mlsanityData to 14 Oct 2026

Category Feature Transformer for Semantic Segmentation

arXiv 2308.05581 ↗First posted 10 Aug 2023cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

Aggregation of multi-stage features has been revealed to play a significant role in semantic segmentation. Unlike previous methods employing point-wise summation or concatenation for feature aggregation, this study proposes the Category Feature Transformer (CFT) that explores the flow of category embedding and transformation among multi-stage features through the prevalent multi-head attention mechanism. CFT learns unified feature embeddings for individual semantic categories from high-level features during each aggregation process and dynamically broadcasts them to high-resolution features. Integrating the proposed CFT into a typical feature pyramid structure exhibits superior performance over a broad range of backbone networks. We conduct extensive experiments on popular semantic segmentation benchmarks. Specifically, the proposed CFT obtains a compelling 55.1% mIoU with greatly reduced model parameters and computations on the challenging ADE20K dataset.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 48 of its 58 references that are in the map. First posted on arXiv 10 Aug 2023.

Builds on

48 of 58 references.

References · 48

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  5. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  6. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  7. 2016Layer Normalizationcited by 5,669
  8. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  9. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  10. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  11. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
  12. 2022A ConvNet for the 2020scited by 3,579
36 more
  1. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,223
  2. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,940
  3. 2016Pyramid Scene Parsing Networkcited by 2,479
  4. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,351
  5. 2017Non-local Neural Networkscited by 2,293
  6. 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,292
  7. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,161
  8. 2020Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformerscited by 1,369
  9. 2018Unified Perceptual Parsing for Scene Understandingcited by 1,271
  10. 2021Per-Pixel Classification is Not All You Need for Semantic Segmentationcited by 1,152
  11. 2021Segmenter: Transformer for Semantic Segmentationcited by 855
  12. 2018Image Transformercited by 772
  13. 2022Exploring Plain Vision Transformer Backbones for Object Detectioncited by 724
  14. 2018CCNet: Criss-Cross Attention for Semantic Segmentationcited by 718
  15. 2019Panoptic Feature Pyramid Networkscited by 645
  16. 2019Segmentation Transformer: Object-Contextual Representations for Semantic Segmentationcited by 576
  17. 2022Vision Transformer Adapter for Dense Predictionscited by 565
  18. 2019Attention Augmented Convolutional Networkscited by 363
  19. 2020Visual Transformers: Token-based Image Representation and Processing for Computer Visioncited by 334
  20. 2018Context Encoding for Semantic Segmentationcited by 290
  21. 2021K-Net: Towards Unified Image Segmentationcited by 212
  22. 2019Asymmetric Non-local Neural Networks for Semantic Segmentationcited by 196
  23. 2020Context Prior for Scene Segmentationcited by 121
  24. 2022SegViT: Semantic Segmentation with Plain Vision Transformerscited by 106
  25. 2020Feature Pyramid Transformercited by 96
  26. 2021FaPN: Feature-aligned Pyramid Network for Dense Image Predictioncited by 81
  27. 2019ACFNet: Attentional Class Feature Network for Semantic Segmentationcited by 75
  28. 2020AlignSeg: Feature-Aligned Segmentation Networkscited by 53
  29. 2019Decoders Matter for Semantic Segmentation: Data-Dependent Decoding Enables Flexible Feature Aggregationcited by 34
  30. 2022StructToken : Rethinking Semantic Segmentation with Structural Priorcited by 30
  31. 2021Efficient Self-Ensemble for Semantic Segmentationcited by 16
  32. 2021Channelized Axial Attention for Semantic Segmentation -- Considering Channel Relation within Spatial Attention for Semantic Segmentationcited by 14
  33. 2022CAR: Class-aware Regularizations for Semantic Segmentationcited by 14
  34. 2021Dynamic Neural Representational Decoders for High-Resolution Semantic Segmentationcited by 11
  35. 2016High-performance Semantic Segmentation Using Very Deep Fully Convolutional Networkscited by 9
  36. 2021CondNet: Conditional Classifier for Scene Segmentationcited by 2

Built on by

Cited by year

Citing papers per year: 2024: 3.

3 papers.

  1. 2024SLAB: Efficient Transformers with Simplified Linear Attention and Progressive Re-parameterized Batch Normalizationcited by 17
  2. 2024A Deep Semantic Segmentation Network with Semantic and Contextual Refinementscited by 3
  3. 2024SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformerscited by 2