Efficient inter-image relation graph neural network hashing for scalable image retrieval

Cui, Hui; Zhu, Lei; Tan, Wentao

doi:10.1145/3444685.3446321

Cited by 6 publications

(6 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hashing aims to learn hash functions that encode highdimensional data into binary hash codes while maintaining semantic relationships. It offers advantageous attributes in terms of data storage efficiency and retrieval speed, which has consequently garnered significant attention (Zhu et al 2020;Lu et al 2019;Cui et al 2020Cui et al , 2021. Hashing can be broadly categorized based on its reliance on semantic labels: unsupervised hashing and supervised hashing.…”

Section: Related Workmentioning

confidence: 99%

Effective Comparative Prototype Hashing for Unsupervised Domain Adaptation

Cui,

Zhao,

et al. 2024

AAAI

View full text Add to dashboard Cite

Unsupervised domain adaptive hashing is a highly promising research direction within the field of retrieval. It aims to transfer valuable insights from the source domain to the target domain while maintaining high storage and retrieval efficiency. Despite its potential, this field remains relatively unexplored. Previous methods usually lead to unsatisfactory retrieval performance, as they frequently directly apply slightly modified domain adaptation algorithms to hash learning framework, or pursue domain alignment within the Hamming space characterized by limited semantic information. In this paper, we propose a simple yet effective approach named Comparative Prototype Hashing (CPH) for unsupervised domain adaptive image retrieval. We establish a domain-shared unit hypersphere space through prototype contrastive learning and then obtain the Hamming hypersphere space via mapping from the shared hypersphere. This strategy achieves a cohesive synergy between learning uniformly distributed and category conflict-averse feature representations, eliminating domain discrepancies, and facilitating hash code learning. Moreover, by leveraging dual-domain information to supervise the entire hashing model training process, we can generate hash codes that retain inter-sample similarity relationships within both domains. Experimental results validate that our CPH significantly outperforms the state-of-the-art counterparts across multiple cross-domain and single-domain retrieval tasks. Notably, on Office-Home and Office-31 datasets, CPH achieves an average performance improvement of 19.29% and 13.85% on cross-domain retrieval tasks compared to the second-best results, respectively. The source codes of our method are available at: https://github.com/christinecui/CPH.

show abstract

Section: Related Workmentioning

confidence: 99%

Effective Comparative Prototype Hashing for Unsupervised Domain Adaptation

Cui,

Zhao,

et al. 2024

AAAI

View full text Add to dashboard Cite

show abstract

“…In this paper, we therefore focus on hashing methods, particularly aiming to minimise the aforementioned semantic gap of data from different modalities. Hashing approaches are distinguished into single-view [6,27] and multi-view approaches [4,11,20,21,23,[35][36][37]. The former approaches can only handle one modality, while the latter approaches support two or more modalities.…”

Section: Musehash: Supervised Bayesian Hashing For Multimodal Image R...mentioning

confidence: 99%

“…The former approaches can only handle one modality, while the latter approaches support two or more modalities. In addition, they can categorised into unsupervised [6,11,37] and supervised [4,15,20,21,23,27,35,36] depending on the method of learning hash functions. In general, supervised methods can take more advantage of the inner relationships of data from annotation and due to that they perform better than unsupervised methods.…”

Section: Musehash: Supervised Bayesian Hashing For Multimodal Image R...mentioning

confidence: 99%

“…Unsupervised Deep Hashing with Pseudo Labels (UDHPL) [11] generates the pseudo-labels through the Bayes' rule and maximizes the correlation between the projection vectors of pseudo-labels and deep features. Lightweight Augmented Graph Network Hashing (LAGNH) [6] uses a lightweight deep learning network with the assistance of the auxiliary semantics, which significantly reduces the number of parameters of the network and accelerates the training process.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

MuseHash: Supervised Bayesian Hashing for Multimodal Image Representation

Pegia

Jónsson

Moumtzidou

et al. 2023

Proceedings of the 2023 ACM International Conference on Multimedia Retrieval

View full text Add to dashboard Cite

“…People are no longer content with a single form of access to data, which makes it urgent to retrieve multimedia data swiftly and efficiently. However, multi-modal data are massive, heterogeneous and highly dimensional, and the retrieval of multi-modal data takes a great deal of time and storage space [ 1 ]. Therefore, it is crucial to reduce the storage space of multi-modal data and improve retrieval performance.…”

Section: Introductionmentioning

confidence: 99%

CLIP-Based Adaptive Graph Attention Network for Large-Scale Unsupervised Multi-Modal Hashing Retrieval

et al. 2023

Sensors

View full text Add to dashboard Cite

With the proliferation of multi-modal data generated by various sensors, unsupervised multi-modal hashing retrieval has been extensively studied due to its advantages in storage, retrieval efficiency, and label independence. However, there are still two obstacles to existing unsupervised methods: (1) As existing methods cannot fully capture the complementary and co-occurrence information of multi-modal data, existing methods suffer from inaccurate similarity measures. (2) Existing methods suffer from unbalanced multi-modal learning and data semantic structure being corrupted in the process of hash codes binarization. To address these obstacles, we devise an effective CLIP-based Adaptive Graph Attention Network (CAGAN) for large-scale unsupervised multi-modal hashing retrieval. Firstly, we use the multi-modal model CLIP to extract fine-grained semantic features, mine similar information from different perspectives of multi-modal data and perform similarity fusion and enhancement. In addition, this paper proposes an adaptive graph attention network to assist the learning of hash codes, which uses an attention mechanism to learn adaptive graph similarity across modalities. It further aggregates the intrinsic neighborhood information of neighboring data nodes through a graph convolutional network to generate more discriminative hash codes. Finally, this paper employs an iterative approximate optimization strategy to mitigate the information loss in the binarization process. Extensive experiments on three benchmark datasets demonstrate that the proposed method significantly outperforms several representative hashing methods in unsupervised multi-modal retrieval tasks.

show abstract

Efficient inter-image relation graph neural network hashing for scalable image retrieval

Cited by 6 publications

References 44 publications

Effective Comparative Prototype Hashing for Unsupervised Domain Adaptation

Effective Comparative Prototype Hashing for Unsupervised Domain Adaptation

MuseHash: Supervised Bayesian Hashing for Multimodal Image Representation

CLIP-Based Adaptive Graph Attention Network for Large-Scale Unsupervised Multi-Modal Hashing Retrieval

Contact Info

Product

Resources

About