Cross-domain Self-supervised Learning for Domain Adaptation with Few Source Labels

Kim, Donghyun; Saito, Kuniaki; Oh, Tae-Hyun; Plummer, Bryan A.; Sclaroff, Stan; Saenko, Kate

doi:10.48550/arxiv.2003.08264

Cited by 17 publications

(46 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, self-supervised learning methods [35,33] have been proposed to perform domain alignment between two domains. One trivial extension is combining all source domains first, and then perform domain alignment between M i=1 S i ∪ S u i and T .…”

Section: Multi-domain Prototypical Self-supervised Learningmentioning

confidence: 99%

“…We evaluate our method (MSFAN) in multi-source few-shot setting on three standard domain adaptation benchmarks, Office [41], Office-Home [42], and DomainNet [26]. The labeled data in each domain are chosen following [35,33], and each domain is in turn regarded as the target domain, while the others in the same dataset are considered as source domains. Office [41] is a real-world dataset for domain adaptation tasks.…”

Section: Experimental Settingmentioning

confidence: 99%

“…Office-Home [42] is a more difficult dataset than Office, which consists of 4 domains (Art, Clipart, Product, Real) in 65 classes. Following [35,33], we look into the settings with 3% and 6% labeled source images per class, which means each class has 2 to 4 labeled images on average. DomainNet [26] is a large-scale domain adaptation benchmark.…”

Section: Experimental Settingmentioning

confidence: 99%

“…We use ResNet-101 [1] (for DomainNet) and ResNet-50 (for other datasets) pre-trained on ImageNet [43] as backbones for all baselines and MSFAN. To enable a fair comparison with [35] and [33], we replaced the last fully connected layer with a 512-dimension randomly initialized linear layer. We use k-means GPU implementation in faiss [44] for efficient clustering.…”

Section: Implementation Detailsmentioning

confidence: 99%

“…In MFDA, however, with a limited number of labels in each source, it is much harder to learn discriminative features for both source and target. Some recent works [35,33] perform few-shot adaptation with a single source, and in this work, we build upon these contributions and investigate the multiple source scenario.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Multi-source Few-shot Domain Adaptation

Yue,

Zheng,

Reed

et al. 2021

Preprint

View full text Add to dashboard Cite

Multi-source Domain Adaptation (MDA) aims to transfer predictive models from multiple, fully-labeled source domains to an unlabeled target domain. However, in many applications, relevant labeled source datasets may not be available, and collecting source labels can be as expensive as labeling the target data itself. In this paper, we investigate Multi-source Few-shot Domain Adaptation (MFDA): a new domain adaptation scenario with limited multi-source labels and unlabeled target data. As we show, existing methods often fail to learn discriminative features for both source and target domains in the MFDA setting. Therefore, we propose a novel framework, termed Multi-Source Few-shot Adaptation Network (MSFAN), which can be trained end-to-end in a non-adversarial manner. MSFAN operates by first using a type of prototypical, multi-domain, self-supervised learning to learn features that are not only domain-invariant but also class-discriminative. Second, MSFAN uses a small, labeled support set to enforce feature consistency and domain invariance across domains. Finally, prototypes from multiple sources are leveraged to learn better classifiers. Compared with state-of-the-art MDA methods, MSFAN improves the mean classification accuracy over different domain pairs on MFDA by 20.2%, 9.4%, and 16.2% on Office, Office-Home, and DomainNet, respectively. * Equal contribution; work done when Zangwei was in Nanjing University.Preprint. Under review.

show abstract

Section: Multi-domain Prototypical Self-supervised Learningmentioning

confidence: 99%

Section: Experimental Settingmentioning

confidence: 99%

Section: Experimental Settingmentioning

confidence: 99%

Section: Implementation Detailsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Multi-source Few-shot Domain Adaptation

Yue,

Zheng,

Reed

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

Unsupervised domain adaptation of dynamic extension networks based on class decision boundaries

Chen,

Wang,

Zhu

et al. 2024

Multimedia Systems

View full text Add to dashboard Cite

In response to the problems of inaccurate feature alignment, loss of source domain information, imbalanced sample distribution, and biased class decision boundaries in traditional unsupervised domain adaptation methods, this paper proposes a class decision boundary-based dynamic expansion network unsupervised domain adaptation method called CDE-Net. Specifically, our method dynamically expands the autoencoder-based network structure, which can preserve source domain feature information while gradually adapting to the target domain data distribution and learning useful feature information from the target domain. Meanwhile, by minimizing clustering loss and conditional entropy loss, CDE-Net can explore the intrinsic structure of the data and push class decision boundaries away from dense data areas. We experimentally verify our method on three medical image datasets, chest X-rays, intracranial hemorrhage, and mammography, and achieve an average AUC improvement of 25.8% or more compared to non-transfer methods. In addition, we compare our method with previous unsupervised domain adaptation methods, and the experimental results show that our method achieves better classification accuracy and generalization performance.

show abstract

Domain Adaptation: Challenges, Methods, Datasets, and Applications

et al. 2023

View full text Add to dashboard Cite

Deep Neural Networks (DNNs) trained on one dataset (source domain) do not perform well on another set of data (target domain), which is different but has similar properties as the source domain. Domain Adaptation (DA) strives to alleviate this problem and has great potential in its application in practical settings, real-world scenarios, industrial applications and many data domains. Various DA methods aimed at individual data domains have been reported in the last few years; however, there is no comprehensive survey that encompasses all these data domains, focuses on the datasets available, the methods relevant to each domain, and importantly the applications and challenges. To that end, this survey paper discusses how DA can help DNNs work efficiently in these settings by reviewing DA methods and techniques. We have considered five data domains: computer vision, natural language processing, speech, time-series, and multi-modal data. We present a comprehensive taxonomy, including the methods, datasets, challenges, and applications corresponding to each domain. Our goal is to discuss industrial use cases and DA implementation for those. Our final aim is to provide future research directions based on evolving methods and results, the datasets used, and industrial applications.

show abstract

Cross-domain Self-supervised Learning for Domain Adaptation with Few Source Labels

Cited by 17 publications

References 30 publications

Multi-source Few-shot Domain Adaptation

Multi-source Few-shot Domain Adaptation

Unsupervised domain adaptation of dynamic extension networks based on class decision boundaries

Domain Adaptation: Challenges, Methods, Datasets, and Applications

Contact Info

Product

Resources

About