VISAT: Benchmarking Adversarial and Distribution Shift Robustness in Traffic Sign Recognition with Visual Attributes
Anzeige
Ähnliche Artikel
arXiv – cs.LG
•
CFL: On the Use of Characteristic Function Loss for Domain Alignment in Machine Learning
arXiv – cs.LG
•
Online Time Series Forecasting with Theoretical Guarantees
arXiv – cs.LG
•
DRO-InstructZero: Distributionally Robust Prompt Optimization for Large Language Models
arXiv – cs.LG
•
Mitigating Spurious Correlation via Distributionally Robust Learning with Hierarchical Ambiguity Sets
arXiv – cs.LG
•
Adapt in the Wild: Test-Time Entropy Minimization with Sharpness and Feature Regularization
arXiv – cs.LG
•
Neue Methode nutzt Aktivationsunterräume zur Erkennung von Out-of-Distribution-Daten