Diverse concept-level features for multi-object classification

Abstract : We consider the problem of image classification with semantic features that are built from a set of base classifier outputs, each reflecting visual concepts. However, existing approaches consider visual concepts independently from each other whereas they are often linked together. When those relations are considered, existing models strongly rely on image low-level features, yielding in irrelevant relations when the low-level representation fails. On the contrary, the approach we propose, uses existing human knowledge, the application context itself and the human categorization mechanism to reflect complex relations between concepts. By nesting this human knowledge and the application context in the concept detection and selection processes, our final semantic feature captures the most useful information for an effective categorization. Thus, it enables to give good representation, even if some important concepts failed to be recognized. Experimental validation is conducted on three publicly available benchmarks of multi-class object classification and leads to results that outperforms comparable approaches.
Document type :
Conference papers
Complete list of metadatas

Contributor : Léna Le Roy <>
Submitted on : Tuesday, June 12, 2018 - 3:30:23 PM
Last modification on : Wednesday, January 23, 2019 - 2:39:24 PM



Y. Tamaazousti, H. Le Borgne, Celine Hudelot. Diverse concept-level features for multi-object classification. ICMR '16 Proceedings of the 2016 ACM on International Conference on Multimedia Retrieval Pages 63-70, Jun 2016, New York, United States. pp.63-70, ⟨10.1145/2911996.2912013⟩. ⟨cea-01813723⟩



Record views