Weighted Contrastive Hashing

Abstract

The development of unsupervised hashing is advanced by the recent popular contrastive learning paradigm. However, previous contrastive learning-based works have been hampered by (1) insufficient data similarity mining based on global-only image representations, and (2) the hash code semantic loss caused by the data augmentation. In this paper, we propose a novel method, namely Weighted Contrative Hashing (WCH), to take a step towards solving these two problems. We introduce a novel mutual attention module to alleviate the problem of information asymmetry in network features caused by the missing image structure during contrative augmentation. Furthermore, we explore the fine-grained semantic relations between images, i.e., we divide the images into multiple patches and calculate similarities between patches. The aggregated weighted similarities, which reflect the deep image relations, are distilled to facilitate the hash codes learning with a distillation loss, so as to obtain better r

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyyu2022weighted

Related papers

• Unsupervised Hashing With Contrastive Information Bottleneck (2021)13.50
• Coophash: Cooperative Learning Of Multipurpose Descriptor And Contrastive Pair Generator Via Variational MCMC Teaching For Supervised Image Hashing (2022)0.00
• Hyperbolic Hierarchical Contrastive Hashing (2022)10.97
• Lightweight Contrastive Distilled Hashing For Online Cross-modal Retrieval (2025)4.52
• Deep Self-adaptive Hashing For Image Retrieval (2021)8.35
• Deep Hashing: A Joint Approach For Image Signature Learning (2016)5.24
• Deep Class-wise Hashing: Semantics-preserving Hashing Via Class-wise Loss (2018)11.19
• Unsupervised Domain-adaptive Hash For Networks (2021)0.00