Research map / Label-efficient and robust learning / Domain adaptation and generalization
DINE: Domain Adaptation From Single and Multiple Black-Box Predictors
Jian Liang, Dapeng Hu, Jiashi Feng, Ran He
Check 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 changed | Where | Measured | Effect |
|---|---|---|---|
| add mutual information regularization during distillation and fine-tuning (ablation) | DINE · Office-Home closed-set UDA, D→A | accuracy: 63.6±3.5 -> 72.2±1.8 | Improved |
| add MixUp interpolation consistency regularization (ablation) | DINE · Office-Home closed-set UDA, D→A | accuracy: 72.0±1.7 -> 72.2±1.8 | Improved |
| add the second fine-tuning stage (ablation) | DINE multi-source · Office multi-source closed-set UDA, ResNet-101 source (Avg.) | accuracy: 92.1 -> 93.4 | Improved |
| use adaptive label smoothing with top-1 confidence rather than hard one-hot labels (ablation) | DINE · Office-Home closed-set UDA, D→A | accuracy: 67.3±1.7 -> 72.2±1.8 | Improved |
| use adaptive label smoothing with top-1 confidence rather than vanilla label smoothing (ablation) | DINE · Office-Home closed-set UDA, D→A | accuracy: 68.4±1.8 -> 72.2±1.8 | Improved |
| retain top 3 classes instead of using top 1 in adaptive label smoothing (ablation) | DINE · Office-Home closed-set UDA, D→A | accuracy: 72.2±1.8 -> 72.9±2.0 | Improved |
| use the full source prediction vector instead of top-1 adaptive smoothing (ablation) | DINE · Office-Home partial-set UDA, ViT source → ResNet-50 target (Avg.) | accuracy: 83.0 -> 82.1 | Hurt |
| use full source prediction vectors instead of top-1 adaptive smoothing (ablation) | DINE · Office-Home closed-set UDA, D→A | accuracy: 72.2±1.8 -> 72.9±2.5 | Mixed |
Later papers that compared with this method
7 later accepted papers report DINE as a baseline in their results tables; 6 of them report a better number on most of the results they share with it.
- Bridge Then Begin Anew: Generating Target-Relevant Intermediate Model for Source-Free Visual Emotion Adaptation (AAAI 2025 · better on 3 of 3 shared results)
- A Bayesian Approach to OOD Robustness in Image Classification (CVPR 2024 · better on 2 of 2 shared results)
- A Separation and Alignment Framework for Black-Box Domain Adaptation (AAAI 2024 · better on 1 of 1 shared result)
- A Curriculum-Style Self-Training Approach for Source-Free Semantic Segmentation (TPAMI 2024 · better on 0 of 1 shared result)
- Black-Box Unsupervised Domain Adaptation with Bi-Directional Atkinson-Shiffrin Memory (ICCV 2023 · better on 7 of 7 shared results)
- Divide to Adapt: Mitigating Confirmation Bias for Domain Adaptation of Black-Box Predictors (ICLR 2023 · better on 1 of 1 shared result)
- Prior Knowledge Guided Unsupervised Domain Adaptation (ECCV 2022 · better on 3 of 3 shared results)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Unsupervised Multi-Source Domain Adaptation Without Access to Source Data (CVPR 2021 · similarity 0.91)
- Can We Evaluate Domain Adaptation Models Without Target-Domain Labels? (ICLR 2024 · similarity 0.90)
- Prior Knowledge Guided Unsupervised Domain Adaptation (ECCV 2022 · similarity 0.90)
- UDA-Bench: Revisiting Common Assumptions in Unsupervised Domain Adaptation Using a Standardized Framework (ECCV 2024 · similarity 0.90)
- CASUAL: Conditional Support Alignment for Domain Adaptation with Label Shift (AAAI 2025 · similarity 0.88)
- Revisiting Source-Free Domain Adaptation: Insights into Representativeness, Generalization, and Variety (CVPR 2025 · similarity 0.88)
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.
