AI Paper Atlas

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

Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptation

Shiqi Yang, Yaxing Wang, Joost van de weijer, Luis Herranz, SHANGLING JUI

NeurIPS 2021 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Source-free domain adaptation · 103 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
Use NRC instead of SHOTsource-free domain adaptation · Office-Home Avgaccuracy (%): 71.8 -> 72.2Improved
Use NRC instead of SHOTsource-free domain adaptation · VisDA-C Synthesis→Real Per-classaccuracy (%): 82.9 -> 85.9Improved
Use NRC instead of PointDANPointDA-10 · PointDA-10 Avgaccuracy (%): 48.7 -> 52.6Improved
Add nearest-neighbor consistency to diversity loss (ablation)NRC · Office-Home Avgaccuracy: 62.1 -> 69.1Improved
Add reciprocal-neighbor affinity weighting (ablation)NRC with nearest-neighbor consistency · Office-Home Avgaccuracy: 69.1 -> 71.1Improved
Add expanded neighbors with affinity weighting (ablation)NRC with nearest-neighbor affinity · Office-Home Avgaccuracy: 71.1 -> 72.2Improved
Add expanded neighbors without affinity weighting (ablation)NRC · Office-Home Avgaccuracy: 71.1 -> 65.2Hurt
Retain duplicate expanded neighbors (ablation)NRC · Office-Home Avgaccuracy: 69.1 -> 72.2Improved
Replace expanded neighbors with a larger nearest-neighbor set (ablation)NRC · VisDA-C Synthesis→Realaccuracy: 85.9 -> 84.0Hurt
Replace expanded neighbors with a larger nearest-neighbor set (ablation)NRC · Office-Home Avgaccuracy: 72.2 -> 69.5Hurt
Use a smaller memory bank (ablation)NRC · VisDA-C Synthesis→Realper-class accuracy (%): 85.9 -> 85.3Hurt

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