Research map / Label-efficient and robust learning / Domain adaptation and generalization
Consensus 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 |
|---|---|---|---|
| let source encoder be fine-tuned jointly instead of fixing it (CADA vs ADDA) | adversarial domain adaptation · SVHN to MNIST | accuracy (%): 76.0 ± 1.8 -> 90.9 ± 0.2 | Helped |
| let source encoder be fine-tuned jointly (CADA vs ADDA) | adversarial domain adaptation · MNIST to USPS | accuracy (%): 89.4 ± 0.2 -> 96.4 ± 0.1 | Helped |
| let source encoder be fine-tuned jointly (CADA vs ADDA) | adversarial domain adaptation · USPS to MNIST | accuracy (%): 90.1 ± 0.8 -> 97.0 ± 0.1 | Helped |
| let source encoder be fine-tuned jointly (CADA vs ADDA) | adversarial domain adaptation · WiFi gesture Large to Small | accuracy (%): 71.5 ± 0.3 -> 88.8 ± 0.1 | Helped |
| add CADA adaptation to source-only classifier | source classifier · SVHN to MNIST | accuracy (%): 60.1 ± 1.1 -> 90.9 ± 0.2 | Helped |
| add label propagation with 1 labeled target sample per class (F-CADA over CADA) | CADA · SVHN to MNIST | accuracy (%): 90.9 ± 0.2 -> 94.8 | Helped |
| increase labeled target samples per class from 1 to 7 | F-CADA · SVHN to MNIST | accuracy (%): 94.8 -> 96.1 | Helped |
| F-CADA label learning vs FADA at 1 label per class | few-shot adaptation · SVHN to MNIST | accuracy (%): 72.8 -> 94.8 | Helped |
| increase labeled target gestures from 1 to 5 | F-CADA · WiFi gesture Large to Small | accuracy (%): 92.3 -> 98.7 | Helped |
Closest papers by meaning
- Few-Shot Adversarial Domain Adaptation (NeurIPS 2017 · similarity 0.90)
- A DIRT-T Approach to Unsupervised Domain Adaptation (ICLR 2018 · similarity 0.88)
- Multi-Adversarial Domain Adaptation (AAAI 2018 · similarity 0.88)
- Adversarial Discriminative Domain Adaptation (CVPR 2017 · similarity 0.87)
- Cooperative and Adversarial Learning: Co-enhancing Discriminability and Transferability in Domain Adaptation (AAAI 2023 · similarity 0.87)
- CASUAL: Conditional Support Alignment for Domain Adaptation with Label Shift (AAAI 2025 · similarity 0.86)
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.