Controlling Over-generalization and its Effect on Adversarial Examples Generation and Detection

Convolutional Neural Networks (CNNs) significantly improve the state-of-the-art for many applications, especially in computer vision. However, CNNs still suffer from a tendency to confidently classify out-distribution samples from unknown classes into pre-defined known classes... (read more)

Results in Papers With Code
(↓ scroll down to see all results)