mlsanityData to 14 Oct 2026

Top-K Pooling with Patch Contrastive Learning for Weakly-Supervised Semantic Segmentation

arXiv 2310.09828 ↗First posted 15 Oct 2023cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

Weakly Supervised Semantic Segmentation (WSSS) using only image-level labels has gained significant attention due to cost-effectiveness. Recently, Vision Transformer (ViT) based methods without class activation map (CAM) have shown greater capability in generating reliable pseudo labels than previous methods using CAM. However, the current ViT-based methods utilize max pooling to select the patch with the highest prediction score to map the patch-level classification to the image-level one, which may affect the quality of pseudo labels due to the inaccurate classification of the patches. In this paper, we introduce a novel ViT-based WSSS method named top-K pooling with patch contrastive learning (TKP-PCL), which employs a top-K pooling layer to alleviate the limitations of previous max pooling selection. A patch contrastive error (PCE) is also proposed to enhance the patch embeddings to further improve the final results. The experimental results show that our approach is very efficient and outperforms other state-of-the-art WSSS methods on the PASCAL VOC 2012 dataset.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 27 of its 41 references that are in the map. First posted on arXiv 15 Oct 2023.

Builds on

27 of 41 references.

References · 27

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2020End-to-End Object Detection with Transformerscited by 7,414
  4. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
  5. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,223
  6. 2015Learning Deep Features for Discriminative Localizationcited by 2,436
  7. 2016Pixel Recurrent Neural Networkscited by 816
  8. 2018Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentationcited by 321
  9. 2019Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relationscited by 247
  10. 2017Object Region Mining with Adversarial Erasing: A Simple Classification to Semantic Segmentation Approachcited by 201
  11. 2016Seed, Expand and Constrain: Three Principles for Weakly-Supervised Image Segmentationcited by 198
  12. 2020Single-Stage Semantic Segmentation from Image Labelscited by 167
15 more
  1. 2020Weakly-Supervised Semantic Segmentation via Sub-category Explorationcited by 145
  2. 2020Mining Cross-Image Semantics for Weakly Supervised Semantic Segmentationcited by 144
  3. 2022Multi-class Token Transformer for Weakly Supervised Semantic Segmentationcited by 138
  4. 2021Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic Segmentationcited by 134
  5. 2022Learning Affinity from Attention: End-to-End Weakly-Supervised Semantic Segmentation with Transformerscited by 118
  6. 2023NDC-Scene: Boost Monocular 3D Semantic Scene Completion in Normalized Device Coordinates Spacecited by 90
  7. 2022Self-supervised Image-specific Prototype Exploration for Weakly Supervised Semantic Segmentationcited by 87
  8. 2021Weakly Supervised Semantic Segmentation by Pixel-to-Prototype Contrastcited by 85
  9. 2022Class Re-Activation Maps for Weakly-Supervised Semantic Segmentationcited by 75
  10. 2023Token Contrast for Weakly-Supervised Semantic Segmentationcited by 65
  11. 2022Max Pooling with Vision Transformers reconciles class and shape in weakly supervised semantic segmentationcited by 41
  12. 2023Improving Depth Gradient Continuity in Transformers: A Comparative Study on Monocular Depth Estimation with CNNcited by 35
  13. 2023Brain Diffuser: An End-to-End Brain Image to Brain Network Pipelinecited by 21
  14. 2022ShaDocNet: Learning Spatial-Aware Tokens in Transformer for Document Shadow Removalcited by 16
  15. 2023Class-level Multiple Distributions Representation are Necessary for Semantic Segmentationcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 5; 2025: 4; 2026: 1.

10 papers.

  1. 2024Image Augmentation Agent for Weakly Supervised Semantic Segmentationcited by 15
  2. 2024SMAFormer: Synergistic Multi-Attention Transformer for Medical Image Segmentationcited by 14
  3. 2024Test-Time Intensity Consistency Adaptation for Shadow Detectioncited by 11
  4. 2024Uncertainty-Participation Context Consistency Learning for Semi-supervised Semantic Segmentationcited by 6
  5. 2025Hybrid Generative Fusion for Efficient and Privacy-Preserving Face Recognition Dataset Generationcited by 5
  6. 2025Contrastive Prompt Clustering for Weakly Supervised Semantic Segmentationcited by 1
  7. 2024Text-Driven Weakly Supervised OCT Lesion Segmentation with Structural Guidancecited by 0
  8. 2025SFormer: SNR-guided Transformer for Underwater Image Enhancement from the Frequency Domaincited by 0
  9. 2025Recognition of Abnormal Events in Surveillance Videos using Weakly Supervised Dual-Encoder Modelscited by 0
  10. 2026Context Patch Fusion With Class Token Enhancement for Weakly Supervised Semantic Segmentationcited by 0