Unsupervised Triplet Hashing for Fast Image Retrieval

Abstract

The explosive growth of multimedia contents has made hashing an indispensable component in image retrieval. In particular, learning-based hashing has recently shown great promising with the advance of Convolutional Neural Network (CNN). However, the existing hashing methods are mostly tuned for classification. Learning hash functions for retrieval tasks, especially for instance-level retrieval, still faces many challenges. Considering the difficulty in obtaining labeled datasets for image retrieval task in large scale, we propose a novel CNN-based unsupervised hashing method, namely Unsupervised Triplet Hashing (UTH). The unsupervised hashing network is designed based on the following three principles: 1) maximizing the discrimination among image representations; 2) minimizing the quantization loss between the original real-valued feature descriptors and the learned hash codes; 3) maximizing the information entropy for the learned hash codes to improve their representation ability. Extensive experiments on CIFAR-10, MNIST and In-shop datasets have shown that UTH outperforms several state-of-the-art unsupervised hashing methods in terms of retrieval accuracy.