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

arXiv: https://arxiv.org/abs/2310.09828 · HTML: https://mlsanity.com/paper/2310.09828/

## 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 (most cited first, 27 of 27)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Pixel Recurrent Neural Networks](https://mlsanity.com/paper/1601.06759/) (2016)
- [Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/1803.10464/) (2018)
- [Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relations](https://mlsanity.com/paper/1904.05044/) (2019)
- [Object Region Mining with Adversarial Erasing: A Simple Classification to Semantic Segmentation Approach](https://mlsanity.com/paper/1703.08448/) (2017)
- [Seed, Expand and Constrain: Three Principles for Weakly-Supervised Image Segmentation](https://mlsanity.com/paper/1603.06098/) (2016)
- [Single-Stage Semantic Segmentation from Image Labels](https://mlsanity.com/paper/2005.08104/) (2020)
- [Weakly-Supervised Semantic Segmentation via Sub-category Exploration](https://mlsanity.com/paper/2008.01183/) (2020)
- [Mining Cross-Image Semantics for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2007.01947/) (2020)
- [Multi-class Token Transformer for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2203.02891/) (2022)
- [Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2103.08896/) (2021)
- [Learning Affinity from Attention: End-to-End Weakly-Supervised Semantic Segmentation with Transformers](https://mlsanity.com/paper/2203.02664/) (2022)
- [NDC-Scene: Boost Monocular 3D Semantic Scene Completion in Normalized Device Coordinates Space](https://mlsanity.com/paper/2309.14616/) (2023)
- [Self-supervised Image-specific Prototype Exploration for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2203.02909/) (2022)
- [Weakly Supervised Semantic Segmentation by Pixel-to-Prototype Contrast](https://mlsanity.com/paper/2110.07110/) (2021)
- [Class Re-Activation Maps for Weakly-Supervised Semantic Segmentation](https://mlsanity.com/paper/2203.00962/) (2022)
- [Token Contrast for Weakly-Supervised Semantic Segmentation](https://mlsanity.com/paper/2303.01267/) (2023)
- [Max Pooling with Vision Transformers reconciles class and shape in weakly supervised semantic segmentation](https://mlsanity.com/paper/2210.17400/) (2022)
- [Improving Depth Gradient Continuity in Transformers: A Comparative Study on Monocular Depth Estimation with CNN](https://mlsanity.com/paper/2308.08333/) (2023)
- [Brain Diffuser: An End-to-End Brain Image to Brain Network Pipeline](https://mlsanity.com/paper/2303.06410/) (2023)
- [ShaDocNet: Learning Spatial-Aware Tokens in Transformer for Document Shadow Removal](https://mlsanity.com/paper/2211.16675/) (2022)
- [Class-level Multiple Distributions Representation are Necessary for Semantic Segmentation](https://mlsanity.com/paper/2303.08029/) (2023)

## Built on by (most cited first, 10 of 10)

- [Image Augmentation Agent for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2412.20439/) (2024)
- [SMAFormer: Synergistic Multi-Attention Transformer for Medical Image Segmentation](https://mlsanity.com/paper/2409.00346/) (2024)
- [Test-Time Intensity Consistency Adaptation for Shadow Detection](https://mlsanity.com/paper/2410.07695/) (2024)
- [Uncertainty-Participation Context Consistency Learning for Semi-supervised Semantic Segmentation](https://mlsanity.com/paper/2412.17331/) (2024)
- [Hybrid Generative Fusion for Efficient and Privacy-Preserving Face Recognition Dataset Generation](https://mlsanity.com/paper/2508.10672/) (2025)
- [Contrastive Prompt Clustering for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2508.17009/) (2025)
- [Text-Driven Weakly Supervised OCT Lesion Segmentation with Structural Guidance](https://mlsanity.com/paper/2411.12615/) (2024)
- [SFormer: SNR-guided Transformer for Underwater Image Enhancement from the Frequency Domain](https://mlsanity.com/paper/2508.18664/) (2025)
- [Recognition of Abnormal Events in Surveillance Videos using Weakly Supervised Dual-Encoder Models](https://mlsanity.com/paper/2511.13276/) (2025)
- [Context Patch Fusion With Class Token Enhancement for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2601.14718/) (2026)

## 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.