AI Paper Atlas

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

Source-Free Domain Adaptation with Vision-Language Prior

Song Tang, Yunxiang Bai, Wenxin X. Su, Mao Ye, Jianwei Zhang, Xiatian Zhu

IJCV 2026 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Source-free domain adaptation · 1 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 L_cac when training with L_S-I, L_pc and L_rc (ablation)DIFO++ · Closed-set ablation (avg of three datasets)average accuracy: 80.7 -> 89.3Improved
add L_pc to the other losses (ablation)DIFO++ · Closed-set ablation (avg of three datasets)average accuracy: 81.7 -> 89.3Improved
add L_rc to the other losses (ablation)DIFO++ · Closed-set ablation (avg of three datasets)average accuracy: 88.6 -> 89.3Improved
add L_S-I to the other losses (ablation)DIFO++ · Closed-set ablation (avg of three datasets)average accuracy: 87.7 -> 89.3Improved
optimize mutual information instead of KL divergence (ablation)DIFO++ · Closed-set ablation (avg of three datasets)average accuracy: 82.8 -> 89.3Improved
use referenced-entropy hard data sampling instead of random selection (ablation)DIFO++ · Closed-set ablation (avg of three datasets)average accuracy: 87.8 -> 89.3Improved
use referenced uncertainty instead of conventional entropy (ablation)DIFO++ · Closed-set ablation (avg of three datasets)average accuracy: 87.9 -> 89.3Improved
use prompt learning to customize CLIP instead of fixed template (ablation)DIFO++ · Closed-set ablation (avg of three datasets)average accuracy: 87.7 -> 89.3Improved
use weighted combination of target and ViL predictions vs target prediction only (ablation)DIFO++ · Closed-set ablation (avg of three datasets)average accuracy: 83.3 -> 89.3Improved
use weighted combination vs ViL prediction only (ablation)DIFO++ · Closed-set ablation (avg of three datasets)average accuracy: 87.6 -> 89.3Improved
add gap region-driven transfer on top of DIFODIFO++ · Office-Home closed-setaverage accuracy: 83.1 -> 84.5Improved
add DIFO++ to continual SFDA vs DIFODIFO++ · Office-Home continual SFDAaccuracy: 51 out of 64 casesImproved

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