Noisy Boundaries: Lemon or Lemonade for Semi-supervised Instance Segmentation?
This work addresses the cost and scalability issues in instance segmentation for computer vision applications, representing a strong incremental improvement in semi-supervised methods.
The paper tackles the problem of high annotation costs in instance segmentation by proposing a semi-supervised framework that uses pixel-level pseudo labels, achieving performance gains of over 6% on Cityscapes, 7% on COCO, and 4.5% on BDD100k compared to supervised baselines.
Current instance segmentation methods rely heavily on pixel-level annotated images. The huge cost to obtain such fully-annotated images restricts the dataset scale and limits the performance. In this paper, we formally address semi-supervised instance segmentation, where unlabeled images are employed to boost the performance. We construct a framework for semi-supervised instance segmentation by assigning pixel-level pseudo labels. Under this framework, we point out that noisy boundaries associated with pseudo labels are double-edged. We propose to exploit and resist them in a unified manner simultaneously: 1) To combat the negative effects of noisy boundaries, we propose a noise-tolerant mask head by leveraging low-resolution features. 2) To enhance the positive impacts, we introduce a boundary-preserving map for learning detailed information within boundary-relevant regions. We evaluate our approach by extensive experiments. It behaves extraordinarily, outperforming the supervised baseline by a large margin, more than 6% on Cityscapes, 7% on COCO and 4.5% on BDD100k. On Cityscapes, our method achieves comparable performance by utilizing only 30% labeled images.