Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2509.12496 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908665785614336 |
|---|---|
| author | Torabi, Ali Gaihre, Sanjog Rahman, MD Mahbubur Majeed, Yaqoob |
| author_facet | Torabi, Ali Gaihre, Sanjog Rahman, MD Mahbubur Majeed, Yaqoob |
| contents | Weakly Supervised Semantic Segmentation (WSSS) addresses the challenge of training segmentation models using only image-level annotations. Existing WSSS methods struggle with precise object boundary localization and focus only on the most discriminative regions. To address these challenges, we propose IG-CAM (Instance-Guided Class Activation Mapping), a novel approach that leverages instance-level cues and influence functions to generate high-quality, boundary-aware localization maps. Our method introduces three key innovations: (1) Instance-Guided Refinement using object proposals to guide CAM generation, ensuring complete object coverage; (2) Influence Function Integration that captures the relationship between training samples and model predictions; and (3) Multi-Scale Boundary Enhancement with progressive refinement strategies. IG-CAM achieves state-of-the-art performance on PASCAL VOC 2012 with 82.3% mIoU before post-processing, improving to 86.6% after CRF refinement, significantly outperforming previous WSSS methods. Extensive ablation studies validate each component's contribution, establishing IG-CAM as a new benchmark for weakly supervised semantic segmentation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_12496 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Localized Region Guidance for Class Activation Mapping in WSSS Torabi, Ali Gaihre, Sanjog Rahman, MD Mahbubur Majeed, Yaqoob Computer Vision and Pattern Recognition Weakly Supervised Semantic Segmentation (WSSS) addresses the challenge of training segmentation models using only image-level annotations. Existing WSSS methods struggle with precise object boundary localization and focus only on the most discriminative regions. To address these challenges, we propose IG-CAM (Instance-Guided Class Activation Mapping), a novel approach that leverages instance-level cues and influence functions to generate high-quality, boundary-aware localization maps. Our method introduces three key innovations: (1) Instance-Guided Refinement using object proposals to guide CAM generation, ensuring complete object coverage; (2) Influence Function Integration that captures the relationship between training samples and model predictions; and (3) Multi-Scale Boundary Enhancement with progressive refinement strategies. IG-CAM achieves state-of-the-art performance on PASCAL VOC 2012 with 82.3% mIoU before post-processing, improving to 86.6% after CRF refinement, significantly outperforming previous WSSS methods. Extensive ablation studies validate each component's contribution, establishing IG-CAM as a new benchmark for weakly supervised semantic segmentation. |
| title | Localized Region Guidance for Class Activation Mapping in WSSS |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.12496 |