Image Cosegmentation via Multi-task Learning

Qiang Zhang, Jiayu Zhou, Yilin Wang, Jieping Ye and Baoxin Li

In Proceedings British Machine Vision Conference 2014


Image segmentation has been studied by computer vision researchers for decades and still remains a challenging task. One major difficulty results from the differences between the foreground object and background could be very ambiguous, especially when prior knowledge is missing. To overcome this difficulty, cosegmentation is proposed, where a set of image, which are assumed to share common foreground objects, are segmented simultaneously. Different Models have been proposed for exploring the prior of the common foreground objects. In this paper, we propose to formulate the image cosegmentaion problem under multi-task learning framework, where segmenting each image is viewed as one task and the prior that common object is shared in the images is modeled as the intrinsic relatedness among the tasks. Compared with the existing methods, the proposed method is able to simultaneously segmenting more than two images and has low computational cost. The proposed method is evaluated on two common datasets, CMU iCoseg dataset and MSRC dataset, with comparisons to existing methods. In addition, we analysis and compare three types of multi-task learning frameworks. The experiment results demonstrate the effectiveness of the proposed method.


Poster Session


Extended Abstract (PDF, 1 page, 675K)
Paper (PDF, 13 pages, 1.1M)
Bibtex File


Qiang Zhang, Jiayu Zhou, Yilin Wang, Jieping Ye, and Baoxin Li. Image Cosegmentation via Multi-task Learning. Proceedings of the British Machine Vision Conference. BMVA Press, September 2014.


	title = {Image Cosegmentation via Multi-task Learning},
	author = {Zhang, Qiang and Zhou, Jiayu and Wang, Yilin and Ye, Jieping and Li, Baoxin},
	year = {2014},
	booktitle = {Proceedings of the British Machine Vision Conference},
	publisher = {BMVA Press},
	editors = {Valstar, Michel and French, Andrew and Pridmore, Tony}
	doi = { }