Overlap Loss: Rethinking Weakly Supervised Instance Segmentation in Crowded Scenes

This is the authors' abstract. We don't add key points for this paper.

Weakly supervised instance segmentation (WSIS) has gained increasing popularity in recent years due to low labelling cost. However, its performance deteriorates dramatically in more challenging crowded scenario, which is caused by overlapping among similar objects. To ameliorate the negative effects of instance overlapping, we propose a new loss, i.e., OverlapLoss, which achieves instance disentanglement between masks according to the degree of overlapping among instances. Besides, a new dataset of CrowdHuman Instance Segmentation (CIS) is presented to bridge the gap in crowded scenes. Experiments on the CIS and COCO datasets validate that the proposed loss can improve the baseline in typical crowed scenes by at least 2% and in uncrowded scenes by more than 0.3% w.r.t. absolute AP. The code and dataset are available at: https://github.com/shanghangjiang/CIS.