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 51–75 of 629 papers

TitleStatusHype
Demo Abstract: Real-Time Out-of-Distribution Detection on a Mobile RobotCode1
Heatmap-based Out-of-Distribution DetectionCode1
Density-based Feasibility Learning with Normalizing Flows for Introspective Robotic AssemblyCode1
How Good Are LLMs at Out-of-Distribution Detection?Code1
Diffusion for Out-of-Distribution Detection on Road Scenes and BeyondCode1
Beyond AUROC & co. for evaluating out-of-distribution detection performanceCode1
InFlow: Robust outlier detection utilizing Normalizing FlowsCode1
Block Selection Method for Using Feature Norm in Out-of-distribution DetectionCode1
Detection of out-of-distribution samples using binary neuron activation patternsCode1
LAPT: Label-driven Automated Prompt Tuning for OOD Detection with Vision-Language ModelsCode1
CLIPN for Zero-Shot OOD Detection: Teaching CLIP to Say NoCode1
Breaking Down Out-of-Distribution Detection: Many Methods Based on OOD Training Data Estimate a Combination of the Same Core QuantitiesCode1
Can Autonomous Vehicles Identify, Recover From, and Adapt to Distribution Shifts?Code1
A Rate-Distortion View of Uncertainty QuantificationCode1
Isotropy Maximization Loss and Entropic Score: Accurate, Fast, Efficient, Scalable, and Turnkey Neural Networks Out-of-Distribution Detection Based on The Principle of Maximum EntropyCode1
Calibrated Language Model Fine-Tuning for In- and Out-of-Distribution DataCode1
Conjugated Semantic Pool Improves OOD Detection with Pre-trained Vision-Language ModelsCode1
CAN bus intrusion detection based on auxiliary classifier GAN and out-of-distribution detectionCode1
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
Contrastive Out-of-Distribution Detection for Pretrained TransformersCode1
Adversarial vulnerability of powerful near out-of-distribution detectionCode1
Can We Detect Failures Without Failure Data? Uncertainty-Aware Runtime Failure Detection for Imitation Learning PoliciesCode1
Combine and Conquer: A Meta-Analysis on Data Shift and Out-of-Distribution DetectionCode1
How to Exploit Hyperspherical Embeddings for Out-of-Distribution Detection?Code1
Show:102550
← PrevPage 3 of 26Next →

No leaderboard results yet.