{"ID":2871171,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.12496","arxiv_id":"2509.12496","title":"Localized Region Guidance for Class Activation Mapping in WSSS","abstract":"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.","short_abstract":"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-...","url_abs":"https://arxiv.org/abs/2509.12496","url_pdf":"https://arxiv.org/pdf/2509.12496v2","authors":"[\"Ali Torabi\",\"Sanjog Gaihre\",\"MD Mahbubur Rahman\",\"Yaqoob Majeed\"]","published":"2025-09-15T22:41:44Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}