Incremental Evolving Domain Adaptation

Bitarafan, Adeleh; Baghshah, Mahdieh Soleymani; Gheisari, Marzieh

doi:10.1109/tkde.2016.2551241

Cited by 33 publications

(29 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Step three is the domain adaptation and it computes the transformation matrix Gn from the target domain to the source domain based on the approach of Bitarafan et al [14] which adopts the GFK method [2], a manifold alignment technique.…”

Section: Proposed Ouda Methodsmentioning

confidence: 99%

“…We used the Evolving Domain Adaptation (EDA) [14] method as the reference model for comparing the classification accuracy with our proposed OUDA method and its variants. The metric for classification accuracy is based on [14] as A(n) = { n τ =1 a(τ )}/n, where A(n) is the accuracy of the n arrived data and a(τ ) is the accuracy for τ th mini-batch. Figure 4 depicts the classification accuracy when the minibatches are arriving.…”

Section: Comparison With Previous Methodsmentioning

confidence: 99%

“…To evaluate our proposed OUDA method in data classification, we performed experiments on four datasets [14]-the Traffic dataset, the Car dataset, the Waveform21 dataset, and the Waveform40 dataset. These datasets provided a large variety of time-variant images and signals to test upon.…”

Section: Datasetsmentioning

confidence: 99%

See 2 more Smart Citations

Multi-Step Online Unsupervised Domain Adaptation

Moon

Das

Lee

2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

In this paper, we address the Online Unsupervised Domain Adaptation (OUDA) problem, where the target data are unlabelled and arriving sequentially. The traditional methods on the OUDA problem mainly focus on transforming each arriving target data to the source domain, and they do not sufficiently consider the temporal coherency and accumulative statistics among the arriving target data. We propose a multi-step framework for the OUDA problem, which institutes a novel method to compute the mean-target subspace inspired by the geometrical interpretation on the Euclidean space. This meantarget subspace contains accumulative temporal information among the arrived target data. Moreover, the transformation matrix computed from the mean-target subspace is applied to the next target data as a preprocessing step, aligning the target data closer to the source domain. Experiments on four datasets demonstrated the contribution of each step in our proposed multi-step OUDA framework and its performance over previous approaches.Index Terms-Unsupervised domain adaptation, online domain adaptation, mean subspace, Grassmann manifold.

show abstract

Section: Proposed Ouda Methodsmentioning

confidence: 99%

Section: Comparison With Previous Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Multi-Step Online Unsupervised Domain Adaptation

Moon

Das

Lee

2020

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

show abstract

“…Harel and Mannor [14] learnt rotation matrices to match source data distributions to that of the target domain. Wang and Mahadevan [15] used the class labels of training data to learn the manifold alignment by simultaneously maximizing the intra-domain similarity and the inter-domain dissimilarity. By kernelizing the method in [16], Kulis et al [17] proposed to learn an asymmetric kernel transformation to transfer feature knowledge between the data from the source and target domains.…”

Section: Labelled Target Datasetmentioning

confidence: 99%

Recent Advances in Transfer Learning for Cross-Dataset Visual Recognition

Zhang

Ogunbona

et al. 2019

ACM Comput. Surv.

View full text Add to dashboard Cite

This paper takes a problem-oriented perspective and presents a comprehensive review of transfer learning methods, both shallow and deep, for cross-dataset visual recognition. Specifically, it categorises the cross-dataset recognition into seventeen problems based on a set of carefully chosen data and label attributes. Such a problem-oriented taxonomy has allowed us to examine how different transfer learning approaches tackle each problem and how well each problem has been researched to date. The comprehensive problem-oriented review of the advances in transfer learning with respect to the problem has not only revealed the challenges in transfer learning for visual recognition, but also the problems (e.g. eight of the seventeen problems) that have been scarcely studied.This survey not only presents an up-to-date technical review for researchers, but also a systematic approach and a reference for a machine learning practitioner to categorise a real problem and to look up for a possible solution accordingly.

show abstract

“…This method can search annotated data that are similar, transferring learning to the target data and thereby increasing the size of the target dataset and improving the performance of deep learning. Transfer learning can be used to transfer labels or data structures from the Source domain (training dataset of other objects) to the Target domain (training dataset of the current object) in order to improve the learning effect [7].…”

Section: Introductionmentioning

confidence: 99%

Spectral Normalization for Domain Adaptation

Zhao

Liu

2020

Information

View full text Add to dashboard Cite

The transfer learning method is used to extend our existing model to more difficult scenarios, thereby accelerating the training process and improving learning performance. The conditional adversarial domain adaptation method proposed in 2018 is a particular type of transfer learning. It uses the domain discriminator to identify which images the extracted features belong to. The features are obtained from the feature extraction network. The stability of the domain discriminator directly affects the classification accuracy. Here, we propose a new algorithm to improve the predictive accuracy. First, we introduce the Lipschitz constraint condition into domain adaptation. If the constraint condition can be satisfied, the method will be stable. Second, we analyze how to make the gradient satisfy the condition, thereby deducing the modified gradient via the spectrum regularization method. The modified gradient is then used to update the parameter matrix. The proposed method is compared to the ResNet-50, deep adaptation network, domain adversarial neural network, joint adaptation network, and conditional domain adversarial network methods using the datasets that are found in Office-31, ImageCLEF-DA, and Office-Home. The simulations demonstrate that the proposed method has a better performance than other methods with respect to accuracy.

show abstract

Incremental Evolving Domain Adaptation

Cited by 33 publications

References 31 publications

Multi-Step Online Unsupervised Domain Adaptation

Multi-Step Online Unsupervised Domain Adaptation

Recent Advances in Transfer Learning for Cross-Dataset Visual Recognition

Spectral Normalization for Domain Adaptation

Contact Info

Product

Resources

About