Journal
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
Volume -, Issue -, Pages 8199-8208Publisher
IEEE
DOI: 10.1109/ICCV48922.2021.00811
Keywords
-
Funding
- FEDER/MCIU/AEI project [PGC2018-098817-A-I00]
- Aragon regional government [DGA T45 17R/FSE]
- Office of Naval Research Global project [ONRG-NICOP-N62909-19-1-2027]
Ask authors/readers for more resources
This work presents a novel approach for semi-supervised semantic segmentation by utilizing a contrastive learning module to enforce similar pixel-level feature representations for same-class samples. The method outperforms the current state-of-the-art for semi-supervised semantic segmentation, particularly in scenarios with limited labeled data.
This work presents a novel approach for semi-supervised semantic segmentation. The key element of this approach is our contrastive learning module that enforces the segmentation network to yield similar pixel-level feature representations for same-class samples across the whole dataset. To achieve this, we maintain a memory bank which is continuously updated with relevant and high-quality feature vectors from labeled data. In an end-to-end training, the features from both labeled and unlabeled data are optimized to be similar to same-class samples from the memory bank. Our approach not only outperforms the current state-of-the-art for semi-supervised semantic segmentation but also for semi-supervised domain adaptation on well-known public benchmarks, with larger improvements on the most challenging scenarios, i.e., less available labeled data. Code is available at https://github.com/ Shathe/SemiSeg-Contrastive
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