Michael A. Alcorn

Strike (With) a Pose: Neural Networks Are Easily Fooled by Strange Poses of Familiar Objects

Despite excellent performance on stationary test sets, deep neural networks (DNNs) can fail to generalize to out-of-distribution (OoD) inputs, including natural, non-adversarial ones, which are common in real-world settings. In this paper, we present a framework for discovering DNN failures that har…