AI Paper Atlas

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

CVPR 2019 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adversarial domain adaptation · 114 citations (OpenAlex)

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 changedWhereMeasuredEffect
Add predictive-certainty attention (ablation)Bayesian domain adaptation with AlexNet · Office-31average classification accuracy (%): 78.0 -> 80.4Improved
Add aleatoric-certainty attention (ablation)Bayesian domain adaptation with AlexNet · Office-31average classification accuracy (%): 78.0 -> 79.3Improved
Add predictive-certainty attention (ablation)Bayesian domain adaptation with ResNet-50 · Office-31average classification accuracy (%): 87.2 -> 89.5Improved
Add aleatoric-certainty attention (ablation)Bayesian domain adaptation with ResNet-50 · Office-31average classification accuracy (%): 87.2 -> 88.5Improved
Use predictive rather than aleatoric certainty for attention (ablation)CADA with AlexNet · Office-31average classification accuracy (%): 79.3 -> 80.4Improved
Use predictive rather than aleatoric certainty for attention (ablation)CADA with ResNet-50 · Office-31average classification accuracy (%): 88.5 -> 89.5Improved
Use predictive rather than aleatoric certainty for attention (ablation)CADA with ResNet-50 · Office-Homeaverage classification accuracy (%): 70.1 -> 70.2No clear effect
Use predictive rather than aleatoric certainty for attention (ablation)CADA with ResNet-50 · ImageCLEFaverage classification accuracy (%): 88.2 -> 88.3No clear effect
Use certainty-based attention to focus classification on discriminator-certain regionsCADA-P with ResNet-50 · Office-Homeaverage classification accuracy (%): 62.8 -> 70.2Improved
Use certainty-based attention to focus classification on discriminator-certain regionsCADA-P with ResNet-50 · ImageCLEFaverage classification accuracy (%): 87.5 -> 88.3Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy