Fig. 5: Perturbation scores detect out-of-distribution (OOD) image data.
From: Assessing and improving reliability of neighbor embedding methods: a map-continuity perspective
a We use a pretrained ResNet-18 model to extract features of CIFAR-10 images and, as out-of-distribution data, of DTD texture images. Then we visualize the features using t-SNE with perplexity 100. A fraction of OOD embedding points are absorbed into clusters that represent CIFAR-10 image categories such as deer, truck, and automobile. b–d Perturbation scores can effectively identify misplaced out-of-distribution data points. The ROC curves show the proportion of OOD points correctly identified by the perturbation scores. Source data are provided as a Source Data file.
