# ModuSeg: Decoupling Object Discovery and Semantic Retrieval for Training-Free Weakly Supervised Segmentation

arXiv: https://arxiv.org/abs/2604.07021 · HTML: https://mlsanity.com/paper/2604.07021/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 34 of its 47 references that are in the map.
- First posted on arXiv 8 Apr 2026.

## Builds on (most cited first, 30 of 34)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [Extract Free Dense Labels from CLIP](https://mlsanity.com/paper/2112.01071/) (2021)
- [The Faiss library](https://mlsanity.com/paper/2401.08281/) (2024)
- [Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/1803.10464/) (2018)
- [CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2303.11797/) (2023)
- [Rethinking Semantic Segmentation: A Prototype View](https://mlsanity.com/paper/2203.15102/) (2022)
- [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)
- [High-Quality Entity Segmentation](https://mlsanity.com/paper/2211.05776/) (2022)
- [Cross Language Image Matching for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2203.02668/) (2022)
- [Token Contrast for Weakly-Supervised Semantic Segmentation](https://mlsanity.com/paper/2303.01267/) (2023)
- [Segment Anything Model (SAM) Enhanced Pseudo Labels for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2305.05803/) (2023)
- [Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation](https://mlsanity.com/paper/2411.09219/) (2024)
- [CorrCLIP: Reconstructing Patch Correlations in CLIP for Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2411.10086/) (2024)
- [Extracting Class Activation Maps from Non-Discriminative Features as well](https://mlsanity.com/paper/2303.10334/) (2023)
- [MCTformer+: Multi-Class Token Transformer for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2308.03005/) (2023)
- [Mask-Adapter: The Devil is in the Masks for Open-Vocabulary Segmentation](https://mlsanity.com/paper/2412.04533/) (2024)
- [DuPL: Dual Student with Trustworthy Progressive Learning for Robust Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2403.11184/) (2024)
- [Frozen CLIP: A Strong Backbone for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2406.11189/) (2024)
- [Separate and Conquer: Decoupling Co-occurrence via Decomposition and Representation for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2402.18467/) (2024)
- [C-RADIOv4 (Tech Report)](https://mlsanity.com/paper/2601.17237/) (2026)
- [MoRe: Class Patch Attention Needs Regularization for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2412.11076/) (2024)
- [ReME: A Data-Centric Framework for Training-Free Open-Vocabulary Segmentation](https://mlsanity.com/paper/2506.21233/) (2025)

## Abstract (arXiv)

Weakly supervised semantic segmentation aims to achieve pixel-level predictions using image-level labels. Existing methods typically entangle semantic recognition and object localization, which often leads models to focus exclusively on sparse discriminative regions. Although foundation models show immense potential, many approaches still follow the tightly coupled optimization paradigm, struggling to effectively alleviate pseudo-label noise and often relying on time-consuming multi-stage retraining or unstable end-to-end joint optimization. To address the above challenges, we present ModuSeg, a training-free weakly supervised semantic segmentation framework centered on explicitly decoupling object discovery and semantic assignment. Specifically, we integrate a general mask proposer to extract geometric proposals with reliable boundaries, while leveraging semantic foundation models to construct an offline feature bank, transforming segmentation into a non-parametric feature retrieval process. Furthermore, we propose semantic boundary purification and soft-masked feature aggregation strategies to effectively mitigate boundary ambiguity and quantization errors, thereby extracting high-quality category prototypes. Extensive experiments demonstrate that the proposed decoupled architecture better preserves fine boundaries without parameter fine-tuning and achieves highly competitive performance on standard benchmark datasets. Code is available at https://github.com/Autumnair007/ModuSeg.