UNSUPERVISED DEEP HASHING WITH STACKED CONVOLUTIONAL AUTOENCODERS

Sovann En 1 Bruno Crémilleux 2 Frédéric Jurie 1
1 Equipe Image - Laboratoire GREYC - UMR6072
GREYC - Groupe de Recherche en Informatique, Image, Automatique et Instrumentation de Caen
2 Equipe CODAG - Laboratoire GREYC - UMR6072
GREYC - Groupe de Recherche en Informatique, Image, Automatique et Instrumentation de Caen
Abstract : Learning-based image hashing consists in turning high-dimensional image features into compact binary codes, while preserving their semantic similarity (i.e., if two images are close in terms of content, their codes should be close as well). In this context, many existing hashing techniques rely on supervision for preserving these semantic properties. In this paper , we aim at learning such binary codes by exploiting the underlying structure of unlabeled data, using deep learning. The proposed deep network is based on a stacked convolu-tional autoencoder which hierarchically maps input images into a low-dimensional space. A binary relaxation constraint applied to the middle layer of the network – the one containing the code – makes the codes sparse and binary. To demonstrate the competitiveness of the proposed architecture, we evaluate the so produced hash codes on image retrieval and image classification tasks on the MNIST dataset, and compare its performance with state-of-the-art approaches.
Document type :
Conference papers
Complete list of metadatas

Cited literature [24 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01528097
Contributor : Frederic Jurie <>
Submitted on : Wednesday, May 31, 2017 - 11:51:30 AM
Last modification on : Tuesday, February 26, 2019 - 6:06:02 PM
Long-term archiving on : Wednesday, September 6, 2017 - 10:26:26 AM

File

icip-17-hashing.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01528097, version 1

Citation

Sovann En, Bruno Crémilleux, Frédéric Jurie. UNSUPERVISED DEEP HASHING WITH STACKED CONVOLUTIONAL AUTOENCODERS. IEEE International Conference on Image Processing, Sep 2017, Bejing, China. ⟨hal-01528097⟩

Share

Metrics

Record views

346

Files downloads

1981