期刊
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
卷 -, 期 -, 页码 7055-7064出版社
IEEE COMPUTER SOC
DOI: 10.1109/CVPR52688.2022.00693
关键词
-
资金
- National Natural Science Foundation of China [61836014, U21B2042, 62072457, 62006231, 62176009]
- Project of Beijing Municipal Education Commission Project [KZ201910005008]
- Major Project for New Generation of AI [2018AAA0100400]
This paper proposes a challenging cross-domain few-shot semantic segmentation task and addresses the domain shift problem in few-shot learning by introducing a meta-memory bank and a contrastive learning strategy.
Few-shot semantic segmentation intends to predict pixel-level categories using only a few labeled samples. Existing few-shot methods focus primarily on the categories sampled from the same distribution. Nevertheless, this assumption cannot always be ensured. The actual domain shift problem significantly reduces the performance of few-shot learning. To remedy this problem, we propose an interesting and challenging cross-domain few-shot semantic segmentation task, where the training and test tasks perform on different domains. Specifically, we first propose a meta-memory bank to improve the generalization of the segmentation network by bridging the domain gap between source and target domains. The meta-memory stores the intra-domain style information from source domain instances and transfers it to target samples. Subsequently, we adopt a new contrastive learning strategy to explore the knowledge of different categories during the training stage. The negative and positive pairs are obtained from the proposed memory-based style augmentation. Comprehensive experiments demonstrate that our proposed method achieves promising results on cross-domain few-shot semantic segmentation tasks on C000-20(i) , PASCAL-5(i), FSS-1000, and SHIM datasets.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据