Multi-label visual classification with label exclusive context

Authors:
Xiangyu Chen;Xiao-Tong Yuan;Qiang Chen;Shuicheng Yan;Tat-Seng Chua
Affiliations:
NUS Graduate School for Integrative Sciences and Engineering, Singapore;Department of Electrical and Computer Engineering, National University of Singapore, Singapore;Department of Electrical and Computer Engineering, National University of Singapore, Singapore;Department of Electrical and Computer Engineering, National University of Singapore, Singapore;NUS Graduate School for Integrative Sciences and Engineering, Singapore
Venue:
ICCV '11 Proceedings of the 2011 International Conference on Computer Vision
Year:
2011

Citing 0
Cited 4

Auto-grouped sparse representation for visual analysis

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part I
Robust image annotation via simultaneous feature and sample outlier pursuit

ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP)
Towards efficient sparse coding for scalable image annotation

Proceedings of the 21st ACM international conference on Multimedia
A Multi-View Embedding Space for Modeling Internet Images, Tags, and Their Semantics

International Journal of Computer Vision

Quantified Score

Hi-index	0.00

Visualization

Abstract

We introduce in this paper a novel approach to multi-label image classification which incorporates a new type of context--label exclusive context--with linear representation and classification. Given a set of exclusive label groups that describe the negative relationship among class labels, our method, namely LELR for Label Exclusive Linear Representation, enforces repulsive assignment of the labels from each group to a query image. The problem can be formulated as an exclusive Lasso (eLasso) model with group overlaps and affine transformation. Since existing eLasso solvers are not directly applicable to solving such an variant of eLasso in our setting, we propose a Nesterov's smoothing approximation algorithm for efficient optimization. Extensive comparing experiments on the challenging real-world visual classification benchmarks demonstrate the effectiveness of incorporating label exclusive context into visual classification.