Can Biases in ImageNet Models Explain Generalization?

arXiv:2404.01509v1 Announce Type: cross
Abstract: The robust generalization of models to rare, in-distribution (ID) samples drawn from the long tail of the training distribution and to out-of-training-distribution (OOD) samples is one of the major challenges of current deep learning methods. For image classification, this manifests in the existence of adversarial attacks, the performance drops on distorted images, and a lack of generalization to concepts such as sketches. The current understanding of generalization in neural networks is very limited, but some …

arxiv biases cs.ai cs.cv cs.lg imagenet stat.ml type