AI Paper Atlas

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

Prototypical Cross-Domain Self-Supervised Learning for Few-Shot Unsupervised Domain Adaptation

Xiangyu Yue, Zangwei Zheng, Shanghang Zhang, Yang Gao, Trevor Darrell, Kurt Keutzer, Alberto Sangiovanni Vincentelli

CVPR 2021 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Feature alignment for unsupervised adaptation · 157 citations (OpenAlex)

Check 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
Use PCS instead of the strongest reported baselineFew-shot domain adaptation · Office, 1-shot, Avgtarget accuracy (%): 66.1 -> 76.6Improved
Use PCS instead of the strongest reported baselineFew-shot domain adaptation · Office, 3-shots, Avgtarget accuracy (%): 80.6 -> 84.0Improved
Use PCS instead of the strongest reported baselineFew-shot domain adaptation · Office-Home, 3% labeled source, Avgtarget accuracy (%): 56.2 -> 59.7Improved
Use PCS instead of the strongest reported baselineFew-shot domain adaptation · Office-Home, 6% labeled source, Avgtarget accuracy (%): 60.1 -> 62.6Improved
Use PCS instead of the strongest reported baselineFew-shot domain adaptation · VisDA-2017, 0.1% labeled sourcetarget accuracy (%): 69.0 -> 78.0Improved
Use PCS instead of the strongest reported baselineFew-shot domain adaptation · VisDA-2017, 1% labeled sourcetarget accuracy (%): 78.3 -> 79.0Improved
Use PCS instead of the strongest reported baselineFew-shot domain adaptation · DomainNet, 1-shot, Avgtarget accuracy (%): 21.5 -> 34.7Improved
Use PCS instead of the strongest reported baselineFew-shot domain adaptation · DomainNet, 3-shots, Avgtarget accuracy (%): 42.5 -> 46.1Improved
Add in-domain prototypical self-supervision (ablation)Classification-loss-only model · Office, 1-shot, Avgtarget accuracy (%): 44.2 -> 52.1Improved
Add cross-domain instance-prototype self-supervision (ablation)Model with classification loss and in-domain self-supervision · Office, 1-shot, Avgtarget accuracy (%): 52.1 -> 60.1Improved
Add mutual information maximization (ablation)Model with in-domain and cross-domain self-supervision · Office, 1-shot, Avgtarget accuracy (%): 60.1 -> 64.9Improved
Add adaptive prototype-classifier update (ablation)Model with classification, both self-supervision losses, and MIM · Office, 1-shot, Avgtarget accuracy (%): 64.9 -> 76.6Improved

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