Unsupervised multi-class co-segmentation via joint object detection and segmentation with energy minimization
Lists
Only you see this
Abstract
Multi-class co-segmentation is a challenging task because of the variety and complexity of the objects and images. To get more accurate object proposals is the key step for the existing co-segmentation methods to obtain better performance. In this paper, we propose a novel method to co-segment multiple regions from a group of images in an unsupervised way. The key idea is to discover unknown object proposals for each image via joint object detection and object-level segmentation. First, object proposals of each image are generated by object-like windows (or boxes) and object-level segmentation using graph cuts, and two Gaussian mixture models (GMMs) are employed to characterize the object proposals for all images and single image, respectively. Then, a weighted graph for each image is constructed on super-pixel level, and multi-label graph cuts with global and local energy is employed to obtain the final co-segmentation results. In contrast to previous methods, our method could obtain the object proposals with high objectness by object-level segmentation. Experimental results demonstrate the good performance of the proposed method on the multi-class co-segmentation.
BibTeX
@inproceedings{li2015unsupervised,
author = {Lei Li and Xuan Fei and Zhuoli Dong and Dexian Zhang},
title = {{Unsupervised multi-class co-segmentation via joint object detection and segmentation with energy minimization}},
booktitle = {Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE},
year = {2015},
doi = {10.1117/12.2210737},
}Loading related content...