Research map / Label-efficient and robust learning / Domain adaptation and generalization
Attending to Discriminative Certainty for Domain Adaptation
Vinod Kumar Kurmi, Shanu Kumar, Vinay P. Namboodiri
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 predictive-certainty attention (ablation) | Bayesian domain adaptation with AlexNet · Office-31 | average classification accuracy (%): 78.0 -> 80.4 | Improved |
| Add aleatoric-certainty attention (ablation) | Bayesian domain adaptation with AlexNet · Office-31 | average classification accuracy (%): 78.0 -> 79.3 | Improved |
| Add predictive-certainty attention (ablation) | Bayesian domain adaptation with ResNet-50 · Office-31 | average classification accuracy (%): 87.2 -> 89.5 | Improved |
| Add aleatoric-certainty attention (ablation) | Bayesian domain adaptation with ResNet-50 · Office-31 | average classification accuracy (%): 87.2 -> 88.5 | Improved |
| Use predictive rather than aleatoric certainty for attention (ablation) | CADA with AlexNet · Office-31 | average classification accuracy (%): 79.3 -> 80.4 | Improved |
| Use predictive rather than aleatoric certainty for attention (ablation) | CADA with ResNet-50 · Office-31 | average classification accuracy (%): 88.5 -> 89.5 | Improved |
| Use predictive rather than aleatoric certainty for attention (ablation) | CADA with ResNet-50 · Office-Home | average classification accuracy (%): 70.1 -> 70.2 | No clear effect |
| Use predictive rather than aleatoric certainty for attention (ablation) | CADA with ResNet-50 · ImageCLEF | average classification accuracy (%): 88.2 -> 88.3 | No clear effect |
| Use certainty-based attention to focus classification on discriminator-certain regions | CADA-P with ResNet-50 · Office-Home | average classification accuracy (%): 62.8 -> 70.2 | Improved |
| Use certainty-based attention to focus classification on discriminator-certain regions | CADA-P with ResNet-50 · ImageCLEF | average classification accuracy (%): 87.5 -> 88.3 | Improved |
Closest papers by meaning
- Drop to Adapt: Learning Discriminative Features for Unsupervised Domain Adaptation (ICCV 2019 · similarity 0.90)
- Mind the Discriminability: Asymmetric Adversarial Domain Adaptation (ECCV 2020 · similarity 0.89)
- Maximum Classifier Discrepancy for Unsupervised Domain Adaptation (CVPR 2018 · similarity 0.89)
- Reusing the Task-Specific Classifier as a Discriminator: Discriminator-Free Adversarial Domain Adaptation (CVPR 2022 · similarity 0.89)
- A Balanced and Uncertainty-aware Approach for Partial Domain Adaptation (ECCV 2020 · similarity 0.89)
- Low Category Uncertainty and High Training Potential Instance Learning for Unsupervised Domain Adaptation (AAAI 2024 · 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.
