Presentation 2016-09-06
Evaluation Metrics for Saliency Map Compensating Center-Bias Effect
Takao Yamanaka,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In order to evaluate the saliency maps (a probabilistic map of an image to predict human-eye fixations), a wide variety of evaluation metrics are utilized. Among them, sAUC (shuffled Area Under the Curve) has been most widely employed, because it compensates the center-bias effect, which is the tendency to look around the center of an image when a person looks at the image. In this paper, an evaluation method compensating center-bias effect is proposed for the metrics other than sAUC. It was confirmed that the proposed method can be utilized for the evaluation compensating center-bias effect with publicly available databases. Thus, an evaluation metric for saliency maps can be selected considering the properties other than the compensationability of the center-bias effect, such as differentiability of the metric.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Saliency Map / Fixation / Evaluation Metric
Paper # PRMU2016-76,IBISML2016-31
Date of Issue 2016-08-29 (PRMU, IBISML)

Conference Information
Committee PRMU / IPSJ-CVIM / IBISML
Conference Date 2016/9/5(2days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Eisaku Maeda(NTT) / / Kenji Fukumizu(ISM)
Vice Chair Seiichi Uchida(Kyushu Univ.) / Hironobu Fujiyoshi(Chubu Univ.) / / Masashi Sugiyama(Univ. of Tokyo) / Hisashi Kashima(Kyoto Univ.)
Secretary Seiichi Uchida(Kyoto Univ.) / Hironobu Fujiyoshi(NTT) / / Masashi Sugiyama(Univ. of Tokyo) / Hisashi Kashima(Nagoya Inst. of Tech.)
Assistant Masaki Oonishi(AIST) / Takuya Funatomi(NAIST) / / Toshihiro Kamishima(AIST) / Tomoharu Iwata(NTT)

Paper Information
Registration To Technical Committee on Pattern Recognition and Media Understanding / Special Interest Group on Computer Vision and Image Media / Technical Committee on Infomation-Based Induction Sciences and Machine Learning
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Evaluation Metrics for Saliency Map Compensating Center-Bias Effect
Sub Title (in English)
Keyword(1) Saliency Map
Keyword(2) Fixation
Keyword(3) Evaluation Metric
1st Author's Name Takao Yamanaka
1st Author's Affiliation Sophia University(Sophia Univ.)
Date 2016-09-06
Paper # PRMU2016-76,IBISML2016-31
Volume (vol) vol.116
Number (no) PRMU-208,IBISML-209
Page pp.pp.173-178(PRMU), pp.173-178(IBISML),
#Pages 6
Date of Issue 2016-08-29 (PRMU, IBISML)