arXiv:2002.05380
CEB Improves Model Robustness
원문 초록
We demonstrate that the Conditional Entropy Bottleneck (CEB) can improve model robustness. CEB is an easy strategy to implement and works in tandem with data augmentation procedures. We report results of a large scale adversarial robustness study on CIFAR-10, as well as the ImageNet-C Common Corruptions Benchmark, ImageNet-A, and PGD attacks.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
MOBODY: Model Based Off-Dynamics Offline Reinforcement Learning
A Flat Minima Perspective on Understanding Augmentations and Model Robustness
SenseShift6D: Multimodal RGB-D Benchmarking for Robust 6D Pose Estimation across Environment and Sensor Variations
RAID: A Dataset for Testing the Adversarial Robustness of AI-Generated Image Detectors
Making Language Model a Hierarchical Classifier and Generator
Implementing Adaptations for Vision AutoRegressive Model
토론
이 논문과 연결된 포럼 글이 아직 없습니다.