Search Results for author:
Found 2 papers, 0 papers with code
Identification of Systematic Errors of Image Classifiers on Rare Subgroups
Despite excellent average-case performance of many image classifiers, their performance can substantially deteriorate on semantically coherent subgroups of the data that were under-represented in the training data.
Certified Defences Against Adversarial Patch Attacks on Semantic Segmentation
Adversarial patch attacks are an emerging security threat for real world deep learning applications.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
