mlsanityData to 7 Oct 2026

Local Relation Networks for Image Recognition

arXiv 1904.11491 ↗First posted 25 Apr 2019cs.CV cs.AI cs.LGcited by 210

Not on the map. Why?

Abstract (arXiv)

The convolution layer has been the dominant feature extractor in computer vision for years. However, the spatial aggregation in convolution is basically a pattern matching process that applies fixed filters which are inefficient at modeling visual elements with varying spatial distributions. This paper presents a new image feature extractor, called the local relation layer, that adaptively determines aggregation weights based on the compositional relationship of local pixel pairs. With this relational approach, it can composite visual elements into higher-level entities in a more efficient manner that benefits semantic inference. A network built with local relation layers, called the Local Relation Network (LR-Net), is found to provide greater modeling capacity than its counterpart built with regular convolution on large-scale recognition tasks such as ImageNet classification.

Key facts. Cited by 210 papers in the map (data through 7 Oct 2026). First posted on arXiv 25 Apr 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 93; 2022: 66; 2023: 28; 2024: 16; 2025: 6; 2026: 1.

210 papers.

Sort:

By area:

  1. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  2. 2021Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentationcited by 1,218
  3. 2021Swin Transformer V2: Scaling Up Capacity and Resolutioncited by 1,215
  4. 2021Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNetcited by 1,096
  5. 2021Video Swin Transformercited by 1,090
  6. 2021Transformers in Vision: A Surveycited by 1,009
  7. 2021UNETR: Transformers for 3D Medical Image Segmentationcited by 954
  8. 2021CvT: Introducing Convolutions to Vision Transformerscited by 946
  9. 2021Multiscale Vision Transformerscited by 896
  10. 2021CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classificationcited by 806
  11. 2021Intriguing Properties of Vision Transformerscited by 446
  12. 2021VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Textcited by 427
38 more
  1. 2021Bottleneck Transformers for Visual Recognitioncited by 364
  2. 2022Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizationscited by 359
  3. 2022V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transformercited by 320
  4. 2021DeepViT: Towards Deeper Vision Transformercited by 288
  5. 2021Escaping the Big Data Paradigm with Compact Transformerscited by 261
  6. 2021Incorporating Convolution Designs into Visual Transformerscited by 248
  7. 2021Attention Mechanisms in Computer Vision: A Surveycited by 232
  8. 2021Co-Scale Conv-Attentional Image Transformerscited by 224
  9. 2021Scaling Local Self-Attention for Parameter Efficient Visual Backbonescited by 220
  10. 2021Group-Free 3D Object Detection via Transformerscited by 215
  11. 2021UniT: Multimodal Multitask Learning with a Unified Transformercited by 195
  12. 2022Focal Modulation Networkscited by 186
  13. 2021VOLO: Vision Outlooker for Visual Recognitioncited by 164
  14. 2021TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Upcited by 162
  15. 2021Revisiting ResNets: Improved Training and Scaling Strategiescited by 158
  16. 2022Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNscited by 155
  17. 2021StyleSwin: Transformer-based GAN for High-resolution Image Generationcited by 152
  18. 2021HRFormer: High-Resolution Transformer for Dense Predictioncited by 149
  19. 2021Visformer: The Vision-friendly Transformercited by 137
  20. 2023Run, Don't Walk: Chasing Higher FLOPS for Faster Neural Networkscited by 129
  21. 2021RegionViT: Regional-to-Local Attention for Vision Transformerscited by 126
  22. 2021Transformer-Based Attention Networks for Continuous Pixel-Wise Predictioncited by 125
  23. 2023Transformer-Based Visual Segmentation: A Surveycited by 124
  24. 2021Video Frame Interpolation Transformercited by 122
  25. 2021Generative Adversarial Transformerscited by 120
  26. 2021A Survey of Visual Transformerscited by 117
  27. 2021Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformercited by 115
  28. 2022Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentationcited by 114
  29. 2021LambdaNetworks: Modeling Long-Range Interactions Without Attentioncited by 107
  30. 2021Efficient Training of Visual Transformers with Small Datasetscited by 107
  31. 2022Vision Transformer for NeRF-Based View Synthesis from a Single Input Imagecited by 104
  32. 2021Variational Relational Point Completion Networkcited by 103
  33. 2021Vision Permutator: A Permutable MLP-Like Architecture for Visual Recognitioncited by 103
  34. 2021Fast Point Transformercited by 103
  35. 2021Involution: Inverting the Inherence of Convolution for Visual Recognitioncited by 99
  36. 2021Contextual Transformer Networks for Visual Recognitioncited by 90
  37. 2022Accurate Image Restoration with Attention Retractable Transformercited by 85
  38. 2021Scalable Vision Transformers with Hierarchical Poolingcited by 84

50 most cited of 210 All 210 (JSON)