Out-of-Distribution Detection
329 papers with code • 50 benchmarks • 22 datasets
Detect out-of-distribution or anomalous examples.
Benchmarks
These leaderboards are used to track progress in Out-of-Distribution Detection
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Out-of-Distribution Detection models and implementationsDatasets
CIFAR-10
CIFAR-100
Fashion-MNIST
SST
STL-10
iSUN
Places365
20 Newsgroups
ImageNet-1k vs Textures
ImageNet-1k vs iNaturalist
Latest papers with no code
Enhancing Out-of-Distribution Detection with Multitesting-based Layer-wise Feature Fusion
When trained using KNN on CIFAR10, MLOD-Fisher significantly lowers the false positive rate (FPR) from 24. 09% to 7. 47% on average compared to merely utilizing the features of the last layer.
Energy Correction Model in the Feature Space for Out-of-Distribution Detection
In this work, we study the out-of-distribution (OOD) detection problem through the use of the feature space of a pre-trained deep classifier.
Extracting Explanations, Justification, and Uncertainty from Black-Box Deep Neural Networks
Deep Neural Networks (DNNs) do not inherently compute or exhibit empirically-justified task confidence.
Towards a Framework for Deep Learning Certification in Safety-Critical Applications Using Inherently Safe Design and Run-Time Error Detection
Although an ever-growing number of applications employ deep learning based systems for prediction, decision-making, or state estimation, almost no certification processes have been established that would allow such systems to be deployed in safety-critical applications.
COOD: Combined out-of-distribution detection using multiple measures for anomaly & novel class detection in large-scale hierarchical classification
The individual measures are several existing state-of-the-art measures and several novel OOD measures developed with novel class detection and hierarchical class structure in mind.
Trustworthy Partial Label Learning with Out-of-distribution Detection
PLL-OOD significantly enhances model adaptability and accuracy by merging self-supervised learning with partial label loss and pioneering the Partial-Energy (PE) score for OOD detection.
Advancing Out-of-Distribution Detection through Data Purification and Dynamic Activation Function Design
Our work addresses this challenge by enhancing the detection and management of OOD samples in neural networks.
Approximations to the Fisher Information Metric of Deep Generative Models for Out-Of-Distribution Detection
In this work, we analyse using the gradient of a data point with respect to the parameters of the deep generative model for OOD detection, based on the simple intuition that OOD data should have larger gradient norms than training data.
Towards Out-of-Distribution Detection for breast cancer classification in Point-of-Care Ultrasound Imaging
All methods are tested on three different OOD data sets.
Out-of-Distribution Detection using Neural Activation Prior
Our neural activation prior is based on a key observation that, for a channel before the global pooling layer of a fully trained neural network, the probability of a few neurons being activated with a large response by an in-distribution (ID) sample is significantly higher than that by an OOD sample.
