Journal
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
Volume -, Issue -, Pages 13921-13930Publisher
IEEE COMPUTER SOC
DOI: 10.1109/CVPR46437.2021.01371
Keywords
-
Funding
- National Key Research and Development Program of China [2017YFA0700904]
- National Science and Technology Major Project [2018ZX01028-102]
- National Natural Science Foundation of China [61836014, U19B2034, 62061136001, 61620106010]
Ask authors/readers for more resources
This paper proposes a BPR framework to improve the boundary quality of instance segmentation models by extracting and refining small boundary patches along predicted instance boundaries, achieving significant improvements on the Cityscapes benchmark.
Tremendous efforts have been made on instance segmentation but the mask quality is still not satisfactory. The boundaries of predicted instance masks are usually imprecise due to the low spatial resolution of feature maps and the imbalance problem caused by the extremely low proportion of boundary pixels. To address these issues, we propose a conceptually simple yet effective post-processing refinement framework to improve the boundary quality based on the results of any instance segmentation model, termed BPR. Following the idea of looking closer to segment boundaries better, we extract and refine a series of small boundary patches along the predicted instance boundaries. The refinement is accomplished by a boundary patch refinement network at higher resolution. The proposed BPR framework yields significant improvements over the Mask R-CNN baseline on Cityscapes benchmark, especially on the boundary-aware metrics. Moreover, by applying the BPR framework to the PolyTransform + SegFix baseline, we reached 1st place on the Cityscapes leaderboard. Code is available at https://github.com/tinyalpha/BPR.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available