MoRe: Class Patch Attention Needs Regularization for Weakly Supervised Semantic Segmentation

TL;DR

This paper introduces MoRe, a regularization framework for class patch attention in weakly supervised semantic segmentation using ViT, which reduces artifacts and improves localization accuracy.

Contribution

MoRe proposes novel graph-based and localization-informed regularizations to enhance class-patch attention modeling in WSSS with ViT, addressing artifact issues and achieving state-of-the-art results.

Findings

MoRe significantly reduces false activations in localization maps.

It outperforms recent methods on PASCAL VOC and MS COCO datasets.

The approach effectively regularizes class-patch attention for better segmentation.

Abstract

Weakly Supervised Semantic Segmentation (WSSS) with image-level labels typically uses Class Activation Maps (CAM) to achieve dense predictions. Recently, Vision Transformer (ViT) has provided an alternative to generate localization maps from class-patch attention. However, due to insufficient constraints on modeling such attention, we observe that the Localization Attention Maps (LAM) often struggle with the artifact issue, i.e., patch regions with minimal semantic relevance are falsely activated by class tokens. In this work, we propose MoRe to address this issue and further explore the potential of LAM. Our findings suggest that imposing additional regularization on class-patch attention is necessary. To this end, we first view the attention as a novel directed graph and propose the Graph Category Representation module to implicitly regularize the interaction among class-patch entities. It ensures that class tokens dynamically condense the related patch information and suppress unrelated artifacts at a graph level. Second, motivated by the observation that CAM from classification weights maintains smooth localization of objects, we devise the Localization-informed Regularization module to explicitly regularize the class-patch attention. It directly mines the token relations from CAM and further supervises the consistency between class and patch tokens in a learnable manner. Extensive experiments are conducted on PASCAL VOC and MS COCO, validating that MoRe effectively addresses the artifact issue and achieves state-of-the-art performance, surpassing recent single-stage and even multi-stage methods. Code is available at https://github.com/zwyang6/MoRe.