Research map / Label-efficient and robust learning / Domain adaptation and generalization
Slimmable Domain Adaptation
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use SlimDA rather than SymNets | ImageCLEF-DA · ImageCLEF-DA | accuracy (Avg.): 89.9 -> 88.9 | Hurt |
| Use SlimDA rather than SymNets | Office-31 · Office-31 | accuracy (Avg.): 88.4 -> 87.6 | Hurt |
| Use SlimDA rather than BNM | Office-Home · Office-Home | accuracy (Avg.): 67.9 -> 68.4 | Helped |
| Use SlimDA rather than SHOT++ | VisDA · VisDA | mean accuracy: 77.2 -> 78.5 | Helped |
| Reduce SlimDA FLOPs from 1× to 1/64× | ImageCLEF-DA · ImageCLEF-DA | accuracy (Avg.): 88.9 -> 86.6 | Hurt |
| Reduce SlimDA FLOPs from 1× to 1/64× | Office-31 · Office-31 | accuracy (Avg.): 87.6 -> 86.8 | Hurt |
| Reduce SlimDA FLOPs from 1× to 1/64× | Office-Home · Office-Home | accuracy (Avg.): 68.4 -> 64.0 | Hurt |
| Reduce SlimDA FLOPs from 1× to 1/64× | VisDA · VisDA | mean accuracy: 78.5 -> 77.7 | Hurt |
| Add SEED to the slimmable baseline without OSTC (ablation) | ImageCLEF-DA · ImageCLEF-DA, 1/64× FLOPs | accuracy: 81.7 -> 85.9 | Helped |
| Add SEED to the slimmable baseline without OSTC (ablation) | ImageCLEF-DA · ImageCLEF-DA, 1× FLOPs | accuracy: 88.6 -> 87.9 | Hurt |
| Add OSTC to SEED (ablation) | ImageCLEF-DA · ImageCLEF-DA, 1/64× FLOPs | accuracy: 85.9 -> 86.6 | Helped |
| Increase model batch size from 2 to 10 (ablation) | SlimDA · ImageCLEF-DA, I→P, 1/64× FLOPs | accuracy: 73.5 -> 78.3 | Helped |
Closest papers by meaning
- Distribution-Informed Neural Networks for Domain Adaptation Regression (NeurIPS 2022 · similarity 0.88)
- Agile Multi-Source-Free Domain Adaptation (AAAI 2024 · similarity 0.88)
- Divide to Adapt: Mitigating Confirmation Bias for Domain Adaptation of Black-Box Predictors (ICLR 2023 · similarity 0.88)
- On Balancing Bias and Variance in Unsupervised Multi-Source-Free Domain Adaptation (ICML 2023 · similarity 0.87)
- Self-Training with Dynamic Weighting for Robust Gradual Domain Adaptation (NeurIPS 2025 · similarity 0.87)
- Weight Diffusion for Future: Learn to Generalize in Non-Stationary Environments (NeurIPS 2024 · similarity 0.87)
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.