Deep debiased contrastive hashing

doi:10.1016/j.patcog.2023.109483

Deep debiased contrastive hashing

2023-07-01

7

PRE

AI

Jingkuan Song (Jingkuan Song)

DOI：10.1016/j.patcog.2023.109483

原文链接

原文求助

摘要

En 中文

Hashing has achieved great success in multimedia retrieval due to its high computing efficiency and low storage cost. Recently, contrastive-learning-based hashing methods have achieved decent retrieval performance in label-free scenarios by learning distortion-invariant representations with Siamese networks. Their learning principle, i.e., instance discrimination , maximizes the correlation between self-augmented views and treats all others as negative samples. However, it may learn with false negative samples that are naturally similar, resulting in biased hash learning. To bridge this flaw, we reveal the between-instance similarity of naturally similar samples by exploring the latent structure of the training data. As a result, we propose the Deep Debiased Contrastive Hashing ( DDCH) algorithm, using the neighborhood discovery module to explore the intrinsic similarity relationship that can help contrastive hashing reduce false negatives for superior discriminatory ability. Furthermore, we elucidate the rationale for incorporating the module into the contrastive hashing framework and explain our hashing process from an Expectation-Maximization (EM) perspective. Extensive experimental results on three benchmark image datasets demonstrate that DDCH significantly outperforms the state-of-the-art unsupervised hashing methods for image retrieval. (c) 2023 Elsevier Ltd. All rights reserved.

Keyword:

Learning to hash

Contrastive learning

Instance discrimination

EM Algorithm

Neighborhood discovery

Deep debiased contrastive hashing

摘要

期刊

机构

引用论文