About
Detect out-of-distribution or anomalous examples.
Benchmarks
| TREND | DATASET | BEST METHOD | PAPER TITLE | PAPER | CODE | COMPARE |
|---|---|---|---|---|---|---|
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
Datasets
Greatest papers with code
Likelihood Ratios for Out-of-Distribution Detection
NeurIPS 2019
• google-research/google-research
• 
We propose a likelihood ratio method for deep generative models which effectively corrects for these confounding background statistics.
CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features
ICCV 2019
• rwightman/pytorch-image-models
• 
Regional dropout strategies have been proposed to enhance the performance of convolutional neural network classifiers.
Ranked #2 on
Domain Generalization
on ImageNet-A
DOMAIN GENERALIZATION IMAGE CAPTIONING IMAGE CLASSIFICATION OBJECT LOCALIZATION OUT-OF-DISTRIBUTION DETECTION
A Systematic Comparison of Bayesian Deep Learning Robustness in Diabetic Retinopathy Tasks
From our comparison we conclude that some current techniques which solve benchmarks such as UCI `overfit' their uncertainty to the dataset---when evaluated on our benchmark these underperform in comparison to simpler baselines.
Deep Anomaly Detection with Outlier Exposure
ICLR 2019
• hendrycks/outlier-exposure
•
We also analyze the flexibility and robustness of Outlier Exposure, and identify characteristics of the auxiliary dataset that improve performance.
Ranked #2 on
Out-of-Distribution Detection
on CIFAR-100
(using extra training data)
Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks
ICLR 2018
• facebookresearch/odin
•
We show in a series of experiments that ODIN is compatible with diverse network architectures and datasets.
Natural Adversarial Examples
• hendrycks/natural-adv-examples
•
We also curate an adversarial out-of-distribution detection dataset called ImageNet-O, which is the first out-of-distribution detection dataset created for ImageNet models.
Ranked #7 on
Domain Generalization
on ImageNet-A
ADVERSARIAL ATTACK DATA AUGMENTATION DOMAIN GENERALIZATION OUT-OF-DISTRIBUTION DETECTION
Training Normalizing Flows with the Information Bottleneck for Competitive Generative Classification
In this work, firstly, we develop the theory and methodology of IB-INNs, a class of conditional normalizing flows where INNs are trained using the IB objective: Introducing a small amount of {\em controlled} information loss allows for an asymptotically exact formulation of the IB, while keeping the INN's generative capabilities intact.
A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks
NeurIPS 2018
• pokaxpoka/deep_Mahalanobis_detector
•
Detecting test samples drawn sufficiently far away from the training distribution statistically or adversarially is a fundamental requirement for deploying a good classifier in many real-world machine learning applications.
Ranked #2 on
Out-of-Distribution Detection
on MS-1M vs. IJB-C
CLASS-INCREMENTAL LEARNING INCREMENTAL LEARNING OUT-OF-DISTRIBUTION DETECTION
Learning Confidence for Out-of-Distribution Detection in Neural Networks
• uoguelph-mlrg/confidence_estimation
•
Modern neural networks are very powerful predictive models, but they are often incapable of recognizing when their predictions may be wrong.
Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty
NeurIPS 2019
• hendrycks/ss-ood
•
Self-supervision provides effective representations for downstream tasks without requiring labels.
Ranked #2 on
Anomaly Detection
on One-class ImageNet-30
OUTLIER DETECTION OUT-OF-DISTRIBUTION DETECTION SELF-SUPERVISED LEARNING UNSUPERVISED ANOMALY DETECTION