TY - GEN
T1 - Object Discovery and Localization Via Structural Contrast
AU - Dai, Shuanglu
AU - Su, Pengyu
AU - Man, Hong
N1 - Publisher Copyright:
© 2018 IEEE.
PY - 2018/8/29
Y1 - 2018/8/29
N2 - This paper explores structural contrast of object proposal for unsupervised object discovery. In this paper, an object proposal is considered as distinctive to the others in an image based on the structural uniqueness and distribution. A symmetric Kullback-Leibler (KL) distance metric is proposed to measure the difference between the distributions of structured edges. The computation of this distance metric is fully unsupervised, without any image level annotation or any labeling of visual semantics. Inspired by the pixel-level saliency filtering, a contrast-based saliency assignment is introduced to model the uniqueness and distribution distinctiveness of an object proposal as structural contrast. Visual objects can be discovered and localized by the proposals with the highest ranked structural contrast. Experiments evaluated on PascaiVOC07 demonstrate that the proposed unsupervised method outperforms the state-of-the-art unsupervised and weakly-supervised methods.
AB - This paper explores structural contrast of object proposal for unsupervised object discovery. In this paper, an object proposal is considered as distinctive to the others in an image based on the structural uniqueness and distribution. A symmetric Kullback-Leibler (KL) distance metric is proposed to measure the difference between the distributions of structured edges. The computation of this distance metric is fully unsupervised, without any image level annotation or any labeling of visual semantics. Inspired by the pixel-level saliency filtering, a contrast-based saliency assignment is introduced to model the uniqueness and distribution distinctiveness of an object proposal as structural contrast. Visual objects can be discovered and localized by the proposals with the highest ranked structural contrast. Experiments evaluated on PascaiVOC07 demonstrate that the proposed unsupervised method outperforms the state-of-the-art unsupervised and weakly-supervised methods.
KW - Object discovery
KW - Object proposal
KW - Proposal Saliency
KW - Structural contrast
UR - http://www.scopus.com/inward/record.url?scp=85062909054&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85062909054&partnerID=8YFLogxK
U2 - 10.1109/ICIP.2018.8451050
DO - 10.1109/ICIP.2018.8451050
M3 - Conference contribution
AN - SCOPUS:85062909054
T3 - Proceedings - International Conference on Image Processing, ICIP
SP - 2760
EP - 2764
BT - 2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings
T2 - 25th IEEE International Conference on Image Processing, ICIP 2018
Y2 - 7 October 2018 through 10 October 2018
ER -