Creating Something From Nothing: Unsupervised Knowledge Distillation For Cross-modal Hashing
2020 · Hengtong Hu, Lingxi Xie, Richang Hong, et al.
Abstract
In recent years, cross-modal hashing (CMH) has attracted increasing attentions, mainly because its potential ability of mapping contents from different modalities, especially in vision and language, into the same space, so that it becomes efficient in cross-modal data retrieval. There are two main frameworks for CMH, differing from each other in whether semantic supervision is required. Compared to the unsupervised methods, the supervised methods often enjoy more accurate results, but require much heavier labors in data annotation. In this paper, we propose a novel approach that enables guiding a supervised method using outputs produced by an unsupervised method. Specifically, we make use of teacher-student optimization for propagating knowledge. Experiments are performed on two popular CMH benchmarks, i.e., the MIRFlickr and NUS-WIDE datasets. Our approach outperforms all existing unsupervised methods by a large margin.
Authors
(none)
Tags
Stats
Related papers
- Unsupervised Multi-modal Hashing For Cross-modal Retrieval (2019)8.35
- Semantic-cohesive Knowledge Distillation For Deep Cross-modal Hashing (2025)0.00
- Adaptive Structural Similarity Preserving For Unsupervised Cross Modal Hashing (2022)10.97
- Cluster-wise Unsupervised Hashing For Cross-modal Similarity Search (2019)11.39
- Lightweight Contrastive Distilled Hashing For Online Cross-modal Retrieval (2025)4.52
- Comprehensive Graph-conditional Similarity Preserving Network For Unsupervised Cross-modal Hashing (2020)3.14
- Fusion-supervised Deep Cross-modal Hashing (2019)8.60
- Multi-modal Mutual Information Maximization: A Novel Approach For Unsupervised Deep Cross-modal Hashing (2021)12.02