Can I read SCOPS: Self-Supervised Co-Part Segmentation on EtoBox?

SCOPS: Self-Supervised Co-Part Segmentation by Hung, Wei-Chih; Jampani, Varun; Liu, Sifei; Molchanov, Pavlo; Yang, Ming-Hsuan; Kautz, Jan is a scholarly article available to read on EtoBox.

What is SCOPS: Self-Supervised Co-Part Segmentation about?

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.

Author

Hung, Wei-Chih; Jampani, Varun; Liu, Sifei; Molchanov, Pavlo; Yang, Ming-Hsuan; Kautz, Jan

Published

2019

Language

EN