Joint Object and Part Segmentation using Deep Learned Potentials

TL;DR

This paper presents a joint object and part segmentation method that leverages deep learned potentials and a fully connected CRF to improve accuracy by utilizing object-level context and detailed part localization.

Contribution

It introduces semantic compositional parts (SCP) and a two-channel FCN for joint segmentation, enhancing performance over existing methods.

Findings

Outperforms state-of-the-art on three datasets

Mutually improves object and part segmentation accuracy

Effectively utilizes long-range context for detailed parsing

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.