Conditional Adaptation Deep Networks for Unsupervised Cross Domain Image Classifcation

Chen, Yu; Yang, Chunling; Zhang, Yan; Li, Yuze

doi:10.1109/iciea.2019.8834368

Cited by 3 publications

(3 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…D S and D T are sampled from different data distributions, p and q, where p ̸ = q. The purpose of transfer learning is to reduce the distribution difference between the source domain and the target domain by designing a network f (x) [27,[37][38][39][40].…”

Section: Joint Dynamic Maximum Mean Differencementioning

confidence: 99%

Multi-Representation Joint Dynamic Domain Adaptation Network for Cross-Database Facial Expression Recognition

Yan,

Yue,

et al. 2024

Electronics

View full text Add to dashboard Cite

In order to obtain more fine-grained information from multiple sub-feature spaces for domain adaptation, this paper proposes a novel multi-representation joint dynamic domain adaptation network (MJDDAN) and applies it to achieve cross-database facial expression recognition. The MJDDAN uses a hybrid structure to extract multi-representation features and maps the original facial expression features into multiple sub-feature spaces, aligning the expression features of the source domain and target domain in multiple sub-feature spaces from different angles to extract features more comprehensively. Moreover, the MJDDAN proposes the Joint Dynamic Maximum Mean Difference (JD-MMD) model to reduce the difference in feature distribution between different subdomains by simultaneously minimizing the maximum mean difference and local maximum mean difference in each substructure. Three databases, including eNTERFACE, FABO, and RAVDESS, are used to design a large number of cross-database transfer learning facial expression recognition experiments. The accuracy of emotion recognition experiments with eNTERFACE, FABO, and RAVDESS as target domains reach 53.64%, 43.66%, and 35.87%, respectively. Compared to the best comparison method chosen in this article, the accuracy rates were improved by 1.79%, 0.85%, and 1.02%, respectively.

show abstract

Section: Joint Dynamic Maximum Mean Differencementioning

confidence: 99%

Multi-Representation Joint Dynamic Domain Adaptation Network for Cross-Database Facial Expression Recognition

Yan,

Yue,

et al. 2024

Electronics

View full text Add to dashboard Cite

show abstract

“…Domain adaptation can solve the distribution discrepancy between the source and target domains by learning domain-invariant features. Domain adaption may be described in two forms: unsupervised domain adaptation [20], [36], [37] and supervised domain adaptation [38]- [40]. In domain adaptation, the source domain has rich learning information.…”

Section: A Domain Adaptationmentioning

confidence: 99%

Convolutional Transformer-Based Few-Shot Learning for Cross-Domain Hyperspectral Image Classification

Peng

Liu

et al. 2023

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

In cross-domain hyperspectral image (HSI) classification, the labeled samples of the target domain are very limited, and it is a worthy attention to obtain sufficient class information from the source domain to categorize the target domain classes (both the same and new unseen classes). This article investigates this problem by employing few-shot learning (FSL) in a meta-learning paradigm. However, most existing crossdomain FSL methods extract statistical features based on convolutional neural networks (CNNs), which typically only consider the local spatial information among features, while ignoring the global information. To make up for these shortcomings, this paper proposes novel convolutional transformer-based few-shot learning (CTFSL). Specifically, FSL is first performed in the classes of source and target domains simultaneously to build the consistent scenario. Then, a domain aligner is set up to map the source and target domains to the same dimensions. In addition, a convolutional transformer (CT) network is utilized to extract local-global features. Finally, a domain discriminator is executed subsequently that can not only reduce domain shift, but also distinguish from which domain a feature originates. Experiments on three widely used hyperspectral image datasets indicate that the proposed CTFSL method is superior to the state-of-the-art cross-domain FSL methods and several typical HSI classification methods in terms of classification accuracy.

show abstract

“…This method generally utilizes minimum domain spacing 8,9 or adversarial strategies 10,11 to apply the knowledge learned by the model from the source domain to the detection of the target domain, so as to solve the problem of mapping bias. In the past few years, unsupervised domain adaptation has been gradually applied and developed in the fields of image classification 12,13 and mechanical fault detection. [14][15][16] However, the detection method based on unsupervised domain adaptation still has some defects, and two problems are more prominent:…”

Section: Introductionmentioning

confidence: 99%

Active domain adaptation method for label expansion problem

Zhang

Qinle

et al. 2022

Proceedings of the Institution of Mechanical Engineers, Part O:

View full text Add to dashboard Cite

Over the past few years, cross-domain fault detection methods based on unsupervised domain adaptation (UDA) have gradually matured. However, existing methods usually assume that the source and target domains have the same label domain space, but ignore the problem of label expansion in the target domain. The source domain of such problems lacks transferable knowledge of newly added health categories, so the domain invariant features extracted by the UDA model only have a large correlation with the source domain health categories, but lack the key features to distinguish the newly added health categories. We found that most of the diagnostic results of this type of samples are distributed at the decision boundary of the source domain health category, and this special distribution means that the newly added health category samples have a high amount of information. Therefore, this paper considers using active learning to select samples of newly added health categories in the target domain to assist model training, and proposes an active domain adaptation intelligent fault detection framework LDE-ADA to deal with the label expansion problem. Finally, on the rotating machinery dataset, the analysis and comparison are carried out through six transfer tasks. The results show that when there is one new health category, the accuracy of LDE-ADA will increase by about 9.39% in the case of labeling three samples per round and training for 20 rounds. Experiments show that this method is an effective method to deal with the label expansion problem.

show abstract

Conditional Adaptation Deep Networks for Unsupervised Cross Domain Image Classifcation

Cited by 3 publications

References 11 publications

Multi-Representation Joint Dynamic Domain Adaptation Network for Cross-Database Facial Expression Recognition

Multi-Representation Joint Dynamic Domain Adaptation Network for Cross-Database Facial Expression Recognition

Convolutional Transformer-Based Few-Shot Learning for Cross-Domain Hyperspectral Image Classification

Active domain adaptation method for label expansion problem

Contact Info

Product

Resources

About