Parts provide a good intermediate representation of objects that is robust with respect to the camera, pose and appearance variations. Existing works on part segmentation is dominated by supervised approaches that rely on large amounts of manual annotations and can not generalize to unseen object categories. We propose a self-supervised deep learning approach for part segmentation, where we devise several loss functions that aids in predicting part segments that are geometrically concentrated, robust to object variations and are also semantically consistent across different object instances. Extensive experiments on different types of image collections demonstrate that our approach can produce part segments that adhere to object boundaries and also more semantically consistent across object instances compared to existing self-supervised techniques.
@article{arxiv.1905.01298,
title = {SCOPS: Self-Supervised Co-Part Segmentation},
author = {Wei-Chih Hung and Varun Jampani and Sifei Liu and Pavlo Molchanov and Ming-Hsuan Yang and Jan Kautz},
journal= {arXiv preprint arXiv:1905.01298},
year = {2019}
}
Comments
Accepted in CVPR 2019. Project page: http://varunjampani.github.io/scops