Skip to Main content Skip to Navigation
Conference papers

Kernel Square-Loss Exemplar Machines for Image Retrieval

Rafael S Rezende 1 Joaquin Zepeda 2, 3 Jean S Ponce 4, 1 Francis S Bach 5 Patrick Pérez 2 
1 WILLOW - Models of visual object recognition and scene understanding
DI-ENS - Département d'informatique - ENS Paris, Inria de Paris
5 SIERRA - Statistical Machine Learning and Parsimony
DI-ENS - Département d'informatique - ENS Paris, CNRS - Centre National de la Recherche Scientifique, Inria de Paris
Abstract : Zepeda and Pérez have recently demonstrated the promise of the exemplar SVM (ESVM) as a feature encoder for image retrieval. This paper extends this approach in several directions: We first show that replacing the hinge loss by the square loss in the ESVM cost function significantly reduces encoding time with negligible effect on accuracy. We call this model square-loss exemplar machine, or SLEM. We then introduce a kernelized SLEM which can be implemented efficiently through low-rank matrix decomposition , and displays improved performance. Both SLEM variants exploit the fact that the negative examples are fixed, so most of the SLEM computational complexity is relegated to an offline process independent of the positive examples. Our experiments establish the performance and computational advantages of our approach using a large array of base features and standard image retrieval datasets.
Document type :
Conference papers
Complete list of metadata

Cited literature [39 references]  Display  Hide  Download
Contributor : Rafael Sampaio de Rezende Connect in order to contact the contributor
Submitted on : Thursday, April 27, 2017 - 10:26:54 AM
Last modification on : Wednesday, June 8, 2022 - 12:50:06 PM
Long-term archiving on: : Friday, July 28, 2017 - 12:31:28 PM


Files produced by the author(s)


  • HAL Id : hal-01515224, version 1



Rafael S Rezende, Joaquin Zepeda, Jean S Ponce, Francis S Bach, Patrick Pérez. Kernel Square-Loss Exemplar Machines for Image Retrieval. Computer Vision and Pattern Recognition 2017, Jul 2017, Honolulu, United States. ⟨hal-01515224⟩



Record views


Files downloads