Unsupervised Domain Adaptation in the Absence of Source Data

Sahoo, R.; Shanmugam, Divya; Guttag, John V.

doi:10.48550/arxiv.2007.10233

Cited by 3 publications

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most of the source-free UDA methods require image/feature generation [22,19,17] which are difficult to scale while ensuring robustness on large datasets like VisDA-C [36]. Other recently introduced approaches [38,45,51] that are designed for pixel level corruptions [12] do not extend well to more complex domain adaptation tasks we present in this paper.…”

Section: Baselinesmentioning

confidence: 96%

“…UDA without Source Data. The UDA without source data can be broadly divided into three categories: (i) generative approach [22,19,17]; (ii) pseudo-label approach [15,23]; and (iii) others [38,53]. The generative approach is often difficult to scale up, as learning to generate the images/features is known to be difficult.…”

Section: Related Workmentioning

confidence: 99%

“…The problem of unsupervised domain adaptation with-arXiv:2103.14577v1 [cs.CV] 26 Mar 2021 out source data has recently been studied in [23,15,38,22,19,17,53]. However, the existing work does not take robustness into consideration.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Unsupervised Robust Domain Adaptation without Source Data

Agarwal

Paudel

Zaech

et al. 2022

2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

View full text Add to dashboard Cite

We study the problem of robust domain adaptation in the context of unavailable target labels and source data. The considered robustness is against adversarial perturbations. This paper aims at answering the question of finding the right strategy to make the target model robust and accurate in the setting of unsupervised domain adaptation without source data. The major findings of this paper are: (i) robust source models can be transferred robustly to the target; (ii) robust domain adaptation can greatly benefit from nonrobust pseudo-labels and the pair-wise contrastive loss. The proposed method of using non-robust pseudo-labels performs surprisingly well on both clean and adversarial samples, for the task of image classification. We show a consistent performance improvement of over 10% in accuracy against the tested baselines on four benchmark datasets. Our source code will be made publicly available.

show abstract

Section: Baselinesmentioning

confidence: 96%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Unsupervised Robust Domain Adaptation without Source Data

Agarwal

Paudel

Zaech

et al. 2022

2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

View full text Add to dashboard Cite

show abstract

“…The application of source-free domain adaption in natural language processing (NLP) is still relatively limited. Related settings and studies in NLP include continuous learning [151], [152] and generalization capabilities of pre-trained models [153]. Laparra et al designed the SemEval 2021 Task 10 dataset [154] on two tasks, i.e., negation detection and time expression recognition.…”

Section: Natural Language Processingmentioning

confidence: 99%

Source-Free Domain Adaptation for Real-World Image Dehazing

Huang

Liu

et al. 2022

Proceedings of the 30th ACM International Conference on Multimedia

View full text Add to dashboard Cite

Over the past decade, domain adaptation has become a widely studied branch of transfer learning that aims to improve performance on target domains by leveraging knowledge from the source domain. Conventional domain adaptation methods often assume access to both source and target domain data simultaneously, which may not be feasible in real-world scenarios due to privacy and confidentiality concerns. As a result, the research of Source-Free Domain Adaptation (SFDA) has drawn growing attention in recent years, which only utilizes the source-trained model and unlabeled target data to adapt to the target domain. Despite the rapid explosion of SFDA work, yet there has no timely and comprehensive survey in the field. To fill this gap, we provide a comprehensive survey of recent advances in SFDA and organize them into a unified categorization scheme based on the framework of transfer learning. Instead of presenting each approach independently, we modularize several components of each method to more clearly illustrate their relationships and mechanics in light of the composite properties of each method. Furthermore, we compare the results of more than 30 representative SFDA methods on three popular classification benchmarks, namely Office-31, Office-home, and VisDA, to explore the effectiveness of various technical routes and the combination effects among them. Additionally, we briefly introduce the applications of SFDA and related fields. Drawing from our analysis of the challenges facing SFDA, we offer some insights into future research directions and potential settings.

show abstract

“…With these insights, we formulate a new but important problem -source-free domain adaptation for semantic segmentation, in which only a well-trained source model and an unlabeled target domain dataset are available for adaptation. Recently, a tiny number of source-free UDA methods [25,24,27,38,22,26] have been developed to tackle a similar issue on image classification. However, the imagelevel computer vision task just associates the label with a whole image, which is fundamentally different from image segmentation that belongs to a pixel-level task with each pixel associated with a semantic label.…”

Section: Introductionmentioning

confidence: 99%

Source-Free Domain Adaptation for Semantic Segmentation

Liu¹,

Zhang²,

Wang³

2021

Preprint

View full text Add to dashboard Cite

Unsupervised Domain Adaptation (UDA) can tackle the challenge that convolutional neural network (CNN)-based approaches for semantic segmentation heavily rely on the pixel-level annotated data, which is labor-intensive. However, existing UDA approaches in this regard inevitably require the full access to source datasets to reduce the gap between the source and target domains during model adaptation, which are impractical in the real scenarios where the source datasets are private, and thus cannot be released along with the well-trained source models. To cope with this issue, we propose a source-free domain adaptation framework for semantic segmentation, namely SFDA, in which only a well-trained source model and an unlabeled target domain dataset are available for adaptation. SFDA not only enables to recover and preserve the source domain knowledge from the source model via knowledge transfer during model adaptation, but also distills valuable information from the target domain for self-supervised learning. The pixeland patch-level optimization objectives tailored for semantic segmentation are seamlessly integrated in the framework. The extensive experimental results on numerous benchmark datasets highlight the effectiveness of our framework against the existing UDA approaches relying on source data.

show abstract

Unsupervised Domain Adaptation in the Absence of Source Data

Cited by 3 publications

References 0 publications

Unsupervised Robust Domain Adaptation without Source Data

Unsupervised Robust Domain Adaptation without Source Data

Source-Free Domain Adaptation for Real-World Image Dehazing

Source-Free Domain Adaptation for Semantic Segmentation

Contact Info

Product

Resources

About