# Exploring CLIP's Dense Knowledge for Weakly Supervised Semantic Segmentation

arXiv: https://arxiv.org/abs/2503.20826 · HTML: https://mlsanity.com/paper/2503.20826/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 41 of its 52 references that are in the map.
- First posted on arXiv 26 Mar 2025.

## Builds on (most cited first, 30 of 41)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [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)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [CLIP-Adapter: Better Vision-Language Models with Feature Adapters](https://mlsanity.com/paper/2110.04544/) (2021)
- [Extract Free Dense Labels from CLIP](https://mlsanity.com/paper/2112.01071/) (2021)
- [DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting](https://mlsanity.com/paper/2112.01518/) (2021)
- [ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1604.05144/) (2016)
- [Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/1803.10464/) (2018)
- [What's the Point: Semantic Segmentation with Point Supervision](https://mlsanity.com/paper/1506.02106/) (2015)
- [BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1503.01640/) (2015)
- [Single-Stage Semantic Segmentation from Image Labels](https://mlsanity.com/paper/2005.08104/) (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)
- [Railroad is not a Train: Saliency as Pseudo-pixel Supervision for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2105.08965/) (2021)
- [Learning Affinity from Attention: End-to-End Weakly-Supervised Semantic Segmentation with Transformers](https://mlsanity.com/paper/2203.02664/) (2022)
- [CLIP is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2212.09506/) (2022)
- [BBAM: Bounding Box Attribution Map for Weakly Supervised Semantic and Instance Segmentation](https://mlsanity.com/paper/2103.08907/) (2021)
- [Learning random-walk label propagation for weakly-supervised semantic segmentation](https://mlsanity.com/paper/1802.00470/) (2018)
- [Weakly Supervised Semantic Segmentation by Pixel-to-Prototype Contrast](https://mlsanity.com/paper/2110.07110/) (2021)
- [Weakly-Supervised Semantic Segmentation by Iteratively Mining Common Object Features](https://mlsanity.com/paper/1806.04659/) (2018)
- [Class Re-Activation Maps for Weakly-Supervised Semantic Segmentation](https://mlsanity.com/paper/2203.00962/) (2022)
- [Cross Language Image Matching for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2203.02668/) (2022)
- [Context Decoupling Augmentation for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2103.01795/) (2021)
- [Regional Semantic Contrast and Aggregation for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2203.09653/) (2022)
- [Weakly Supervised Semantic Segmentation using Out-of-Distribution Data](https://mlsanity.com/paper/2203.03860/) (2022)
- [L2G: A Simple Local-to-Global Knowledge Transfer Framework for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2204.03206/) (2022)

## Built on by (most cited first, 8 of 8)

- [OpenDPR: Open-Vocabulary Change Detection via Vision-Centric Diffusion-Guided Prototype Retrieval for Remote Sensing Imagery](https://mlsanity.com/paper/2603.27645/) (2026)
- [Dual-Modality Anchor-Guided Filtering for Test-time Prompt Tuning](https://mlsanity.com/paper/2604.12403/) (2026)
- [Semantic segmentation with reward](https://mlsanity.com/paper/2505.17905/) (2025)
- [Object-IR: Leveraging Object Consistency and Mesh Deformation for Self-Supervised Image Retargeting](https://mlsanity.com/paper/2510.27236/) (2025)
- [Depth Edge Alignment Loss: DEALing with Depth in Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2509.17702/) (2025)
- [Region-CAM: Towards Accurate Object Regions in Class Activation Maps for Weakly Supervised Learning Tasks](https://mlsanity.com/paper/2510.25134/) (2025)
- [ModuSeg: Decoupling Object Discovery and Semantic Retrieval for Training-Free Weakly Supervised Segmentation](https://mlsanity.com/paper/2604.07021/) (2026)
- [CRF Loss is How Networks Should Learn Boundaries in Weakly Supervised Segmentation](https://mlsanity.com/paper/2609.34183/) (2026)

## Abstract (arXiv)

Weakly Supervised Semantic Segmentation (WSSS) with image-level labels aims to achieve pixel-level predictions using Class Activation Maps (CAMs). Recently, Contrastive Language-Image Pre-training (CLIP) has been introduced in WSSS. However, recent methods primarily focus on image-text alignment for CAM generation, while CLIP's potential in patch-text alignment remains unexplored. In this work, we propose ExCEL to explore CLIP's dense knowledge via a novel patch-text alignment paradigm for WSSS. Specifically, we propose Text Semantic Enrichment (TSE) and Visual Calibration (VC) modules to improve the dense alignment across both text and vision modalities. To make text embeddings semantically informative, our TSE module applies Large Language Models (LLMs) to build a dataset-wide knowledge base and enriches the text representations with an implicit attribute-hunting process. To mine fine-grained knowledge from visual features, our VC module first proposes Static Visual Calibration (SVC) to propagate fine-grained knowledge in a non-parametric manner. Then Learnable Visual Calibration (LVC) is further proposed to dynamically shift the frozen features towards distributions with diverse semantics. With these enhancements, ExCEL not only retains CLIP's training-free advantages but also significantly outperforms other state-of-the-art methods with much less training cost on PASCAL VOC and MS COCO.