Localized Region Guidance for Class Activation Mapping in WSSS
This work addresses the challenge of training semantic segmentation models with only image-level annotations, offering a novel method that improves boundary accuracy and object coverage, though it is incremental in the context of existing WSSS approaches.
The paper tackled the problem of imprecise object boundary localization and limited discriminative region focus in Weakly Supervised Semantic Segmentation (WSSS) by proposing IG-CAM, which achieved state-of-the-art performance with 82.3% mIoU before post-processing and 86.6% after refinement on PASCAL VOC 2012.
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.