A noisy elephant in the room: Is your out-of-distribution detector robust to label noise?

arXiv:2404.01775v1 Announce Type: cross
Abstract: The ability to detect unfamiliar or unexpected images is essential for safe deployment of computer vision systems. In the context of classification, the task of detecting images outside of a model's training domain is known as out-of-distribution (OOD) detection. While there has been a growing research interest in developing post-hoc OOD detection methods, there has been comparably little discussion around how these methods perform when the underlying classifier is not trained on a clean, carefully …

arxiv cs.ai cs.cv cs.lg distribution noise robust room type