Out of Distribution (OOD) Detection
214 papers with code • 5 benchmarks • 7 datasets
Out of Distribution (OOD) Detection is the task of detecting instances that do not belong to the distribution the classifier has been trained on. OOD data is often referred to as "unseen" data, as the model has not encountered it during training.
OOD detection is typically performed by training a model to distinguish between in-distribution (ID) data, which the model has seen during training, and OOD data, which it has not seen. This can be done using a variety of techniques, such as training a separate OOD detector, or modifying the model's architecture or loss function to make it more sensitive to OOD data.
Benchmarks
These leaderboards are used to track progress in Out of Distribution (OOD) Detection
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Out of Distribution (OOD) Detection models and implementations
ATIS
SNIPS
ImageNet-O
Persian-ATIS
MUAD
ImageNet-1K vs OpenImage-O
Most implemented papers
Deep Anomaly Detection with Outlier Exposure
hendrycks/outlier-exposure
•
•
ICLR 2019
We also analyze the flexibility and robustness of Outlier Exposure, and identify characteristics of the auxiliary dataset that improve performance.
Likelihood Ratios for Out-of-Distribution Detection
google-research/google-research
•
•
NeurIPS 2019
We propose a likelihood ratio method for deep generative models which effectively corrects for these confounding background statistics.
Detecting Out-of-Distribution Examples with In-distribution Examples and Gram Matrices
VectorInstitute/gram-ood-detection
•
•
We find that characterizing activity patterns by Gram matrices and identifying anomalies in gram matrix values can yield high OOD detection rates.
Energy-based Out-of-distribution Detection
wetliu/energy_ood
•
•
NeurIPS 2020
We propose a unified framework for OOD detection that uses an energy score.
Improved Contrastive Divergence Training of Energy Based Models
yilundu/improved_contrastive_divergence
•
•
Contrastive divergence is a popular method of training energy-based models, but is known to have difficulties with training stability.
Hierarchical VAEs Know What They Don't Know
Deep generative models have been demonstrated as state-of-the-art density estimators.
Likelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encoder
XavierXiao/Likelihood-Regret
•
•
NeurIPS 2020
An important application of generative modeling should be the ability to detect out-of-distribution (OOD) samples by setting a threshold on the likelihood.
SSD: A Unified Framework for Self-Supervised Outlier Detection
inspire-group/SSD
•
•
ICLR 2021
We demonstrate that SSD outperforms most existing detectors based on unlabeled data by a large margin.
A Simple Fix to Mahalanobis Distance for Improving Near-OOD Detection
google/uncertainty-baselines
•
•
Mahalanobis distance (MD) is a simple and popular post-processing method for detecting out-of-distribution (OOD) inputs in neural networks.
Out of Distribution Detection via Neural Network Anchoring
llnl/amp
•
•
Our goal in this paper is to exploit heteroscedastic temperature scaling as a calibration strategy for out of distribution (OOD) detection.
