AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Understanding the Limits of Unsupervised Domain Adaptation via Data Poisoning

Akshay Mehra, Bhavya Kailkhura, Pin-Yu Chen, Jihun Hamm

NeurIPS 2021 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Feature alignment for unsupervised adaptation · 5 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Add mislabeled target-domain data to the source training dataDANN · SVHN → MNISTtarget domain accuracy: 78.05$\pm$1.15 -> {\bf 1.46$\pm$1.12}Hurt
Add mislabeled target-domain data to the source training dataCDAN · MNIST → MNIST_Mtarget domain accuracy: 73.88$\pm$1.10 -> {\bf0.59$\pm$0.12}Hurt
Add mislabeled target-domain data to the source training dataMCD · MNIST → USPStarget domain accuracy: 89.96$\pm$2.04 -> {\bf0.66$\pm$0.16}Hurt
Add mislabeled target-domain data to the source training dataSSL · USPS → MNISTtarget domain accuracy: 82.23$\pm$1.59 -> {\bf9.88$\pm$1.07}Hurt
Add mislabeled target-domain data to the source training dataDANN · A → Dtarget domain accuracy: 84.06 -> {\bf59.83$\pm$0.20}Hurt
Add mislabeled target-domain data to the source training dataCDAN · D → Atarget domain accuracy: 71.25 -> {\bf11.19$\pm$1.47}Hurt
Use mislabeled source-domain data rather than target-domain data as poisons (ablation)DANN · SVHN → MNISTtarget domain accuracy: 78.05$\pm$1.15 -> 70.26$\pm$2.84Hurt
Use source-looking watermarked poison data and increase the watermarking percentage (ablation)DANN · MNIST → USPStarget domain accuracy: 92.17$\pm$0.73 -> 39.29$\pm$1.34$_{0.30}$Hurt
Use source-domain rather than target-domain base data to initialize clean-label poisons (ablation)UDA methods · MNIST → MNIST_M, two-class (3 vs 8)attack success rateHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy