Unsupervised Triplet Hashing for Fast Image Retrieval
This work addresses the challenge of instance-level image retrieval for applications needing efficient search without labeled data, though it is incremental as it builds on existing CNN-based hashing methods.
The paper tackled the problem of large-scale image retrieval by proposing an unsupervised hashing method to address the lack of labeled datasets, achieving improved retrieval accuracy on benchmarks like CIFAR-10, MNIST, and In-shop datasets.
Hashing has played a pivotal role in large-scale image retrieval. With the development of Convolutional Neural Network (CNN), hashing learning has shown great promise. But existing methods are mostly tuned for classification, which are not optimized for retrieval tasks, especially for instance-level retrieval. In this study, we propose a novel hashing method for large-scale image retrieval. 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 under the following three principles: 1) more discriminative representations for image retrieval; 2) minimum quantization loss between the original real-valued feature descriptors and the learned hash codes; 3) maximum information entropy for the learned hash codes. 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.