Noisy Boundaries: Lemon or Lemonade for Semi-supervised Instance Segmentation?

• Published in: 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) pp. 16805 - 16814
• Main Authors: Wang, Zhenyu, Li, Yali, Wang, Shengjin
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2022
• Subjects: categorization; Computer vision; Costs; grouping and shape analysis; Self-& semi-& meta- & unsupervised learning; Head; Image segmentation; Pattern recognition; Resists; retrieval; Segmentation; Scene analysis and understanding; Recognition: detection; Training
• ISSN: 2575-7075
• DOI: 10.1109/CVPR52688.2022.01632

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.