# Unsupervised Triplet Hashing for Fast Image Retrieval

arXiv: https://arxiv.org/abs/1702.08798 · HTML: https://mlsanity.com/paper/1702.08798/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Feb 2017.

## Built on by (most cited first, 5 of 5)

- [Unsupervised Hashing with Contrastive Information Bottleneck](https://mlsanity.com/paper/2105.06138/) (2021)
- [Contrastive Quantization with Code Memory for Unsupervised Image Retrieval](https://mlsanity.com/paper/2109.05205/) (2021)
- [One Loss for Quantization: Deep Hashing with Discrete Wasserstein Distributional Matching](https://mlsanity.com/paper/2205.15721/) (2022)
- [Unsupervised Hashing with Semantic Concept Mining](https://mlsanity.com/paper/2209.11475/) (2022)
- [Unsupervised Hashing with Similarity Distribution Calibration](https://mlsanity.com/paper/2302.07669/) (2023)

## Abstract (arXiv)

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.