Search Results for author:
Found 3 papers, 1 papers with code
Target Domain Data induces Negative Transfer in Mixed Domain Training with Disjoint Classes
In practical scenarios, it is often the case that the available training data within the target domain only exist for a limited number of classes, with the remaining classes only available within surrogate domains.
Shape-Biased Domain Generalization via Shock Graph Embeddings
There is an emerging sense that the vulnerability of Image Convolutional Neural Networks (CNN), i. e., sensitivity to image corruptions, perturbations, and adversarial attacks, is connected with Texture Bias.
Ranked #122 on
Domain Generalization
on PACS
Accurate Layerwise Interpretable Competence Estimation
Estimating machine learning performance 'in the wild' is both an important and unsolved problem.
