CVIRFeb 15, 2023

Unsupervised Hashing with Similarity Distribution Calibration

arXiv:2302.07669v211 citationsh-index: 34Has Code
Originality Incremental advance
AI Analysis

This addresses a specific bottleneck in unsupervised hashing for image retrieval, offering an incremental improvement by calibrating similarity distributions to enhance retrieval accuracy.

The paper tackles the similarity collapse problem in unsupervised hashing, where discrete hash codes fail to preserve similarity from continuous feature spaces, by introducing a Similarity Distribution Calibration (SDC) method that aligns hash code similarity distributions to a calibration distribution, resulting in significant outperformance over state-of-the-art methods in image retrieval tasks.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes