CIAN: Cross-Image Affinity Net for Weakly Supervised Semantic Segmentation

TL;DR

This paper introduces CIAN, a novel cross-image affinity module that leverages relationships across images to improve weakly supervised semantic segmentation, achieving state-of-the-art results using only image-level labels.

Contribution

The paper proposes an end-to-end cross-image affinity module that exploits inter-image relationships, enhancing segmentation accuracy in weakly supervised learning.

Findings

Achieved 64.3% mIoU on Pascal VOC 2012 validation set.

Achieved 65.3% mIoU on Pascal VOC 2012 test set.

Outperformed previous methods using only image-level labels.

Abstract

Weakly supervised semantic segmentation with only image-level labels saves large human effort to annotate pixel-level labels. Cutting-edge approaches rely on various innovative constraints and heuristic rules to generate the masks for every single image. Although great progress has been achieved by these methods, they treat each image independently and do not take account of the relationships across different images. In this paper, however, we argue that the cross-image relationship is vital for weakly supervised segmentation. Because it connects related regions across images, where supplementary representations can be propagated to obtain more consistent and integral regions. To leverage this information, we propose an end-to-end cross-image affinity module, which exploits pixel-level cross-image relationships with only image-level labels. By means of this, our approach achieves 64.3% and 65.3% mIoU on Pascal VOC 2012 validation and test set respectively, which is a new state-of-the-art result by only using image-level labels for weakly supervised semantic segmentation, demonstrating the superiority of our approach.