Salvato in:
Dettagli Bibliografici
Autori principali: Torabi, Ali, Gaihre, Sanjog, Rahman, MD Mahbubur, Majeed, Yaqoob
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