# Joint Object and Part Segmentation using Deep Learned Potentials

Source: [Joint Object and Part Segmentation using Deep Learned Potentials](<https://www.sota2.com/research/paper/68fa61e31e209131ce9f666b>)

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

Data updated: 2025-10-25T20:08:28.563Z

Authors: Peng Wang, Xiaohui Shen, Zhe Lin, Scott Cohen, Brian Price, Alan Yuille

Published: 2015-05-01T20:35:24.000Z

## Abstract

Segmenting semantic objects from images and parsing them into their respective semantic parts are fundamental steps towards detailed object understanding in computer vision. In this paper, we propose a joint solution that tackles semantic object and part segmentation simultaneously, in which higher object-level context is provided to guide part segmentation, and more detailed part-level localization is utilized to refine object segmentation. Specifically, we first introduce the concept of semantic compositional parts (SCP) in which similar semantic parts are grouped and shared among different objects. A two-channel fully convolutional network (FCN) is then trained to provide the SCP and object potentials at each pixel. At the same time, a compact set of segments can also be obtained from the SCP predictions of the network. Given the potentials and the generated segments, in order to explore long-range context, we finally construct an efficient fully connected conditional random field (FCRF) to jointly predict the final object and part labels. Extensive evaluation on three different datasets shows that our approach can mutually enhance the performance of object and part segmentation, and outperforms the current state-of-the-art on both tasks.

## 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.

- [Semantic Part Segmentation on Horse-Cow Horse (test)](<https://www.sota2.com/research/sota/semantic-part-segmentation-on-horse-cow-horse-test.md>): Semantic Part Segmentation; Horse-Cow Horse (test); Bkg Accuracy: 87.34.

- [Semantic Part Segmentation on Horse-Cow Cow (test)](<https://www.sota2.com/research/sota/semantic-part-segmentation-on-horse-cow-cow-test.md>): Semantic Part Segmentation; Horse-Cow Cow (test); Bkg Score: 85.68.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1505.00276>)

[PDF](<https://arxiv.org/pdf/1505.00276.pdf>)
