Joint Object and Part Segmentation Using Deep Learned Potentials
Authors:
- Peng WangPWPeng Wang
- Xiaohui ShenXSXiaohui Shen
- Zhe LinZLZhe Lin
- Scott CohenSCScott Cohen
- Brian PriceBPBrian Price
- Alan YuilleAYAlan Yuille
- 1 December 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1573-1581
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-stream 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.Keywords
All Related Versions
This publication has 31 references indexed in Scilit:
- Semantic part segmentation using compositional model combining shape and appearance2015
- Towards unified depth and semantic prediction from a single image2015
- Towards Unified Human Parsing and Pose Estimation2014
- DeepPose: Human Pose Estimation via Deep Neural Networks2014
- Context as Supervisory Signal: Discovering Objects with Predictable Context2014
- Articulated part-based model for joint object detection and pose estimation2011
- The truth about cats and dogs2011
- Shared parts for deformable part-based models2011
- Auto-Context and Its Application to High-Level Vision Tasks and 3D Brain Image SegmentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2009
- Using Recognition to Guide a Robot's Attention2008