Fast Online Hashing with Multi-Label Projection

TL;DR

This paper introduces a fast online hashing method that updates only relevant binary codes using multi-label supervision, significantly improving retrieval efficiency while maintaining accuracy in large-scale nearest neighbor search.

Contribution

The proposed FOH method efficiently updates only a subset of binary codes based on potential neighbors and incorporates multi-label supervision, enhancing speed and preserving data similarity.

Findings

Achieves up to 6.28 seconds faster query times than baselines.

Maintains competitive retrieval accuracy.

Effectively handles multi-label data in online hashing.

Abstract

Hashing has been widely researched to solve the large-scale approximate nearest neighbor search problem owing to its time and storage superiority. In recent years, a number of online hashing methods have emerged, which can update the hash functions to adapt to the new stream data and realize dynamic retrieval. However, existing online hashing methods are required to update the whole database with the latest hash functions when a query arrives, which leads to low retrieval efficiency with the continuous increase of the stream data. On the other hand, these methods ignore the supervision relationship among the examples, especially in the multi-label case. In this paper, we propose a novel Fast Online Hashing (FOH) method which only updates the binary codes of a small part of the database. To be specific, we first build a query pool in which the nearest neighbors of each central point are recorded. When a new query arrives, only the binary codes of the corresponding potential neighbors are updated. In addition, we create a similarity matrix which takes the multi-label supervision information into account and bring in the multi-label projection loss to further preserve the similarity among the multi-label data. The experimental results on two common benchmarks show that the proposed FOH can achieve dramatic superiority on query time up to 6.28 seconds less than state-of-the-art baselines with competitive retrieval accuracy.