Research map / Label-efficient and robust learning / Domain adaptation and generalization
Few-Shot Adversarial Domain Adaptation
Read the paperCheck 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 FADA instead of the source-only base model | FADA · MNIST → USPS | accuracy: 65.4 -> 89.1 | Helped |
| Use FADA instead of fine-tuning | FADA · USPS → SVHN | accuracy: 25.6 -> 27.5 | Helped |
| Use FADA instead of the strongest supervised baseline | FADA · Office average | accuracy: 85.8 -> 84.9 | Hurt |
| Use FADA instead of the strongest supervised baseline | FADA · Office D → A | accuracy: 71.8 ± 0.5 -> 68.1 ± 06 | Hurt |
| Remove weight-sharing between source and target inference functions (ablation) | FADA · USPS → MNIST, n=5 | accuracy | Hurt |
| Increase the number of labeled target samples per category (ablation) | FADA · MNIST-USPS-SVHN transfer tasks | accuracy: FADA accuracy increases across the reported 1–7 settings | Helped |
Closest papers by meaning
- Adversarial Discriminative Domain Adaptation (CVPR 2017 · similarity 0.90)
- A DIRT-T Approach to Unsupervised Domain Adaptation (ICLR 2018 · similarity 0.90)
- f-Domain Adversarial Learning: Theory and Algorithms (ICML 2021 · similarity 0.90)
- Consensus Adversarial Domain Adaptation (AAAI 2019 · similarity 0.90)
- Generate to Adapt: Aligning Domains Using Generative Adversarial Networks (CVPR 2018 · similarity 0.90)
- Few-Shot Adversarial Prompt Learning on Vision-Language Models (NeurIPS 2024 · similarity 0.89)
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.