AI Paper Atlas

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

Activate and Reject: Towards Safe Domain Generalization under Category Shift

Chaoqi Chen, Luyao Tang, Leitian Tao, Hong-Yu Zhou, Yue Huang, Xiaoguang Han, Yizhou Yu

ICCV 2023 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Augmentation and mixture-of-experts generalization · 11 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 unknown activation loss L_UA (ablation)ART · Four classification benchmarks (average)H-score (%): 47.9 -> 60.1Improved
add smoothed cross-entropy L_SCE (ablation)ART · Four classification benchmarks (average)H-score (%): 54.1 -> 60.1Improved
add Test-time Unknown Rejection on top of UGD (ablation)ART · Four classification benchmarks (average)H-score (%): 55.2 -> 60.1Improved
replace TUR with Tent for test-time adaptation (ablation)UGD · Four classification benchmarks (average)H-score (%): 55.2 -> 45.3Hurt
replace TUR with MEMO or TTT (ablation)UGD · Four classification benchmarks (average)H-score (%): 55.2 -> 56.9 (MEMO), 55.9 (TTT)No clear effect
add UGD on segmentation (ablation)ART · GTA5 to CityscapesH-score: 50.2 -> 63.1Improved
add TUR on segmentation (ablation)ART · GTA5 to CityscapesH-score: 62.6 -> 63.1Improved
add TUR on Pascal VOC to Clipart (ablation)ART · Pascal VOC to Clipart detectionH-score: 8.6 -> 15.9Improved
add L_SCE on Pascal VOC to Watercolor (ablation)ART · Pascal VOC to Watercolor detectionH-score: 20.2 -> 17.6Hurt
vary order of test data (ablation)TUR · Four classification benchmarks (average)H-score (%): 60.0 to 60.3 across ordersNo clear effect
apply ART instead of previous best OSDG baselineDGCS classification · PACSH-score (%): 43.0 -> 52.3Improved

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