Hamming Embedding Similarity-based Image Classification

Mihir Jain 1 Rachid Benmokhtar 1 Patrick Gros 1 Hervé Jégou 1
1 TEXMEX - Multimedia content-based indexing
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
Abstract : In this paper, we have presented a novel approach to image classification based on a matching technique. It consists in combining the Hamming-Embedding similarity-based matching method with a similarity space encoding, which subsequently allows the use of a linear SVM. This method is efficient and achieves state-of-the-art classification results on two reference image classification benchmarks: the PASCAL VOC 2007 and Caltech-256 datasets. Moreover, it is shown to be complementary with the other best classification method based, namely the Fisher kernel. To our knowledge, this method is the first matching-based approach to provide such competitive results. We believe that the flexibility offered by this framework is likely to be extended, in particular for a better integration of the geometrical constraints. As a secondary contribution, we have proposed an effective variant of the SIFT descriptor, which gives a slight yet consistent improvement on classification accuracy. Its interest has been validated with the Fisher Kernel.
Document type :
Conference papers
Complete list of metadatas

Cited literature [27 references]  Display  Hide  Download


https://hal.inria.fr/hal-00688169
Contributor : Hervé Jégou <>
Submitted on : Monday, April 16, 2012 - 11:37:33 PM
Last modification on : Friday, November 16, 2018 - 1:24:59 AM
Long-term archiving on : Monday, November 26, 2012 - 2:50:36 PM

Files

hal_v1.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00688169, version 1

Citation

Mihir Jain, Rachid Benmokhtar, Patrick Gros, Hervé Jégou. Hamming Embedding Similarity-based Image Classification. ICMR - ACM International Conference on Multimedia Retrieval, Jun 2012, Hong-Kong, Hong Kong SAR China. ⟨hal-00688169⟩

Share

Metrics

Record views

1166

Files downloads

1349