","created":"2021-05-12","cited_by_count":855,"area":null},{"id":"2304.00685","title":"Vision-Language Models for Vision Tasks: A Survey","created":"2023-04-03","cited_by_count":839,"area":"mllm"},{"id":"2304.08069","title":"DETRs Beat YOLOs on Real-time Object Detection","created":"2023-04-17","cited_by_count":533,"area":null},{"id":"2101.03697","title":"RepVGG: Making VGG-style ConvNets Great Again","created":"2021-01-11","cited_by_count":522,"area":null},{"id":"2203.10807","title":"ViM: Out-Of-Distribution with Virtual-logit Matching","created":"2022-03-21","cited_by_count":405,"area":null},{"id":"2204.00964","title":"AdaFace: Quality Adaptive Margin for Face Recognition","created":"2022-04-03","cited_by_count":391,"area":null},{"id":"2110.00476","title":"ResNet strikes back: An improved training procedure in timm","created":"2021-10-01","cited_by_count":368,"area":null},{"id":"2101.11605","title":"Bottleneck Transformers for Visual Recognition","created":"2021-01-27","cited_by_count":364,"area":null},{"id":"2103.16302","title":"Rethinking Spatial Dimensions of Vision Transformers","created":"2021-03-30","cited_by_count":361,"area":null},{"id":"2102.06171","title":"High-Performance Large-Scale Image Recognition Without Normalization","created":"2021-02-11","cited_by_count":360,"area":null},{"id":"2107.06263","title":"CMT: Convolutional Neural Networks Meet Vision Transformers","created":"2021-07-13","cited_by_count":310,"area":null},{"id":"2109.12894","title":"Training Spiking Neural Networks Using Lessons From Deep Learning","created":"2021-09-27","cited_by_count":259,"area":null},{"id":"2209.08575","title":"SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation","created":"2022-09-18","cited_by_count":252,"area":null},{"id":"2103.12731","title":"Scaling Local Self-Attention for Parameter Efficient Visual Backbones","created":"2021-03-23","cited_by_count":220,"area":null},{"id":"2104.09367","title":"Contrastive Learning for Compact Single Image Dehazing","created":"2021-04-19","cited_by_count":219,"area":null},{"id":"2212.07784","title":"RTMDet: An Empirical Study of Designing Real-Time Object Detectors","created":"2022-12-14","cited_by_count":195,"area":null},{"id":"2102.04010","title":"Learning N:M Fine-grained Structured Sparse Neural Networks From Scratch","created":"2021-02-08","cited_by_count":179,"area":null},{"id":"2110.09784","title":"SSAST: Self-Supervised Audio Spectrogram Transformer","created":"2021-10-19","cited_by_count":169,"area":null},{"id":"2103.07579","title":"Revisiting ResNets: Improved Training and Scaling Strategies","created":"2021-03-13","cited_by_count":158,"area":null},{"id":"2103.05905","title":"VideoMoCo: Contrastive Video Representation Learning with Temporally Adversarial Examples","created":"2021-03-10","cited_by_count":154,"area":null},{"id":"2104.10858","title":"All Tokens Matter: Token Labeling for Training Better Vision Transformers","created":"2021-04-22","cited_by_count":144,"area":null},{"id":"2204.12451","title":"Understanding The Robustness in Vision Transformers","created":"2022-04-26","cited_by_count":144,"area":null},{"id":"2306.13092","title":"Squeeze, Recover and Relabel: Dataset Condensation at ImageNet Scale From A New Perspective","created":"2023-06-22","cited_by_count":138,"area":null},{"id":"2210.11339","title":"VIOLA: Imitation Learning for Vision-Based Manipulation with Object Proposal Priors","created":"2022-10-20","cited_by_count":136,"area":"offlinerl"},{"id":"2103.11511","title":"MoViNets: Mobile Video Networks for Efficient Video Recognition","created":"2021-03-21","cited_by_count":135,"area":null},{"id":"2104.13188","title":"Rethinking BiSeNet For Real-time Semantic Segmentation","created":"2021-04-27","cited_by_count":124,"area":null},{"id":"2106.06984","title":"A Free Lunch From ANN: Towards Efficient, Accurate Spiking Neural Networks Calibration","created":"2021-06-13","cited_by_count":117,"area":null},{"id":"2102.08602","title":"LambdaNetworks: Modeling Long-Range Interactions Without Attention","created":"2021-02-17","cited_by_count":107,"area":null},{"id":"2106.12368","title":"Vision Permutator: A Permutable MLP-Like Architecture for Visual Recognition","created":"2021-06-23","cited_by_count":103,"area":null},{"id":"2301.04805","title":"DEA-Net: Single image dehazing based on detail-enhanced convolution and content-guided attention","created":"2023-01-12","cited_by_count":91,"area":null},{"id":"2107.12292","title":"Contextual Transformer Networks for Visual Recognition","created":"2021-07-26","cited_by_count":90,"area":null},{"id":"2108.02923","title":"StrucTexT: Structured Text Understanding with Multi-Modal Transformers","created":"2021-08-06","cited_by_count":90,"area":null},{"id":"2105.04714","title":"Sample and Computation Redistribution for Efficient Face Detection","created":"2021-05-10","cited_by_count":89,"area":null},{"id":"2101.08692","title":"Characterizing signal propagation to close the performance gap in unnormalized ResNets","created":"2021-01-21","cited_by_count":88,"area":null},{"id":"2205.00823","title":"CenterCLIP: Token Clustering for Efficient Text-Video Retrieval","created":"2022-05-02","cited_by_count":86,"area":null},{"id":"2304.08291","title":"Refusion: Enabling Large-Size Realistic Image Restoration with Latent-Space Diffusion Models","created":"2023-04-17","cited_by_count":86,"area":"diffusion"},{"id":"2303.14218","title":"Curricular Contrastive Regularization for Physics-aware Single Image Dehazing","created":"2023-03-24","cited_by_count":83,"area":null},{"id":"2211.11943","title":"Conv2Former: A Simple Transformer-Style ConvNet for Visual Recognition","created":"2022-11-22","cited_by_count":81,"area":null},{"id":"2103.12676","title":"Self-supervised representation learning from 12-lead ECG data","created":"2021-03-23","cited_by_count":80,"area":null},{"id":"2112.08954","title":"Advancing Spiking Neural Networks towards Deep Residual Learning","created":"2021-12-15","cited_by_count":79,"area":null},{"id":"2309.06497","title":"A Distributed Data-Parallel PyTorch Implementation of the Distributed Shampoo Optimizer for Training Neural Networks At-Scale","created":"2023-09-12","cited_by_count":77,"area":null},{"id":"2203.16250","title":"PP-YOLOE: An evolved version of YOLO","created":"2022-03-30","cited_by_count":75,"area":null},{"id":"2101.01461","title":"PointCutMix: Regularization Strategy for Point Cloud Classification","created":"2021-01-05","cited_by_count":69,"area":null},{"id":"2102.04761","title":"Quasi-Global Momentum: Accelerating Decentralized Deep Learning on Heterogeneous Data","created":"2021-02-09","cited_by_count":69,"area":null},{"id":"2211.12634","title":"PNI : Industrial Anomaly Detection using Position and Neighborhood Information","created":"2022-11-22","cited_by_count":69,"area":null},{"id":"2202.03382","title":"Corrupted Image Modeling for Self-Supervised Visual Pre-Training","created":"2022-02-07","cited_by_count":68,"area":null},{"id":"2202.12938","title":"Assessing the State of Self-Supervised Human Activity Recognition using Wearables","created":"2022-02-22","cited_by_count":65,"area":null},{"id":"2109.14119","title":"Stochastic Training is Not Necessary for Generalization","created":"2021-09-29","cited_by_count":63,"area":null},{"id":"2111.04060","title":"Are we ready for a new paradigm shift? A Survey on Visual Deep MLP","created":"2021-11-07","cited_by_count":63,"area":null},{"id":"2203.12827","title":"Sparse Instance Activation for Real-Time Instance Segmentation","created":"2022-03-24","cited_by_count":63,"area":null},{"id":"2204.12511","title":"PolyLoss: A Polynomial Expansion Perspective of Classification Loss Functions","created":"2022-04-26","cited_by_count":63,"area":null},{"id":"2201.03299","title":"Avoiding Overfitting: A Survey on Regularization Methods for Convolutional Neural Networks","created":"2022-01-10","cited_by_count":55,"area":null},{"id":"2210.02984","title":"The Lie Derivative for Measuring Learned Equivariance","created":"2022-10-06","cited_by_count":54,"area":null},{"id":"2207.09239","title":"Assaying Out-Of-Distribution Generalization in Transfer Learning","created":"2022-07-19","cited_by_count":53,"area":null},{"id":"2104.00676","title":"Is Label Smoothing Truly Incompatible with Knowledge Distillation: An Empirical Study","created":"2021-04-01","cited_by_count":51,"area":"distill"},{"id":"2102.04828","title":"Consensus Control for Decentralized Deep Learning","created":"2021-02-09","cited_by_count":49,"area":null},{"id":"2307.09018","title":"Multimodal LLMs for health grounded in individual-specific data","created":"2023-07-18","cited_by_count":49,"area":"mllm"},{"id":"2112.02363","title":"CAVER: Cross-Modal View-Mixed Transformer for Bi-Modal Salient Object Detection","created":"2021-12-04","cited_by_count":47,"area":null},{"id":"2309.00810","title":"RenAIssance: A Survey into AI Text-to-Image Generation in the Era of Large Model","created":"2023-09-02","cited_by_count":47,"area":"diffusion"},{"id":"2303.12080","title":"Natural Language-Assisted Sign Language Recognition","created":"2023-03-21","cited_by_count":46,"area":null},{"id":"2103.14021","title":"Orthogonal Projection Loss","created":"2021-03-25","cited_by_count":44,"area":null},{"id":"2105.12931","title":"YOLO5Face: Why Reinventing a Face Detector","created":"2021-05-27","cited_by_count":44,"area":null},{"id":"2210.06441","title":"How Much Data Are Augmentations Worth? An Investigation into Scaling Laws, Invariance, and Implicit Regularization","created":"2022-10-12","cited_by_count":40,"area":null},{"id":"2111.03874","title":"Towards Calibrated Model for Long-Tailed Visual Recognition from Prior Perspective","created":"2021-11-06","cited_by_count":39,"area":null},{"id":"2104.13497","title":"ConTNet: Why not use convolution and transformer at the same time?","created":"2021-04-27","cited_by_count":38,"area":null},{"id":"2204.03216","title":"Neural Implicit Flow: a mesh-agnostic dimensionality reduction paradigm of spatio-temporal data","created":"2022-04-07","cited_by_count":37,"area":null},{"id":"2203.15794","title":"CHEX: CHannel EXploration for CNN Model Compression","created":"2022-03-29","cited_by_count":36,"area":null},{"id":"2210.03482","title":"CLAD: A realistic Continual Learning benchmark for Autonomous Driving","created":"2022-10-07","cited_by_count":36,"area":null},{"id":"2301.08227","title":"Diffusion-based Conditional ECG Generation with Structured State Space Models","created":"2023-01-19","cited_by_count":36,"area":null},{"id":"2212.00974","title":"Faster Adaptive Federated Learning","created":"2022-12-02","cited_by_count":35,"area":null},{"id":"2203.12217","title":"Training-free Transformer Architecture Search","created":"2022-03-23","cited_by_count":33,"area":null},{"id":"2201.11279","title":"Revisiting RCAN: Improved Training for Image Super-Resolution","created":"2022-01-27","cited_by_count":32,"area":null},{"id":"2203.10712","title":"Disentangling Architecture and Training for Optical Flow","created":"2022-03-21","cited_by_count":32,"area":null},{"id":"2206.14532","title":"Revisiting Label Smoothing and Knowledge Distillation Compatibility: What was Missing?","created":"2022-06-29","cited_by_count":32,"area":"distill"},{"id":"2303.08594","title":"FastInst: A Simple Query-Based Model for Real-Time Instance Segmentation","created":"2023-03-15","cited_by_count":32,"area":null},{"id":"2306.04557","title":"PhenoBench -- A Large Dataset and Benchmarks for Semantic Image Interpretation in the Agricultural Domain","created":"2023-06-07","cited_by_count":31,"area":null},{"id":"2412.11890","title":"SegMAN: Omni-scale Context Modeling with State Space Models and Local Attention for Semantic Segmentation","created":"2024-12-16","cited_by_count":31,"area":null},{"id":"2104.10419","title":"PP-YOLOv2: A Practical Object Detector","created":"2021-04-21","cited_by_count":30,"area":null},{"id":"2105.11672","title":"ViBERTgrid: A Jointly Trained Multi-Modal 2D Document Representation for Key Information Extraction from Documents","created":"2021-05-25","cited_by_count":29,"area":null},{"id":"2209.02399","title":"SkeletonMAE: Spatial-Temporal Masked Autoencoders for Self-supervised Skeleton Action Recognition","created":"2022-09-01","cited_by_count":29,"area":null},{"id":"2211.11176","title":"Modeling Multivariate Biosignals With Graph Neural Networks and Structured State Space Models","created":"2022-11-21","cited_by_count":29,"area":"ssm"},{"id":"2107.03576","title":"Rethinking of Pedestrian Attribute Recognition: A Reliable Evaluation under Zero-Shot Pedestrian Identity Setting","created":"2021-07-08","cited_by_count":27,"area":null},{"id":"2206.13424","title":"Benchopt: Reproducible, efficient and collaborative optimization benchmarks","created":"2022-06-27","cited_by_count":27,"area":null},{"id":"2304.03589","title":"On Efficient Training of Large-Scale Deep Learning Models: A Literature Review","created":"2023-04-07","cited_by_count":26,"area":null},{"id":"2107.00057","title":"Simple Training Strategies and Model Scaling for Object Detection","created":"2021-06-30","cited_by_count":25,"area":null},{"id":"2204.03342","title":"Domain Adaptation for Time-Series Classification to Mitigate Covariate Shift","created":"2022-04-07","cited_by_count":24,"area":null},{"id":"2105.12971","title":"Joint-DetNAS: Upgrade Your Detector with NAS, Pruning and Dynamic Distillation","created":"2021-05-27","cited_by_count":23,"area":"distill"},{"id":"2302.09598","title":"Guided Depth Map Super-resolution: A Survey","created":"2023-02-19","cited_by_count":23,"area":null},{"id":"2107.02681","title":"VidLanKD: Improving Language Understanding via Video-Distilled Knowledge Transfer","created":"2021-07-06","cited_by_count":22,"area":"distill"},{"id":"2207.07646","title":"Multimodal Open-Vocabulary Video Classification via Pre-Trained Vision and Language Models","created":"2022-07-15","cited_by_count":22,"area":null},{"id":"2109.04898","title":"LibFewShot: A Comprehensive Library for Few-shot Learning","created":"2021-09-10","cited_by_count":21,"area":null},{"id":"2203.01386","title":"Exploring Hierarchical Graph Representation for Large-Scale Zero-Shot Image Classification","created":"2022-03-02","cited_by_count":21,"area":null},{"id":"2206.10121","title":"Finite Expression Method for Solving High-Dimensional Partial Differential Equations","created":"2022-06-21","cited_by_count":21,"area":null},{"id":"2305.01604","title":"The Training Process of Many Deep Networks Explores the Same Low-Dimensional Manifold","created":"2023-05-02","cited_by_count":21,"area":null},{"id":"2306.08913","title":"Advancing Volumetric Medical Image Segmentation via Global-Local Masked Autoencoder","created":"2023-06-15","cited_by_count":21,"area":null},{"id":"2106.15944","title":"A survey on computational spectral reconstruction methods from RGB to hyperspectral imaging","created":"2021-06-30","cited_by_count":20,"area":null},{"id":"2110.08133","title":"Trade-offs of Local SGD at Scale: An Empirical Study","created":"2021-10-15","cited_by_count":20,"area":null},{"id":"2103.12857","title":"Embracing the Disharmony in Medical Imaging: A Simple and Effective Framework for Domain Adaptation","created":"2021-03-23","cited_by_count":19,"area":null},{"id":"2110.07647","title":"Towards Understanding the Data Dependency of Mixup-style Training","created":"2021-10-14","cited_by_count":19,"area":null}],"next_cursor":"100"}