paper-with-me

홈 › Papers

Robustified Domain Adaptation

2020-11-18 · Jiajin Zhang, Hanqing Chao, Pingkun Yan

Unsupervised domain adaptation (UDA) is widely used to transfer knowledge from a labeled source domain to an unlabeled target domain with different data distribution. While extensive studies attested that deep learning models are vulnerable to adversarial attacks, the adversarial robustness of models in domain adaptation application has largely been overlooked. This paper points out that the inevitable domain distribution deviation in UDA is a critical barrier to model robustness on the target domain. To address the problem, we propose a novel Class-consistent Unsupervised Robust Domain Adaptation (CURDA) framework for training robust UDA models. With the introduced contrastive robust training and source anchored adversarial contrastive losses, our proposed CURDA framework can effectively robustify UDA models by simultaneously minimizing the data distribution deviation and the distance between target domain clean-adversarial pairs without creating classification confusion. Experiments on several public benchmarks show that CURDA can significantly improve model robustness in the target domain with only minor cost of accuracy on the clean samples.

📄 PDF Abstract BibTeX arXiv:2011.09563

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial RobustnessDomain AdaptationUnsupervised Domain Adaptation

Similar Papers 제목 키워드 기반

Lifelong Change Detection: Continuous Domain Adaptation for Small Object Change Detection in Every Robot Navigation

2023-06-28 · Koji Takeda, Kanji Tanaka, Yoshimasa Nakamura

The recently emerging research area in robotics, ground view change detection, suffers from its ill-posed-ness because of visual uncertainty combined with complex nonlinear perspective projection. To regularize the ill-p…

Change DetectionDomain AdaptationObjectRobot Navigation

Robustness, Privacy, and Generalization of Adversarial Training

2020-12-25 · Fengxiang He, Shaopeng Fu, Bohan Wang, DaCheng Tao

Adversarial training can considerably robustify deep neural networks to resist adversarial attacks. However, some works suggested that adversarial training might comprise the privacy-preserving and generalization abiliti…

Generalization BoundsPrivacy Preserving

Sim-to-Real Transfer Learning using Robustified Controllers in Robotic Tasks involving Complex Dynamics

2018-09-13 · Jeroen van Baar, Alan Sullivan, Radu Cordorel, Devesh Jha 외

Learning robot tasks or controllers using deep reinforcement learning has been proven effective in simulations. Learning in simulation has several advantages. For example, one can fully control the simulated environment,…

Deep Reinforcement LearningFrictionReinforcement LearningTransfer Learning

Strong and Precise Modulation of Human Percepts via Robustified ANNs

2023-09-21 · NeurIPS 2023 11

The visual object category reports of artificial neural networks (ANNs) are notoriously sensitive to tiny, adversarial image perturbations. Because human category reports (aka human percepts) are thought to be insensitiv…

Robustified ANNs Reveal Wormholes Between Human Category Percepts

2023-08-14 · Guy Gaziv, Michael J. Lee, James J. DiCarlo

The visual object category reports of artificial neural networks (ANNs) are notoriously sensitive to tiny, adversarial image perturbations. Because human category reports (aka human percepts) are thought to be insensitiv…