Employing Multi-Estimations for Weakly-Supervised Semantic Segmentation

Image-level label based weakly-supervised semantic segmentation (WSSS) aims to adopt image-level labels to train semantic segmentation models, saving vast human labors for costly pixel-level annotations. A typical pipeline for this problem is first to adopt class activation maps (CAM) with image-level labels to generate pseudo-masks (a.k.a. seeds) and then use them for training segmentation models. The main difficulty is that seeds are usually sparse and incomplete. Related works typically try to alleviate this problem by adopting many bells and whistles to enhance the seeds. Instead of struggling to refine a single seed, we propose a novel approach to alleviate the inaccurate seed problem by leveraging the segmentation model's robustness to learn from multiple seeds. We managed to generate many different seeds for each image, which are different estimates of the underlying ground truth. The segmentation model simultaneously exploits these seeds to learn and automatically decides the confidence of each seed. Extensive experiments on Pascal VOC 2012 demonstrate the advantage of this multi-seeds strategy over previous state-of-the-art.