Gradient-Regularized Out-of-Distribution Detection

arXiv:2404.12368v1 Announce Type: cross
Abstract: One of the challenges for neural networks in real-life applications is the overconfident errors these models make when the data is not from the original training distribution.
Addressing this issue is known as Out-of-Distribution (OOD) detection.
Many state-of-the-art OOD methods employ an auxiliary dataset as a surrogate for OOD data during training to achieve improved performance.
However, these methods fail to fully exploit the local information embedded in the auxiliary dataset.
In this work, we …

abstract applications art arxiv challenges cs.cv cs.lg data dataset detection distribution errors gradient issue life networks neural networks state training type