Unsupervised Robust Domain Adaptation without Source Data

2021-03-26 · Peshal Agarwal, Danda Pani Paudel, Jan-Nico Zaech, Luc van Gool

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 non-robust 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.

📄 PDF Abstract BibTeX arXiv:2103.14577

Code (0)

등록된 구현이 없습니다.

Tasks

Domain Adaptation image-classification Image Classification Unsupervised Domain Adaptation

Uncertainty-Guided Mixup for Semi-Supervised Domain Adaptation without Source Data

2021-07-14 · Ning Ma, Jiajun Bu, Zhen Zhang, Sheng Zhou

Present domain adaptation methods usually perform explicit representation alignment by simultaneously accessing the source data and target data. However, the source data are not always available due to the privacy preser…

Domain Adaptation Privacy Preserving Semi-supervised Domain Adaptation Source-Free Domain Adaptation

Unsupervised BatchNorm Adaptation (UBNA): A Domain Adaptation Method for Semantic Segmentation Without Using Source Domain Representations

2020-11-17 · Marvin Klingner, Jan-Aike Termöhlen, Jacob Ritterbach, Tim Fingscheidt

In this paper we present a solution to the task of "unsupervised domain adaptation (UDA) of a given pre-trained semantic segmentation model without relying on any source domain representations". Previous UDA approaches f…

Domain Adaptation Segmentation Semantic Segmentation Unsupervised Domain Adaptation

Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source Data

2021-10-07 · NeurIPS 2021 12 · Jiaxing Huang, Dayan Guan, Aoran Xiao, Shijian Lu

Unsupervised domain adaptation aims to align a labeled source domain and an unlabeled target domain, but it requires to access the source data which often raises concerns in data privacy, data portability and data transm…

Contrastive Learning Domain Adaptation Source Free Object Detection Unsupervised Domain Adaptation

Model Adaptation: Unsupervised Domain Adaptation without Source Data

2025-02-26 · CVPR 2020 6 · Rui Li, Qianfen Jiao, Wenming Cao, Hau-San Wong 외

In this paper, we investigate a challenging unsupervised domain adaptation setting -- unsupervised model adaptation. We aim to explore how to rely only on unlabeled target data to improve performance of an existing sourc…

Domain Adaptation Prediction Unsupervised Domain Adaptation

Multi-Source Domain Adaptation with Collaborative Learning for Semantic Segmentation

2021-03-08 · CVPR 2021 1 · Jianzhong He, Xu Jia, Shuaijun Chen, Jianzhuang Liu

Multi-source unsupervised domain adaptation~(MSDA) aims at adapting models trained on multiple labeled source domains to an unlabeled target domain. In this paper, we propose a novel multi-source domain adaptation framew…

Domain Adaptation Multi-Source Unsupervised Domain Adaptation Semantic Segmentation Unsupervised Domain Adaptation