A fast weighted multi-view Bayesian learning scheme with deep learning for text-based image retrieval from unlabeled galleries

Aiadi, Oussama; Khaldi, Belal; Kherfi, Mohammed Lamine

doi:10.1007/s11042-022-13788-x

Cited by 5 publications

(2 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…GPTKL introduces the deep kernel learning strategy to convert the learning of transfer kernel function into learning a deep feature space; thus, GPTKL can benefit from the powerful representation capacity of deep networks. Aiadi Oussama et al propose a multi-view Gaussian-based Bayesian learning scheme, which can efficiently address text-based image retrieval problems [35]. Benefiting from assigning a weight to each view, it can better deal with intra-class variation.…”

Section: Gaussian Processmentioning

confidence: 99%

Gaussian Process-Based Transfer Kernel Learning for Unsupervised Domain Adaptation

Ge,

Sun

2023

Mathematics

View full text Add to dashboard Cite

The discriminability and transferability of models are two important factors for the success of domain adaptation methods. Recently, some domain adaptation methods have improved models by adding a discriminant information extraction module. However, these methods need to carefully balance the discriminability and transferability of a model. To address this problem, we propose a new deep domain adaptation method, Gaussian Process-based Transfer Kernel Learning (GPTKL), which can perform domain knowledge transfer and improve the discrimination ability of the model simultaneously. GPTKL uses the kernel similarity between all samples in the source and target domains as a priori information to establish a cross-domain Gaussian process. By maximizing its likelihood function, GPTKL reduces the domain discrepancy between the source and target domains, thereby enhancing generalization across domains. At the same time, GPTKL introduces the deep kernel learning strategy into the cross-domain Gaussian process to learn a transfer kernel function based on deep features. Through transfer kernel learning, GPTKL learns a deep feature space with both discriminability and transferability. In addition, GPTKL uses cross-entropy and mutual information to learn a classification model shared by the source and target domains. Experiments on four benchmarks show that GPTKL achieves superior classification performance over state-of-the-art methods.

show abstract

Section: Gaussian Processmentioning

confidence: 99%

Gaussian Process-Based Transfer Kernel Learning for Unsupervised Domain Adaptation

Ge,

Sun

2023

Mathematics

View full text Add to dashboard Cite

show abstract

“…Moreover, even if the textual information is relevant to the image, it may not contain the query keywords. Hence, several works [8]- [17] have been proposed to improve the effectiveness of textbased image retrieval systems, such as relevance feedback [18], document structure [19], [20] , query expansion [21]- [25], etc. We are interested in this paper to the use of the links for image re-ranking.…”

Section: Introduction a Motivationmentioning

confidence: 99%

Link-Driven Study to Enhance Text-Based Image Retrieval: Implicit Links Versus Explicit Links

Gasmi,

Aouadi,

Torjmen

2023

IEEE Access

View full text Add to dashboard Cite

Due to the explosive growth of digital images, new efficient and effective methodologies and tools are needed in the image retrieval field. Compared to the content-based image retrieval approach that suffers from the semantic gap, the text-based image retrieval approach has demonstrated its efficiency in retrieving relevant images for a given query. However, this approach suffers from some limitations. For example, query keywords could not match to the textual content of the document or only some images in a document are relevant to the given query. Therefore, a major challenge of the text-based approach is how to improve the image retrieval accuracy without using the image itself, i.e., by using the surrounding information (context) such as the document structure, the links, etc. To achieve this challenge, some works proposed to explore hyperlinks (explicit links) between documents to re-rank images, while more recent works proposed to automatically build implicit links between images and exploit them in the retrieval process. The aim of this paper is thus to compare the exploration of implicit links versus explicit links, either in image ranking or re-ranking. The Image CLEF 2011 collection on Wikipedia shows that not all top-ranked results are interesting to create and analyze linkages between images. In fact, only the aggregate ranking metric makes notice of the fact that linkages improve image retrieval. We also discover that the retrieval strategy-text-based retrieval with no links, implicit link-based re-ranking, or explicit link-based re-ranking-has a significant impact on the efficiency of the query process.INDEX TERMS implicit links; explicit links; re-ranking; context-based image retrieval

show abstract

Multi-view feature fusion and density-based minority over-sampling technique for amyloid protein prediction under imbalanced data

Yang,

Liu,

Zhang

et al. 2024

Applied Soft Computing

View full text Add to dashboard Cite

A fast weighted multi-view Bayesian learning scheme with deep learning for text-based image retrieval from unlabeled galleries

Cited by 5 publications

References 38 publications

Gaussian Process-Based Transfer Kernel Learning for Unsupervised Domain Adaptation

Gaussian Process-Based Transfer Kernel Learning for Unsupervised Domain Adaptation

Link-Driven Study to Enhance Text-Based Image Retrieval: Implicit Links Versus Explicit Links

Multi-view feature fusion and density-based minority over-sampling technique for amyloid protein prediction under imbalanced data

Contact Info

Product

Resources

About