1. [Publications](/publications)
2. SCOPS: Self-Supervised Co-Part Segmentation
 
 # SCOPS: Self-Supervised Co-Part Segmentation

  ![Publication image](/sites/default/files/styles/wide/public/default_images/default.jpeg?itok=qUFsuJCP "Publication image")

 ![](https://varunjampani.github.io/images/projectpic/scops_results.png)

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.



 ## Authors



Wei-Chih Hung (UCMerced)

Varun Jampani (NVIDIA)

[Sifei Liu](/person/sifei-liu)

[Pavlo Molchanov](/person/pavlo-molchanov)

Ming-Hsuan Yang (UCMerced)

[Jan Kautz](/person/jan-kautz)

 

 

 ## Publication Date



Sunday, June 16, 2019

 

 ## Published in



[CVPR 2019](https://varunjampani.github.io/scops/)

 

 ## Research Area



[Computer Vision](/research-area/computer-vision)

 

 

 ## External Links



[paper](https://varunjampani.github.io/papers/hung19_SCOPS.pdf)

[Supplementary](https://varunjampani.github.io/papers/hung19_SCOPS_supp.pdf)

[Code](https://github.com/NVlabs/SCOPS)

 

 

 ## Copyright



This material is posted here with permission of the IEEE. Internal or personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution must be obtained from the IEEE by writing to <pubs-permissions@ieee.org>.