10 datasets found

The dataset used in the paper for semi-supervised intent classification

The dataset used for out-of-distribution detection through soft clustering with non-negative kernel regression.

The dataset used in the paper to evaluate the proposed two-stage approximately orthogonal training framework (TAOTF) for Deep Neural Networks (DNNs).

The eICU and MIMIC-IV datasets are used for out-of-distribution detection in medical tabular data.

The dataset used in the paper is Fashion-MNIST, MNIST, SVHN, dSprites, and CIFAR-10.

The datasets used for OOD detection.

Out-of-distribution (OOD) detection aims to detect “unknown” data whose labels have not been seen during the in-distribution (ID) training process.

OpenOOD is a benchmarking dataset for generalized out-of-distribution detection.

Out-of-distribution (OOD) detection is a crucial task for ensuring the reliability and safety of deep learning. The dataset used in this paper is CIFAR10, CIFAR100, and ImageNet.

Gaussian Noise, Uniform Noise, Tin (C), Tin (R)