Adaptive Labeling for Deep Learning to Hash

Huei-Fang Yang, Cheng-Hao Tu, Chu-Song Chen; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2019, pp. 0-0

Abstract


Hash function learning has been widely used for large-scale image retrieval because of the efficiency of computation and storage. We introduce AdaLabelHash, a binary hash function learning approach via deep neural networks in this paper. In AdaLabelHash, class label representations are variables that are adapted during the backward network training procedure. We express the labels as hypercube vertices in a K-dimensional space, and the class label representations together with the network weights are updated in the learning process. As the label representations (or referred to as codewords in this work), are learned from data, semantically similar classes will be assigned with the codewords that are close to each other in terms of Hamming distance in the label space. The codewords then serve as the desired output of the hash function learning, and yield compact and discriminating binary hash representations. AdaLabelHash is easy to implement, which can jointly learn label representations and infer compact binary codes from data. It is applicable to both supervised and semi-supervised hash. Experimental results on standard benchmarks demonstrate the satisfactory performance of AdaLabelHash.

Related Material


[pdf]
[bibtex]
@InProceedings{Yang_2019_CVPR_Workshops,
author = {Yang, Huei-Fang and Tu, Cheng-Hao and Chen, Chu-Song},
title = {Adaptive Labeling for Deep Learning to Hash},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2019}
}