Lost in Translation: Modern Neural Networks Still Struggle With Small Realistic Image Transformations

arXiv:2404.07153v1 Announce Type: new
Abstract: Deep neural networks that achieve remarkable performance in image classification have previously been shown to be easily fooled by tiny transformations such as a one pixel translation of the input image. In order to address this problem, two approaches have been proposed in recent years. The first approach suggests using huge datasets together with data augmentation in the hope that a highly varied training set will teach the network to learn to be invariant. The …

abstract arxiv classification cs.cv image lost lost in translation modern networks neural networks performance pixel small struggle translation type