Constrained Local Enhancement of Semantic Features by Content-Based Sparsity - Archive ouverte HAL Access content directly
Conference Papers Year :

Constrained Local Enhancement of Semantic Features by Content-Based Sparsity

(1) , (1) , (1)
1

Abstract

Semantic features represent images by the outputs of a set of visual concept classifiers and have shown interesting performances in image classification and retrieval. All classifier outputs are usually exploited but it was recently shown that feature sparsification improves both performance and scalability. However, existing approaches consider a fixed sparsity level which disregards the actual content of individual images. In this paper, we propose a method to determine automatically a level of sparsity for the semantic features that is adapted to each image content. This method takes into account the amount of information contained by the image through a modeling of the semantic feature entropy and the confidence of individual dimensions of the feature. We also investigate the use of local regions of the image to further improve the quality of semantic features. Experimental validation is conducted on three benchmarks (Pascal VOC 2007, VOC 2012 and MIT Indoor) for image classification and two of them for image retrieval. Our method obtains competitive results on image classification and achieves state-of-the-art performances on image retrieval.
Not file

Dates and versions

cea-01813602 , version 1 (12-06-2018)

Identifiers

Cite

Youssef Tamaazousti, Hervé Le Borgne, Adrian Popescu. Constrained Local Enhancement of Semantic Features by Content-Based Sparsity. the 2016 ACM Conference on Multimedia Retrieval, Jun 2016, New York, France. ⟨10.1145/2911996.2912009⟩. ⟨cea-01813602⟩
43 View
0 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More