Dual Self-Paced Cross-Modal Hashing
Open Access
- 24 March 2024
- journal article
- research article
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 38 (14) , 15184-15192
Abstract
Cross-modal hashing~(CMH) is an efficient technique to retrieve relevant data across different modalities, such as images, texts, and videos, which has attracted more and more attention due to its low storage cost and fast query speed. Although existing CMH methods achieve remarkable processes, almost all of them treat all samples of varying difficulty levels without discrimination, thus leaving them vulnerable to noise or outliers. Based on this observation, we reveal and study dual difficulty levels implied in cross-modal hashing learning, \ie instance-level and feature-level difficulty. To address this problem, we propose a novel Dual Self-Paced Cross-Modal Hashing (DSCMH) that mimics human cognitive learning to learn hashing from ``easy'' to ``hard'' in both instance and feature levels, thereby embracing robustness against noise/outliers. Specifically, our DSCMH assigns weights to each instance and feature to measure their difficulty or reliability, and then uses these weights to automatically filter out the noisy and irrelevant data points in the original space. By gradually increasing the weights during training, our method can focus on more instances and features from ``easy'' to ``hard'' in training, thus mitigating the adverse effects of noise or outliers. Extensive experiments are conducted on three widely-used benchmark datasets to demonstrate the effectiveness and robustness of the proposed DSCMH over 12 state-of-the-art CMH methods.Keywords
This publication has 21 references indexed in Scilit:
- Hierarchical Hashing Learning for Image Set ClassificationIEEE Transactions on Image Processing, 2023
- Asymmetric Supervised Fusion-Oriented Hashing for Cross-Modal RetrievalIEEE Transactions on Cybernetics, 2023
- Robust and discrete matrix factorization hashing for cross-modal retrievalPattern Recognition, 2022
- Cognitive multi-modal consistent hashing with flexible semantic transformationInformation Processing & Management, 2022
- Fast Cross-Modal Hashing With Global and Local Similarity EmbeddingIEEE Transactions on Cybernetics, 2021
- Joint Versus Independent Multiview Hashing for Cross-View RetrievalIEEE Transactions on Cybernetics, 2020
- BATCH: A Scalable Asymmetric Discrete Cross-Modal HashingIEEE Transactions on Knowledge and Data Engineering, 2020
- Discrete Latent Factor Model for Cross-Modal HashingIEEE Transactions on Image Processing, 2019
- Collective Reconstructive Embeddings for Cross-Modal HashingIEEE Transactions on Image Processing, 2018
- Numerics of Gram-Schmidt orthogonalizationLinear Algebra and its Applications, 1994