# Unsupervised Co-part Segmentation through Assembly

Source: [Unsupervised Co-part Segmentation through Assembly](<https://www.sota2.com/research/paper/68fa6a1f1e209131cea26198>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T23:16:37.291Z

Authors: Qingzhe Gao, Bin Wang, Libin Liu, Baoquan Chen

Published: 2021-06-10T16:22:53.000Z

## Abstract

Co-part segmentation is an important problem in computer vision for its rich applications. We propose an unsupervised learning approach for co-part segmentation from images. For the training stage, we leverage motion information embedded in videos and explicitly extract latent representations to segment meaningful object parts. More importantly, we introduce a dual procedure of part-assembly to form a closed loop with part-segmentation, enabling an effective self-supervision. We demonstrate the effectiveness of our approach with a host of extensive experiments, ranging from human bodies, hands, quadruped, and robot arms. We show that our approach can achieve meaningful and compact part segmentation, outperforming state-of-the-art approaches on diverse benchmarks.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2106.05897>)

[PDF](<https://arxiv.org/pdf/2106.05897.pdf>)
