The Secrets of Salient Object Segmentation.

TitleThe Secrets of Salient Object Segmentation.
Publication TypeCBMM Memos
Year of Publication2014
AuthorsLi, Y, Koch, C, Rehg, JM, Yuille, A
Number014
Date Published06/2014
Abstract

In this paper we provide an extensive evaluation of fixation prediction and salient object segmentation algorithms as well as statistics of major datasets. Our analysis identifies serious design flaws of existing salient object benchmarks, called the dataset design bias, by over emphasising the stereotypical concepts of saliency. The dataset design bias does not only create the discomforting disconnection between xations and salient object segmentation, but
also misleads the algorithm designing. Based on our analysis, we propose a new high quality dataset that offers both fixation and salient object segmentation ground-truth. With fixations and salient object being presented simultaneously, we are able to bridge the gap between fixations and salient objects, and propose a novel method for salient object segmentation. Finally, we report significant benchmark progress on three existing datasets of segmenting salient objects.

arXiv

arXiv:1406.2807

DSpace@MIT

http://hdl.handle.net/1721.1/100178

Download:  PDF icon CBMM-Memo-014.pdf
CBMM Memo No:  014

Research Area: 

CBMM Relationship: 

  • CBMM Funded