Unsupervised Hashing with Similarity Distribution Calibration
Kam Woh Ng (University of Surrey),* Xiatian Zhu (University of Surrey), Jiun Tian Hoe (Nanyang Technological University), Chee Seng Chan (University of Malaya), Tianyu Zhang (Geek Plus), Yi-Zhe Song (University of Surrey), Tao Xiang (University of Surrey)
The 34th British Machine Vision Conference
Abstract
Unsupervised hashing methods typically aim to preserve the similarity between data points in a feature space by mapping them to binary hash codes. However, these methods often overlook the fact that the similarity between data points in the continuous feature space may not be preserved in the discrete hash code space, due to the limited similarity range of hash codes. The similarity range is bounded by the code length and can lead to a problem known as similarity collapse. That is, the positive and negative pairs of data points become less distinguishable from each other in the hash space. To alleviate this problem, in this paper a novel Similarity Distribution Calibration (SDC) method is introduced. SDC aligns the hash code similarity distribution towards a calibration distribution (e.g., beta distribution) with sufficient spread across the entire similarity range, thus alleviating the similarity collapse problem. Extensive experiments show that our SDC outperforms significantly the state-of-the-art alternatives on coarse category-level and instance-level image retrieval. Code is available at https://github.com/kamwoh/sdc.Video
Citation
@inproceedings{Ng_2023_BMVC,
author = {Kam Woh Ng and Xiatian Zhu and Jiun Tian Hoe and Chee Seng Chan and Tianyu Zhang and Yi-Zhe Song and Tao Xiang},
title = {Unsupervised Hashing with Similarity Distribution Calibration},
booktitle = {34th British Machine Vision Conference 2023, {BMVC} 2023, Aberdeen, UK, November 20-24, 2023},
publisher = {BMVA},
year = {2023},
url = {https://papers.bmvc2023.org/0053.pdf}
}
Copyright © 2023
The British Machine Vision Conference is organised by