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 1–25 of 629 papers

TitleStatusHype
Rethinking Test-time Likelihood: The Likelihood Path Principle and Its Application to OOD DetectionCode2
Learning Transferable Negative Prompts for Out-of-Distribution DetectionCode2
Recent Advances in OOD Detection: Problems and ApproachesCode2
Training a Helpful and Harmless Assistant with Reinforcement Learning from Human FeedbackCode2
Extremely Simple Multimodal Outlier Synthesis for Out-of-Distribution Detection and SegmentationCode2
DPU: Dynamic Prototype Updating for Multimodal Out-of-Distribution DetectionCode2
GalLoP: Learning Global and Local Prompts for Vision-Language ModelsCode2
MOODv2: Masked Image Modeling for Out-of-Distribution DetectionCode2
Unifying Unsupervised Graph-Level Anomaly Detection and Out-of-Distribution Detection: A BenchmarkCode2
VOS: Learning What You Don't Know by Virtual Outlier SynthesisCode2
Logits-Based FinetuningCode2
A Rate-Distortion View of Uncertainty QuantificationCode1
Can multi-label classification networks know what they don’t know?Code1
Can multi-label classification networks know what they don't know?Code1
Can Autonomous Vehicles Identify, Recover From, and Adapt to Distribution Shifts?Code1
Calibrated Language Model Fine-Tuning for In- and Out-of-Distribution DataCode1
CAN bus intrusion detection based on auxiliary classifier GAN and out-of-distribution detectionCode1
Can We Detect Failures Without Failure Data? Uncertainty-Aware Runtime Failure Detection for Imitation Learning PoliciesCode1
A Hybrid Architecture for Out of Domain Intent Detection and Intent DiscoveryCode1
Beyond AUROC & co. for evaluating out-of-distribution detection performanceCode1
Agree to Disagree: Diversity through Disagreement for Better TransferabilityCode1
Balanced Energy Regularization Loss for Out-of-distribution DetectionCode1
A Multi-Head Model for Continual Learning via Out-of-Distribution ReplayCode1
Accuracy on In-Domain Samples Matters When Building Out-of-Domain detectors: A Reply to Marek et al. (2021)Code1
AdaptiveMix: Improving GAN Training via Feature Space ShrinkageCode1
Show:102550
← PrevPage 1 of 26Next →

No leaderboard results yet.