SOTAVerified

Out of Distribution (OOD) Detection

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.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 101–150 of 629 papers

TitleStatusHype
Provable Guarantees for Understanding Out-of-distribution DetectionCode1
Certifiably Adversarially Robust Detection of Out-of-Distribution DataCode1
Dream the Impossible: Outlier Imagination with Diffusion ModelsCode1
Residual Pattern Learning for Pixel-wise Out-of-Distribution Detection in Semantic SegmentationCode1
Robust Out-of-distribution Detection for Neural NetworksCode1
Improving GAN Training via Feature Space ShrinkageCode1
Deep Anomaly Detection with Outlier ExposureCode1
InFlow: Robust outlier detection utilizing Normalizing FlowsCode1
Secure On-Device Video OOD Detection Without BackpropagationCode1
In or Out? Fixing ImageNet Out-of-Distribution Detection EvaluationCode1
Demo Abstract: Real-Time Out-of-Distribution Detection on a Mobile RobotCode1
Density-based Feasibility Learning with Normalizing Flows for Introspective Robotic AssemblyCode1
Beyond AUROC & co. for evaluating out-of-distribution detection performanceCode1
SSD: A Unified Framework for Self-Supervised Outlier DetectionCode1
LAPT: Label-driven Automated Prompt Tuning for OOD Detection with Vision-Language ModelsCode1
Know Your Limits: Uncertainty Estimation with ReLU Classifiers Fails at Reliable OOD DetectionCode1
LLC: Accurate, Multi-purpose Learnt Low-dimensional Binary CodesCode1
Towards Optimal Feature-Shaping Methods for Out-of-Distribution DetectionCode1
Diffusion for Out-of-Distribution Detection on Road Scenes and BeyondCode1
Learning Structured Representations with Hyperbolic EmbeddingsCode1
Trust Issues: Uncertainty Estimation Does Not Enable Reliable OOD Detection On Medical Tabular DataCode1
Trustworthy Long-Tailed ClassificationCode1
Entropy Maximization and Meta Classification for Out-Of-Distribution Detection in Semantic SegmentationCode1
Uncertainty Aware Semi-Supervised Learning on Graph DataCode1
Detection of out-of-distribution samples using binary neuron activation patternsCode1
Breaking Down Out-of-Distribution Detection: Many Methods Based on OOD Training Data Estimate a Combination of the Same Core QuantitiesCode1
Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution DataCode1
Adversarially Robust Out-of-Distribution Detection Using Lyapunov-Stabilized EmbeddingsCode1
Energy-based Hopfield Boosting for Out-of-Distribution DetectionCode1
Likelihood Ratios for Out-of-Distribution DetectionCode1
MASKER: Masked Keyword Regularization for Reliable Text ClassificationCode1
Likelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encoderCode1
Calibrated Language Model Fine-Tuning for In- and Out-of-Distribution DataCode1
EAT: Towards Long-Tailed Out-of-Distribution DetectionCode1
Can Autonomous Vehicles Identify, Recover From, and Adapt to Distribution Shifts?Code1
A Rate-Distortion View of Uncertainty QuantificationCode1
Dissecting Out-of-Distribution Detection and Open-Set Recognition: A Critical Analysis of Methods and BenchmarksCode1
CAN bus intrusion detection based on auxiliary classifier GAN and out-of-distribution detectionCode1
MUAD: Multiple Uncertainties for Autonomous Driving, a benchmark for multiple uncertainty types and tasksCode1
A Benchmark and Evaluation for Real-World Out-of-Distribution Detection Using Vision-Language ModelsCode1
Can multi-label classification networks know what they don't know?Code1
Distribution Shifts at Scale: Out-of-distribution Detection in Earth ObservationCode1
Can multi-label classification networks know what they don’t know?Code1
Exploring the Limits of Out-of-Distribution DetectionCode1
Adversarial vulnerability of powerful near out-of-distribution detectionCode1
Multidimensional Uncertainty-Aware Evidential Neural NetworksCode1
Can We Detect Failures Without Failure Data? Uncertainty-Aware Runtime Failure Detection for Imitation Learning PoliciesCode1
DICE: Leveraging Sparsification for Out-of-Distribution DetectionCode1
Negative Label Guided OOD Detection with Pretrained Vision-Language ModelsCode1
Out-of-domain Detection for Natural Language Understanding in Dialog SystemsCode1
Show:102550
← PrevPage 3 of 13Next →

No leaderboard results yet.