Contradictory Structure Learning for Semi-supervised Domain Adaptation

Qin, Can; Wang, Lichen; Ma, Qianqian; Yin, Yu; Wang, Huan; Fu, Yun

doi:10.48550/arxiv.2002.02545

Cited by 8 publications

(21 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Semi-supervised domain adaptation (SSDA) is a relatively promising form of transfer learning, which intents to leverage a small number of labeled samples (e.g, one or few samples per class) in the target domain and give full play to their potential to greatly improve the performance of domain adaptation. Recently, SSDA has recently attracted wide attentions [32,29,15,21,17,42] from researchers. [32,29] first proposed to solve SSDA by align-ing the features from both domains by means of adversarial learning.…”

Section: Semi-supervised Domain Adaptationmentioning

confidence: 99%

“…Recently, SSDA has recently attracted wide attentions [32,29,15,21,17,42] from researchers. [32,29] first proposed to solve SSDA by align-ing the features from both domains by means of adversarial learning. [15] proposed to reduce intra-domain discrepancy within the target domain to attract unaligned target sub-distributions towards the corresponding source subdistributions so as to improve feature alignment across domains.…”

Section: Semi-supervised Domain Adaptationmentioning

confidence: 99%

“…To train our model with supervision from all labeled data from both source and target domains, we follow the practices of existing work on SSDA [32,29,15,21,17,42], and include the following standard cross-entropy loss in the training loss,…”

Section: Ns I=1mentioning

confidence: 99%

“…D, W and A) with 31 classes. For fair comparisons, the settings of our benchmark datasets refer to the existing SSDA approaches [32,29,17], including adaptation scenarios of each dataset, the number of labeled target data (typically 1-shot or 3-shot per class), sample selection strategies, etc.…”

Section: Setupsmentioning

confidence: 99%

“…Implementation details: Similar to previous SSDA work [32,15], we choose Alexnet and Resnet34 as our backbone networks. Firstly, the feature extractor is initialized with a pre-trained model on ImageNet 4 and the linear classification layer is initialized randomly, which has the same setting as [32,29,17,15], such as architecture, output feature size, and so on. To balance multiple loss terms, we set λ in Equation ( 7) to 1.0 and ν in Equation (8) to 30.0.…”

Section: Setupsmentioning

confidence: 99%

See 4 more Smart Citations

Cross-Domain Adaptive Clustering for Semi-Supervised Domain Adaptation

Li²,

Shi

et al. 2021

2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

In semi-supervised domain adaptation, a few labeled samples per class in the target domain guide features of the remaining target samples to aggregate around them. However, the trained model cannot produce a highly discriminative feature representation for the target domain because the training data is dominated by labeled samples from the source domain. This could lead to disconnection between the labeled and unlabeled target samples as well as misalignment between unlabeled target samples and the source domain. In this paper, we propose a novel approach called Cross-domain Adaptive Clustering to address this problem. To achieve both inter-domain and intra-domain adaptation, we first introduce an adversarial adaptive clustering loss to group features of unlabeled target data into clusters and perform cluster-wise feature alignment across the source and target domains. We further apply pseudo labeling to unlabeled samples in the target domain and retain pseudolabels with high confidence. Pseudo labeling expands the number of "labeled" samples in each class in the target domain, and thus produces a more robust and powerful cluster core for each class to facilitate adversarial learning. Extensive experiments on benchmark datasets, including DomainNet, Office-Home and Office, demonstrate that our proposed approach achieves the state-of-the-art performance in semi-supervised domain adaptation.

show abstract

Section: Semi-supervised Domain Adaptationmentioning

confidence: 99%

Section: Semi-supervised Domain Adaptationmentioning

confidence: 99%

Section: Ns I=1mentioning

confidence: 99%

Section: Setupsmentioning

confidence: 99%

Section: Setupsmentioning

confidence: 99%

See 3 more Smart Citations

Cross-Domain Adaptive Clustering for Semi-Supervised Domain Adaptation

Li²,

Shi

et al. 2021

2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

show abstract

Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer

Liang

Wang

et al. 2021

IEEE Trans. Pattern Anal. Mach. Intell.

142

250

View full text Add to dashboard Cite

Unsupervised domain adaptation (UDA) aims to transfer knowledge from a related but different well-labeled source domain to a new unlabeled target domain. Most existing UDA methods require access to the source data, and thus are not applicable when the data are confidential and not shareable due to privacy concerns. This paper aims to tackle a realistic setting with only a classification model available trained over, instead of accessing to, the source data. To effectively utilize the source model for adaptation, we propose a novel approach called Source HypOthesis Transfer (SHOT), which learns the feature extraction module for the target domain by fitting the target data features to the frozen source classification module (representing classification hypothesis). Specifically, SHOT exploits both information maximization and self-supervised learning for the feature extraction module learning to ensure the target features are implicitly aligned with the features of unseen source data via the same hypothesis. Furthermore, we propose a new labeling transfer strategy, which separates the target data into two splits based on the confidence of predictions (labeling information), and then employ semi-supervised learning to improve the accuracy of less-confident predictions in the target domain. We denote labeling transfer as SHOT++ if the predictions are obtained by SHOT. Extensive experiments on both digit classification and object recognition tasks show that SHOT and SHOT++ achieve results surpassing or comparable to the state-of-the-arts, demonstrating the effectiveness of our approaches for various visual domain adaptation problems. Code will be available at https://github.com/tim-learn/SHOT-plus.

show abstract

Deep Co-Training with Task Decomposition for Semi-Supervised Domain Adaptation

Yang¹,

Wang²,

Gao³

et al. 2020

Preprint

View full text Add to dashboard Cite

Semi-supervised domain adaptation (SSDA) aims to adapt models from a labeled source domain to a different but related target domain, from which unlabeled data and a small set of labeled data are provided. In this paper we propose a new approach for SSDA, which is to explicitly decompose SSDA into two subproblems: a semi-supervised learning (SSL) problem in the target domain and an unsupervised domain adaptation (UDA) problem across domains. We show that these two sub-problems yield very different classifiers, which we leverage with our algorithm MixUp Co-training (MICO). MICO applies MIXUP to bridge the gap between labeled and unlabeled data of each individual model and employs co-training to exchange the expertise between the two classifiers. MICO needs no adversarial and minmax training, making it easily implementable and stable. MICO achieves state-of-the-art results on SSDA datasets, outperforming the prior art by a notable 4% margin on DomainNet.Preprint. Under review.

show abstract

Contradictory Structure Learning for Semi-supervised Domain Adaptation

Cited by 8 publications

References 40 publications

Cross-Domain Adaptive Clustering for Semi-Supervised Domain Adaptation

Cross-Domain Adaptive Clustering for Semi-Supervised Domain Adaptation

Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer

Deep Co-Training with Task Decomposition for Semi-Supervised Domain Adaptation

Contact Info

Product

Resources

About