# Unsupervised Robust Domain Adaptation without Source Data

Source: [Unsupervised Robust Domain Adaptation without Source Data](<https://www.sota2.com/research/paper/68fa699e1e209131cea231cc>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T23:04:46.235Z

Authors: Peshal Agarwal, Danda Pani Paudel, Jan-Nico Zaech, Luc Van Gool

Published: 2021-03-26T16:42:28.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2103.14577>)

[PDF](<https://arxiv.org/pdf/2103.14577.pdf>)