Research map / Label-efficient and robust learning / Domain adaptation and generalization
Maximum Density Divergence for Domain Adaptation
Jingjing Li, Erpeng Chen, Zhengming Ding, Lei Zhu, Ke Lü, Heng Tao Shen
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add MDD loss to adversarial network (ablation) | CDAN · SVHN->MNIST | accuracy: 89.2 -> 96.1 | Improved |
| add MDD loss (ablation) | CDAN · MNIST->SVHN | accuracy: 71.3 -> 76.6 | Improved |
| add MDD loss (ablation) | CDAN · MNIST->USPS | accuracy: 95.6 -> 96.1 | Improved |
| add MDD loss (ablation) | CDAN · Office-31 (ResNet-50) average 2 | accuracy: 81.8 -> 84.9 | Improved |
| add MDD loss (ablation) | CDAN · Office-31 (AlexNet) average 1 | accuracy: 77.7 -> 79.6 | Improved |
| add MDD loss (ablation) | CDAN · ImageCLEF-DA | accuracy: 87.7 -> 90.0 | Improved |
| add MDD loss (ablation) | CDAN · Office-Home | accuracy: 65.8 -> 67.9 | Improved |
| add MDD loss (ablation) | CDAN · Office-31 W->D | accuracy: 100 -> 100 | No clear effect |
| add all three intra-MDD terms instead of none (ablation) | ATM · SVHN->MNIST | accuracy: 89.2 -> 96.1 | Improved |
| add term 3 to terms 1 and 2 (ablation) | ATM · SVHN->MNIST | accuracy: 95.3 -> 96.1 | Improved |
| add term 2 to terms 1 and 3 (ablation) | ATM · SVHN->MNIST | accuracy: 95.0 -> 96.1 | Improved |
| add term 1 to terms 2 and 3 (ablation) | ATM · SVHN->MNIST | accuracy: 93.8 -> 96.1 | Improved |
Closest papers by meaning
- Bridging Theory and Algorithm for Domain Adaptation (ICML 2019 · similarity 0.90)
- f-Domain Adversarial Learning: Theory and Algorithms (ICML 2021 · similarity 0.90)
- A DIRT-T Approach to Unsupervised Domain Adaptation (ICLR 2018 · similarity 0.90)
- Margin-aware Adversarial Domain Adaptation with Optimal Transport (ICML 2020 · similarity 0.90)
- Divergence-Agnostic Unsupervised Domain Adaptation by Adversarial Attacks (TPAMI 2021 · similarity 0.89)
- Adversarial Discriminative Domain Adaptation (CVPR 2017 · 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.
