Abstract
Weakly Supervised Semantic Segmentation (WSSS) addresses the challenge of training segmentation models using only image-level annotations, eliminating the need for expensive pixel-level labeling. While existing methods struggle with precise object boundary localization and often focus only on the most discriminative regions, 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 that uses ground truth segmentation masks to guide CAM generation, ensuring complete object coverage rather than just discriminative parts; (2) Influence Function Integration that captures the relationship between training samples and model predictions, leading to more robust feature representations; and (3) Multi-Scale Boundary Enhancement that employs progressive refinement strategies to achieve sharp, precise object boundaries. IG-CAM achieves state-of-the-art performance on the PASCAL VOC 2012 dataset with an mIoU of 82.3% before post-processing, which further improves to 86.6% after applying Conditional Random Field (CRF) refinement, significantly outperforming previous WSSS methods. Our approach demonstrates superior localization accuracy, with complete object coverage and precise boundary delineation, while maintaining computational efficiency. Extensive ablation studies validate the contribution of each component, and qualitative comparisons across 600 diverse images showcase the method's robustness and generalization capability. The results establish IG-CAM as a new benchmark for weakly supervised semantic segmentation, offering a practical solution for scenarios where pixel-level annotations are unavailable or prohibitively expensive.
Abstract (translated)
弱监督语义分割（WSSS）致力于使用仅包含图像级标注的数据来训练分割模型，从而避免了昂贵的像素级标签需求。尽管现有的方法在精准定位物体边界方面存在挑战，并且通常只关注最具判别力的区域，我们提出了一种新的方法——基于实例引导类激活映射（IG-CAM），这种方法利用了实例级线索和影响函数来生成高质量、具有边界的定位图。 我们的方法引入了三个关键创新点： 1. 实例导向精炼：该步骤使用真实分割掩码来指导CAM的生成，确保完整地覆盖物体而不是仅仅关注最具判别力的部分。 2. 影响函数整合：这种方法捕捉训练样本与模型预测之间的关系，从而获得更稳健的功能表示。 3. 多尺度边界增强：通过渐进式细化策略实现清晰、精确的物体边界。 在PASCAL VOC 2012数据集上，IG-CAM达到了前所未有的性能，在不进行后处理的情况下获得了82.3%的mIoU分数，并且在应用条件随机场（CRF）精炼之后进一步提升到了86.6%，显著超越了之前的WSSS方法。我们的方法展示了优越的定位精度，包括完整的物体覆盖和精确的边界划分，并保持了计算效率。 详细的消融研究验证了每个组件的贡献，并通过跨越600幅不同图像的定性比较展示了该方法的强大鲁棒性和泛化能力。这些结果确立了IG-CAM作为弱监督语义分割的新基准，为那些像素级标注不可用或成本过高的场景提供了一个实用的解决方案。
URL
https://arxiv.org/abs/2509.12496
