# SCOPS: Self-Supervised Co-Part Segmentation

## TL;DR

This paper introduces a self-supervised deep learning method for object part segmentation that does not require manual annotations and generalizes well across unseen categories by ensuring geometric concentration and semantic consistency.

## Contribution

It presents a novel self-supervised framework with specialized loss functions for accurate, robust, and semantically consistent part segmentation across diverse objects.

## Key findings

- Produces segments aligned with object boundaries
- Achieves higher semantic consistency than existing methods
- Effective across various image collections

## Abstract

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.