Constrained Local Enhancement of Semantic Features by Content-Based Sparsity

Youssef Tamaazousti; Hervé Le Borgne; Adrian Popescu

Constrained Local Enhancement of Semantic Features by Content-Based Sparsity

Youssef Tamaazousti ¹ Hervé Le Borgne ¹ Adrian Popescu ¹

1 DIASI - Département Intelligence Ambiante et Systèmes Interactifs

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.

Keywords : Concept- Sparsification Semantic-Features Image-Retrieval Image-Classification

Document type :

Conference papers

Domain :

Computer Science [cs]

Complete list of metadatas

https://hal-cea.archives-ouvertes.fr/cea-01813602
Contributor : Léna Le Roy <>
Submitted on : Tuesday, June 12, 2018 - 2:49:21 PM
Last modification on : Wednesday, January 23, 2019 - 2:39:24 PM

Constrained Local Enhancement of Semantic Features by Content-Based Sparsity

Identifiers

Collections

Citation

Export

Metrics

99

Contact

Constrained Local Enhancement of Semantic Features by Content-Based Sparsity

Identifiers

Collections

Citation

Export

Share

Metrics

99

Contact