DeepAI AI Chat
Log In Sign Up

Are all outliers alike? On Understanding the Diversity of Outliers for Detecting OODs

by   Ramneet Kaur, et al.

Deep neural networks (DNNs) are known to produce incorrect predictions with very high confidence on out-of-distribution (OOD) inputs. This limitation is one of the key challenges in the adoption of deep learning models in high-assurance systems such as autonomous driving, air traffic management, and medical diagnosis. This challenge has received significant attention recently, and several techniques have been developed to detect inputs where the model's prediction cannot be trusted. These techniques use different statistical, geometric, or topological signatures. This paper presents a taxonomy of OOD outlier inputs based on their source and nature of uncertainty. We demonstrate how different existing detection approaches fail to detect certain types of outliers. We utilize these insights to develop a novel integrated detection approach that uses multiple attributes corresponding to different types of outliers. Our results include experiments on CIFAR10, SVHN and MNIST as in-distribution data and Imagenet, LSUN, SVHN (for CIFAR10), CIFAR10 (for SVHN), KMNIST, and F-MNIST as OOD data across different DNN architectures such as ResNet34, WideResNet, DenseNet, and LeNet5.


Detecting OODs as datapoints with High Uncertainty

Deep neural networks (DNNs) are known to produce incorrect predictions w...

A Survey on Uncertainty Quantification Methods for Deep Neural Networks: An Uncertainty Source Perspective

Deep neural networks (DNNs) have achieved tremendous success in making a...

Dense open-set recognition with synthetic outliers generated by Real NVP

Today's deep models are often unable to detect inputs which do not belon...

A Forgotten Danger in DNN Supervision Testing: Generating and Detecting True Ambiguity

Deep Neural Networks (DNNs) are becoming a crucial component of modern s...

Confidence Aware Neural Networks for Skin Cancer Detection

Deep learning (DL) models have received particular attention in medical ...

Technical outlier detection via convolutional variational autoencoder for the ADMANI breast mammogram dataset

The ADMANI datasets (annotated digital mammograms and associated non-ima...

Detecting Trojaned DNNs Using Counterfactual Attributions

We target the problem of detecting Trojans or backdoors in DNNs. Such mo...