-
[pdf]
[arXiv]
[bibtex]@InProceedings{Amac_2022_WACV, author = {Amac, Mustafa Sercan and Sencan, Ahmet and Baran, Bugra and Ikizler-Cinbis, Nazli and Cinbis, Ramazan Gokberk}, title = {MaskSplit: Self-Supervised Meta-Learning for Few-Shot Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2022}, pages = {1067-1077} }
MaskSplit: Self-Supervised Meta-Learning for Few-Shot Semantic Segmentation
Abstract
Just like other few-shot learning problems, few-shot segmentation aims to minimize the need for manual annotation, which is particularly costly in segmentation tasks. Even though the few-shot setting reduces this cost for novel test classes, there is still a need to annotate the training data. To alleviate this need, we propose a self-supervised training approach for learning few-shot segmentation models. We first use unsupervised saliency estimation to obtain pseudo-masks on images. We then train a simple prototype based model over different splits of pseudo masks and augmentations of images. Our extensive experiments show that the proposed approach achieves promising results, highlighting the potential of self-supervised training. To the best of our knowledge this is the first work that addresses unsupervised few-shot segmentation problem on natural images.
Related Material