mlsanityData to 7 Oct 2026

Low-Resolution Self-Attention for Semantic Segmentation

arXiv 2310.05026 ↗First posted 8 Oct 2023cs.CVcited by 12

Not on the map. Why?

Abstract (arXiv)

Semantic segmentation tasks naturally require high-resolution information for pixel-wise segmentation and global context information for class prediction. While existing vision transformers demonstrate promising performance, they often utilize high-resolution context modeling, resulting in a computational bottleneck. In this work, we challenge conventional wisdom and introduce the Low-Resolution Self-Attention (LRSA) mechanism to capture global context at a significantly reduced computational cost, i.e., FLOPs. Our approach involves computing self-attention in a fixed low-resolution space regardless of the input image's resolution, with additional 3x3 depth-wise convolutions to capture fine details in the high-resolution space. We demonstrate the effectiveness of our LRSA approach by building the LRFormer, a vision transformer with an encoder-decoder structure. Extensive experiments on the ADE20K, COCO-Stuff, and Cityscapes datasets demonstrate that LRFormer outperforms state-of-the-art models. Code is available at https://github.com/yuhuan-wu/LRFormer.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 82 of its 96 references that are in the map. First posted on arXiv 8 Oct 2023.

Builds on

82 of 96 references.

References · 82

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  5. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  6. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  7. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  8. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  9. 2023Visual Instruction Tuningcited by 7,792
  10. 2016Densely Connected Convolutional Networkscited by 6,691
  11. 2016Layer Normalizationcited by 5,579
  12. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
38 more
  1. 2017Squeeze-and-Excitation Networkscited by 4,763
  2. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  3. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  4. 2014Going Deeper with Convolutionscited by 4,231
  5. 2022A ConvNet for the 2020scited by 3,545
  6. 2016Gaussian Error Linear Units (GELUs)cited by 3,431
  7. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  8. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,923
  9. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  10. 2016Pyramid Scene Parsing Networkcited by 2,472
  11. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,338
  12. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
  13. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,960
  14. 2021Vision Transformers for Dense Predictioncited by 1,789
  15. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,417
  16. 2020Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformerscited by 1,368
  17. 2018Unified Perceptual Parsing for Scene Understandingcited by 1,265
  18. 2021Swin Transformer V2: Scaling Up Capacity and Resolutioncited by 1,215
  19. 2021Per-Pixel Classification is Not All You Need for Semantic Segmentationcited by 1,148
  20. 2015Multi-Scale Context Aggregation by Dilated Convolutionscited by 1,128
  21. 2021Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNetcited by 1,096
  22. 2018Dual Attention Network for Scene Segmentationcited by 1,001
  23. 2020Designing Network Design Spacescited by 954
  24. 2021CvT: Introducing Convolutions to Vision Transformerscited by 946
  25. 2015Generation and Comprehension of Unambiguous Object Descriptionscited by 897
  26. 2021Multiscale Vision Transformerscited by 896
  27. 2016COCO-Stuff: Thing and Stuff Classes in Contextcited by 858
  28. 2023LISA: Reasoning Segmentation via Large Language Modelcited by 770
  29. 2021Going deeper with Image Transformerscited by 759
  30. 2021PVT v2: Improved Baselines with Pyramid Vision Transformercited by 749
  31. 2018CCNet: Criss-Cross Attention for Semantic Segmentationcited by 717
  32. 2022EVA: Exploring the Limits of Masked Visual Representation Learning at Scalecited by 685
  33. 2016Training Region-based Object Detectors with Online Hard Example Miningcited by 577
  34. 2019Segmentation Transformer: Object-Contextual Representations for Semantic Segmentationcited by 573
  35. 2021CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windowscited by 526
  36. 2021MetaFormer Is Actually What You Need for Visioncited by 523
  37. 2021MViTv2: Improved Multiscale Vision Transformers for Classification and Detectioncited by 516
  38. 2022InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutionscited by 479

50 most cited of 82 All 82 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 1; 2025: 7; 2026: 3.

12 papers.

  1. 2024Context-Guided Spatial Feature Reconstruction for Efficient Semantic Segmentationcited by 25
  2. 2023Mobile-Seed: Joint Semantic Segmentation and Boundary Detection for Mobile Robotscited by 5
  3. 2025Revisiting Efficient Semantic Segmentation: Learning Offsets for Better Spatial and Class Feature Alignmentcited by 5
  4. 2026ARTA: Adaptive Mixed-Resolution Token Allocation for Efficient Dense Feature Extractioncited by 2
  5. 2025A2Mamba: Attention-augmented State Space Models for Visual Recognitioncited by 1
  6. 2025GAPNet: A Lightweight Framework for Image and Video Salient Object Detection via Granularity-Aware Paradigmcited by 1
  7. 2025Deeply Dual Supervised learning for melanoma recognitioncited by 0
  8. 2025Edge Detection for Organ Boundaries via Top Down Refinement and SubPixel Upsamplingcited by 0
  9. 2025DualResolution Residual Architecture with Artifact Suppression for Melanocytic Lesion Segmentationcited by 0
  10. 2025VesselRW: Weakly Supervised Subcutaneous Vessel Segmentation via Learned Random Walk Propagationcited by 0
  11. 2026Geometry-aware Depth-guided Representation Learning for Structure-preserving Low-light Image Enhancementcited by 0
  12. 2026Effective Receptive Field Ordering Matters for Infrared Small Target Detectioncited by 0