Skip to Main content Skip to Navigation
New interface
Conference papers

Interpretable Visual Models for Human Perception-Based Object Retrieval

Ahmed-Riadh Rebai 1 Alexis Joly 1, 2 Nozha Boujemaa 1 
2 ZENITH - Scientific Data Management
LIRMM - Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier, CRISAM - Inria Sophia Antipolis - Méditerranée
Abstract : Understanding the results returned by automatic visual concept detectors is often a tricky task making users uncomfortable with these technologies. In this paper we attempt to build humanly interpretable visual models, allowing the user to visually understand the underlying semantic. We therefore propose a supervised multiple instance learning algorithm that selects as few as possible discriminant local features for a given object category. The method finds its roots in the lasso theory where a L1-regularization term is introduced in order to constraint the loss function, and subsequently produce sparser solutions. Efficient resolution of the lasso path is achieved through a boosting-like procedure inspired by BLasso algorithm. Quantitatively, our method achieves similar performance as current state-of-the-art, and qualitatively, it allows users to construct their own model from the original set of patches learned, thus allowing for more compound semantic queries.
Complete list of metadata

Cited literature [12 references]  Display  Hide  Download
Contributor : Alexis Joly Connect in order to contact the contributor
Submitted on : Thursday, November 17, 2011 - 3:58:34 PM
Last modification on : Tuesday, September 6, 2022 - 4:55:59 PM
Long-term archiving on: : Monday, December 5, 2016 - 9:14:02 AM


Files produced by the author(s)




Ahmed-Riadh Rebai, Alexis Joly, Nozha Boujemaa. Interpretable Visual Models for Human Perception-Based Object Retrieval. ICMR'11 - First ACM International Conference on Multimedia Retrieval, Apr 2011, Trento, Italy. pp.21:1--21:8, ⟨10.1145/1991996.1992017⟩. ⟨hal-00642232⟩



Record views


Files downloads