Understanding Intrinsic Robustness Using Label Uncertainty
A fundamental question in adversarial machine learning is whether a robust classifier exists for a given task. A line of research has made some progress towards this goal by studying the concentration of measure, but we argue standard concentration fails to fully characterize the intrinsic robustness of a classification problem since it ignores data labels which are essential to any classification task. Building on a novel definition of label uncertainty, we empirically demonstrate that error regions induced by state-of-the-art models tend to have much higher label uncertainty than randomly-selected subsets. This observation motivates us to adapt a concentration estimation algorithm to account for label uncertainty, resulting in more accurate intrinsic robustness measures for benchmark image classification problems.
Code (1)
Tasks
Adversarial RobustnessClassificationimage-classificationImage ClassificationSimilar Papers 제목 키워드 기반
Correlated Uncertainty for Learning Dense Correspondences from Noisy Labels
Many machine learning methods depend on human supervision to achieve optimal performance. However, in tasks such as DensePose, where the goal is to establish dense visual correspondences between images, the quality of ma…
Visual Analysis of Prediction Uncertainty in Neural Networks for Deep Image Synthesis
Ubiquitous applications of Deep neural networks (DNNs) in different artificial intelligence systems have led to their adoption in solving challenging visualization problems in recent years. While sophisticated DNNs offer…
DiversityImage GenerationPredictionLearn to Estimate Labels Uncertainty for Quality Assurance
Deep Learning sets the state-of-the-art in many challenging tasks showing outstanding performance in a broad range of applications. Despite its success, it still lacks robustness hindering its adoption in medical applica…
Bayesian InferenceDeep LearningDelving Aleatoric Uncertainty in Medical Image Segmentation via Vision Foundation Models
Medical image segmentation supports clinical workflows by precisely delineating anatomical structures and lesions. However, medical image datasets medical image datasets suffer from acquisition noise and annotation ambig…
Medical Image SegmentationTumor SegmentationOn the Robustness of Monte Carlo Dropout Trained with Noisy Labels
The memorization effect of deep learning hinders its performance to effectively generalize on test set when learning with noisy labels. Prior study has discovered that epistemic uncertainty techniques are robust when tra…
Learning with noisy labelsMemorization