AI Paper Atlas

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

Interpretable Open-Set Domain Adaptation via Angular Margin Separation

Xinhao Li, Jingjing Li, Zhekai Du, Lei Zhu, Wen Li

ECCV 2022 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Source-free domain adaptation · 9 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 additive angular margin loss in fine-tuning (ablation)SR-OSDA base · P->R semantic recoveryU (unseen class recovery): 45.6 -> 50.9Improved
add additive angular margin loss in fine-tuning (ablation)SR-OSDA base · P->R open-set recognitionOS-unknown (open-set unseen accuracy): 88.1 -> 90.3Improved
add angular regularization in fine-tuning (ablation)AMS fine-tuning margin · P->R semantic recoveryS (seen class recovery): 77.2 -> 77.6Improved
add angular margin in training phase (ablation)AMS with fine-tuning · P->R semantic recoveryU (unseen class recovery): 50.7 -> 47.3Hurt
add angular margin in training phase (ablation)AMS with fine-tuning · P->R open-set recognitionOS* (seen accuracy): 78.3 -> 82.6Improved
add angular regularization in training with a single unseen class (ablation)AMS with training margin · P->R semantic recoveryU (unseen class recovery): 47.3 -> 41.6Hurt
switch classifier to |Cs+K|-way multiple unseen classes without MRC (ablation)AMS with training margin · P->R semantic recoveryU (unseen class recovery)No clear effect
add maximum-response correspondence (MRC) with multiple unseen clusters (ablation)AMS with multi-unseen classifier · P->R semantic recoveryU (unseen class recovery): 12.5%Improved
add post-training attribute re-projection (ablation)AMS · P->R semantic recoveryS (seen class recovery): 81.7 -> 82.8Improved
add post-training attribute re-projection (ablation)AMS · P->R semantic recoveryU (unseen class recovery): 58.1 -> 58.1No clear effect
increase number of unseen clusters K from 1 toward the ground truth (ablation)AMS · P->R open-set recognitionOS-unknown and UImproved
increase K beyond ground truth (more than three times) (ablation)AMS · P->R open-set recognitionall metricsNo clear effect

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