-
[pdf]
[supp]
[bibtex]@InProceedings{Wang_2022_CVPR, author = {Wang, Wenjian and Duan, Lijuan and Wang, Yuxi and En, Qing and Fan, Junsong and Zhang, Zhaoxiang}, title = {Remember the Difference: Cross-Domain Few-Shot Semantic Segmentation via Meta-Memory Transfer}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {7065-7074} }
Remember the Difference: Cross-Domain Few-Shot Semantic Segmentation via Meta-Memory Transfer
Abstract
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 COCO-20, PASCAL-5, FSS-1000, and SUIM datasets.
Related Material