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.
@article{arxiv.2110.12207,
title = {MaskSplit: Self-supervised Meta-learning for Few-shot Semantic Segmentation},
author = {Mustafa Sercan Amac and Ahmet Sencan and Orhun Bugra Baran and Nazli Ikizler-Cinbis and Ramazan Gokberk Cinbis},
journal= {arXiv preprint arXiv:2110.12207},
year = {2021}
}