AI Paper Atlas

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

Balanced Open Set Domain Adaptation via Centroid Alignment

Mengmeng Jing, Jingjing Li, Lei Zhu, Zhengming Ding, Ke Lu, Yang Yang

AAAI 2021 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Source-free domain adaptation · 35 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 centroid alignment (ablation)Balanced OSDA · Office-31 A→WOS∗acc: 90.8 -> 88.8Hurt
Add centroid alignment (ablation)Balanced OSDA · Office-31 A→WUnkacc: 67.7 -> 92.6Improved
Add unknown recognition (ablation)Balanced OSDA with centroid alignment · Office-31 A→WUnkacc: 84.8 -> 92.6Improved
Add distance rectification to Weibull recognition (ablation)Balanced OSDA · Office-31 A→WOS∗acc: 82.2 -> 88.8Improved
Add distance rectification to Weibull recognition (ablation)Balanced OSDA · Office-31 A→WUnkacc: 98.9 -> 92.6Hurt
Use centroid alignment and unknown recognition together (ablation)Balanced OSDA · Office-31 A→WHacc: 64.9 -> 90.7Improved

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