mlsanityData to 7 Oct 2026

ResNeSt: Split-Attention Networks

arXiv 2004.08955 ↗First posted 19 Apr 2020cs.CVcited by 445

Not on the map. Why?

Abstract (arXiv)

It is well known that featuremap attention and multi-path representation are important for visual recognition. In this paper, we present a modularized architecture, which applies the channel-wise attention on different network branches to leverage their success in capturing cross-feature interactions and learning diverse representations. Our design results in a simple and unified computation block, which can be parameterized using only a few variables. Our model, named ResNeSt, outperforms EfficientNet in accuracy and latency trade-off on image classification. In addition, ResNeSt has achieved superior transfer learning results on several public benchmarks serving as the backbone, and has been adopted by the winning entries of COCO-LVIS challenge. The source code for complete system and pretrained models are publicly available.

Key facts. Cited by 445 papers in the map (data through 7 Oct 2026). First posted on arXiv 19 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 146; 2022: 111; 2023: 77; 2024: 61; 2025: 34; 2026: 16.

445 papers.

Sort:

By area:

  1. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  2. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,923
  3. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,960
  4. 2021Vision Transformers for Dense Predictioncited by 1,789
  5. 2021EfficientNetV2: Smaller Models and Faster Trainingcited by 1,127
  6. 2021Multiscale Vision Transformerscited by 896
  7. 2021Segmenter: Transformer for Semantic Segmentationcited by 855
  8. 2021Going deeper with Image Transformerscited by 759
  9. 2022Language-driven Semantic Segmentationcited by 711
  10. 2021MViTv2: Improved Multiscale Vision Transformers for Classification and Detectioncited by 516
  11. 2021LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inferencecited by 475
  12. 2021TransReID: Transformer-based Object Re-Identificationcited by 432
38 more
  1. 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 376
  2. 2021ResNet strikes back: An improved training procedure in timmcited by 365
  3. 2021Bottleneck Transformers for Visual Recognitioncited by 364
  4. 2021Rethinking Spatial Dimensions of Vision Transformerscited by 361
  5. 2022V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transformercited by 320
  6. 2022BoT-SORT: Robust Associations Multi-Pedestrian Trackingcited by 313
  7. 2021DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentationcited by 299
  8. 2021DeepViT: Towards Deeper Vision Transformercited by 288
  9. 2021Focal Self-attention for Local-Global Interactions in Vision Transformerscited by 286
  10. 2022SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentationcited by 252
  11. 2021Attention Mechanisms in Computer Vision: A Surveycited by 232
  12. 2022StrongSORT: Make DeepSORT Great Againcited by 213
  13. 2021K-Net: Towards Unified Image Segmentationcited by 211
  14. 2022UniFormer: Unifying Convolution and Self-attention for Visual Recognitioncited by 206
  15. 2021Distribution Alignment: A Unified Framework for Long-tail Visual Recognitioncited by 198
  16. 2022Focal Modulation Networkscited by 186
  17. 2022DaViT: Dual Attention Vision Transformerscited by 174
  18. 2023FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterizationcited by 161
  19. 2021Revisiting ResNets: Improved Training and Scaling Strategiescited by 158
  20. 2022Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNscited by 155
  21. 2021GDRNPP: A Geometry-guided and Fully Learning-based Object Pose Estimatorcited by 148
  22. 2021All Tokens Matter: Token Labeling for Training Better Vision Transformerscited by 144
  23. 2021Probabilistic two-stage detectioncited by 130
  24. 2021Simple multi-dataset detectioncited by 126
  25. 2021ForgeryNet: A Versatile Benchmark for Comprehensive Forgery Analysiscited by 124
  26. 2021A Survey of Visual Transformerscited by 117
  27. 2021M2TR: Multi-modal Multi-scale Transformers for Deepfake Detectioncited by 114
  28. 2022VLT: Vision-Language Transformer and Query Generation for Referring Segmentationcited by 110
  29. 2021LambdaNetworks: Modeling Long-Range Interactions Without Attentioncited by 107
  30. 2021Vision Permutator: A Permutable MLP-Like Architecture for Visual Recognitioncited by 103
  31. 2021On Interaction Between Augmentations and Corruptions in Natural Corruption Robustnesscited by 98
  32. 2023Large Selective Kernel Network for Remote Sensing Object Detectioncited by 98
  33. 2024Spike-driven Transformer V2: Meta Spiking Neural Network Architecture Inspiring the Design of Next-generation Neuromorphic Chipscited by 97
  34. 2022A Comprehensive Survey of Image Augmentation Techniques for Deep Learningcited by 95
  35. 2021CAT: Cross Attention in Vision Transformercited by 92
  36. 2021Contextual Transformer Networks for Visual Recognitioncited by 90
  37. 2021SO-Pose: Exploiting Self-Occlusion for Direct 6D Pose Estimationcited by 88
  38. 2021You Only Learn One Representation: Unified Network for Multiple Taskscited by 86

50 most cited of 445 All 445 (JSON)