AI Paper Atlas

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

Improving Unsupervised Domain Adaptation: A Pseudo-Candidate Set Approach

Aveen Dayal, Rishabh Lalla, Linga Reddy Cenkeramaddi, C. Krishna Mohan, Abhinav Kumar, Vineeth N Balasubramanian

ECCV 2024 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Feature alignment for unsupervised adaptation · 2 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
apply UDPCS refinement to existing UDA methods on VisDAMCC, NWD, MDD, LeCo, SDAT · VisDAmean accuracy: 83.8 -> 86.2 (MCC)Improved
apply UDPCS refinement on DomainNetCDAN, MDD, MCC, SDAT · DomainNetaverage accuracy: 52.2 -> 55.7 (MDD)Improved
apply UDPCS refinement to SDAT on DomainNetSDAT · DomainNetaverage accuracy: 51.3 -> 51.4No clear effect
apply UDPCS refinement on OfficeHomeMDD, MCC, LeCo, SDAT, NWD · OfficeHomeaverage accuracy: 69.5 -> 71.3 (MDD)Improved
add candidate loss (ablation)MDD+Ours · OfficeHomeaverage accuracy: 69.5 -> 70.7Improved
add non-candidate loss (ablation)MDD+Ours · OfficeHomeaverage accuracy: 69.5 -> 70.6Improved
add confidence threshold gamma to both losses (ablation)MDD+Ours · OfficeHomeaverage accuracy: 70.9 -> 71.3Improved
use strong augmentation instead of weak augmentation in candidate loss (ablation)MDD+Ours · OfficeHomeaverage accuracy: 69.6 -> 71.3Improved
use strong augmentation instead of weak augmentation in candidate loss (ablation)MCC+Ours · OfficeHomeaverage accuracy: 72.8 -> 73.6Improved
vary lambda between 0.5, 1 and 2 (ablation)MDD+Ours · OfficeHomeaverage accuracy: 71.1 -> 71.2No clear effect
vary threshold gamma between 0.8, 0.85 and 0.9 (ablation)MDD+Ours · OfficeHomeaverage accuracy: 71.1 / 71.3 / 71.1No clear effect
replace KL divergence with cross entropy in candidate loss (ablation)MDD+Ours · OfficeHomeaverage accuracy: 71.3 -> 71.3No 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