ECS-Net: Improving Weakly Supervised Semantic Segmentation by Using Connections Between Class Activation Maps

Image-level weakly supervised semantic segmentation is a challenging task. As classification networks tend to capture notable object features and are insensitive to over-activation, class activation map (CAM) is too sparse and rough to guide segmentation network training. Inspired by the fact that erasing distinguishing features force networks to collect new ones from non-discriminative object regions, we using relationships between CAMs to propose a novel weakly supervised method. In this work, we apply these features, learned from erased images, as segmentation supervision, driving network to study robust representation. In specifically, object regions obtained by CAM techniques are erased on images firstly. To provide other regions with segmentation supervision, Erased CAM Supervision Net (ECSNet) generates pixel-level labels by predicting segmentation results of those processed images. We also design the rule of suppressing noise to select reliable labels. Our experiments on PASCAL VOC 2012 dataset show that without data annotations except for ground truth image-level labels, our ECS-Net achieves 67.6% mIoU on test set and 66.6% mIoU on val set, outperforming previous state-of-the-art methods.

Automated summary

The method proposed in this work leverages erasing object features and relationships between CAMs to achieve weakly supervised semantic segmentation. By using Erased CAM Supervision Net to generate pixel-level labels, it successfully obtains excellent segmentation results without data annotations other than ground truth image-level labels.