AI Paper Atlas

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

Source-Free Domain Adaptation Guided by Vision and Vision-Language Pre-training

Wenyu Zhang, Li Shen, Chuan-Sheng Foo

IJCV 2024 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Conditional distribution alignment · 28 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
co-learn with ImageNet Swin-B instead of the same ResNet-50Co-learn · Office-Homeaccuracy: 70.0 -> 83.5Improved
add Co-learn pseudolabels (Swin-B) to existing SFDA methodsSHOT, SHOT++, NRC, AaD · Office-Homeaccuracy: 3.6-9.4%Improved
add CLIP zero-shot text classifier guidance (Co-learn++) over Co-learnCo-learn (CLIP) · DomainNetaccuracy: 80.3 -> 90.5Improved
co-learn with the same ImageNet network used to initialize the source modelSHOT, SHOT++ · Office-31accuracy: 88.7 -> 88.8No clear effect
co-learn with ResNet-50 on NRC and AaD (Office-31)NRC, AaD · Office-31accuracy: 0.8% and 0.6%Improved
MatchOrConf pseudolabeling rather than SelfConf (ablation)Co-learn · Office-Home (A->C,A->P,A->R)accuracy: 67.0 -> 77.7Improved
MatchOrConf instead of MatchAndConf (ablation)Co-learn · Office-Home (A->C,A->P,A->R)accuracy: 75.4 -> 77.7Improved
fine-tune the feature extractor of the pre-trained branch (ablation)Co-learn · Office-Home (A->C,A->P,A->R)accuracy: 76.6 -> 76.2Hurt
fine-tune only the weighted NCC classifier in the pre-trained branch (ablation)Co-learn · Office-Home (A->C,A->P,A->R)accuracy: 76.6 -> 77.7Improved
lower confidence threshold gamma from 0.5 to 0.1 (ablation)Co-learn · VisDA-Caccuracy: 86.4 -> 87.1Improved
lower confidence threshold gamma from 0.5 to 0.1 (ablation)Co-learn · Office-Homeaccuracy: 77.4 -> 76.1Hurt
strong instead of weak CLIP zero-shot guidance (ablation)Co-learn++ · Office-Homeaccuracy: 87.1 -> 83.7Hurt

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