Setup We additionally evaluate GradNorm on a common benchmark with CIFAR-10 and CIFAR100 [22] as ID datasets, which is routinely used in literature [13, 27, 14, 29, 26]. We use the standard split with 50,000 training images and 10,000 test images. The learning rate is initially 0.1, and decays by a factor of 10 at epochs 50, 75 and 90 respectively. Results We summarize the results in Table 6, where GradNormremains competitive. In particular, GradNorm reduces the average FPR95 by 8.77% on CIFAR-10 compared to the best baseline.

Out-of-distribution (OOD) detection is essential for model trustworthiness which aims to sensitively identity semantic OOD samples and robustly generalize for covariate-shifted OOD samples. However, we discover that the superior OOD detection performance of state-of-the-art methods is achieved by secretly sacrificing the OOD generalization ability. The classification accuracy frequently collapses catastrophically when even slight noise is encountered. Such a phenomenon violates the motivation of trustworthiness and significantly limits the model's deployment in the real world. What is the hidden reason behind such a limitation?

Hopfield Boosting, a boosting approach, which leverages modern Hopfield energy to sharpen the decision boundary between the in-distribution and OOD data.

This paper presents an innovative approach to classification tasks called Credal Deep Ensembles (CreDEs), ensembles of novel Credal-Set Neural Networks (CreNets), aiming to improve EU quantification in the framework of credal inference.