mlsanityData to 7 Oct 2026

SemFormer: Semantic Guided Activation Transformer for Weakly Supervised Semantic Segmentation

arXiv 2210.14618 ↗First posted 26 Oct 2022cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

Recent mainstream weakly supervised semantic segmentation (WSSS) approaches are mainly based on Class Activation Map (CAM) generated by a CNN (Convolutional Neural Network) based image classifier. In this paper, we propose a novel transformer-based framework, named Semantic Guided Activation Transformer (SemFormer), for WSSS. We design a transformer-based Class-Aware AutoEncoder (CAAE) to extract the class embeddings for the input image and learn class semantics for all classes of the dataset. The class embeddings and learned class semantics are then used to guide the generation of activation maps with four losses, i.e., class-foreground, class-background, activation suppression, and activation complementation loss. Experimental results show that our SemFormer achieves 74.3% mIoU and surpasses many recent mainstream WSSS approaches by a large margin on PASCAL VOC 2012 dataset. Code will be available at urlhttps://github.com/JLChen-C/SemFormer.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 38 of its 47 references that are in the map. First posted on arXiv 26 Oct 2022.

Builds on

38 of 47 references.

References · 38

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  3. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  4. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  5. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  6. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  7. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,923
  8. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  9. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,960
  10. 2020Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformerscited by 1,368
  11. 2018BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentationcited by 645
  12. 2021Twins: Revisiting the Design of Spatial Attention in Vision Transformerscited by 565
26 more
  1. 2014Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFscited by 552
  2. 2021CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windowscited by 526
  3. 2016ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentationcited by 330
  4. 2018Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentationcited by 321
  5. 2020Self-supervised Equivariant Attention Mechanism for Weakly Supervised Semantic Segmentationcited by 299
  6. 2015What's the Point: Semantic Segmentation with Point Supervisioncited by 297
  7. 2020Causal Intervention for Weakly-Supervised Semantic Segmentationcited by 229
  8. 2016Simple Does It: Weakly Supervised Instance and Semantic Segmentationcited by 226
  9. 2017Object Region Mining with Adversarial Erasing: A Simple Classification to Semantic Segmentation Approachcited by 201
  10. 2016Seed, Expand and Constrain: Three Principles for Weakly-Supervised Image Segmentationcited by 198
  11. 2016Wider or Deeper: Revisiting the ResNet Model for Visual Recognitioncited by 184
  12. 2018Tell Me Where to Look: Guided Attention Inference Networkcited by 168
  13. 2018Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi- Supervised Semantic Segmentationcited by 145
  14. 2020Weakly-Supervised Semantic Segmentation via Sub-category Explorationcited by 145
  15. 2022Multi-class Token Transformer for Weakly Supervised Semantic Segmentationcited by 138
  16. 2021Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic Segmentationcited by 134
  17. 2021Railroad is not a Train: Saliency as Pseudo-pixel Supervision for Weakly Supervised Semantic Segmentationcited by 127
  18. 2021TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localizationcited by 122
  19. 2021BBAM: Bounding Box Attribution Map for Weakly Supervised Semantic and Instance Segmentationcited by 104
  20. 2018Learning random-walk label propagation for weakly-supervised semantic segmentationcited by 101
  21. 2019Box-driven Class-wise Region Masking and Filling Rate Guided Loss for Weakly Supervised Semantic Segmentationcited by 97
  22. 2018CIAN: Cross-Image Affinity Net for Weakly Supervised Semantic Segmentationcited by 80
  23. 2021Complementary Patch for Weakly Supervised Semantic Segmentationcited by 75
  24. 2022Cross Language Image Matching for Weakly Supervised Semantic Segmentationcited by 72
  25. 2021Reducing Information Bottleneck for Weakly Supervised Semantic Segmentationcited by 65
  26. 2022Threshold Matters in WSSS: Manipulating the Activation for the Robust and Accurate Segmentation Model Against Thresholdscited by 37

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 1.

2 papers.

  1. 2024A Survey on Occupancy Perception for Autonomous Driving: The Information Fusion Perspectivecited by 37
  2. 2023MECPformer: Multi-estimations Complementary Patch with CNN-Transformers for Weakly Supervised Semantic Segmentationcited by 1