The Secrets of Salient Object Segmentation
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 ster...
Main Authors: | Li, Yin, Hou, Xiaodi, Koch, Christof, Rehg, James M., Yuille, Alan L. |
---|---|
Format: | Technical Report |
Language: | en_US |
Published: |
Center for Brains, Minds and Machines (CBMM), arXiv
2015
|
Subjects: | |
Online Access: | http://hdl.handle.net/1721.1/100178 |
Similar Items
-
Detect What You Can: Detecting and Representing Objects using Holistic Models and Body Parts
by: Chen, Xianjie, et al.
Published: (2015) -
Parsing Semantic Parts of Cars Using Graphical Models and Segment Appearance Consistency
by: Lu, Wenhao, et al.
Published: (2015) -
Discriminate-and-Rectify Encoders: Learning from Image Transformation Sets
by: Tachetti, Andrea, et al.
Published: (2017) -
Human-Machine CRFs for Identifying Bottlenecks in Holistic Scene Understanding
by: Mottaghi, Roozbeh, et al.
Published: (2015) -
Semantic Part Segmentation using Compositional Model combining Shape and Appearance
by: Wang, Jianyu, et al.
Published: (2015)