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 76–100 of 629 papers

TitleStatusHype
A Simple Fix to Mahalanobis Distance for Improving Near-OOD DetectionCode1
A framework for benchmarking class-out-of-distribution detection and its application to ImageNetCode1
CLIPN for Zero-Shot OOD Detection: Teaching CLIP to Say NoCode1
AdaptiveMix: Improving GAN Training via Feature Space ShrinkageCode1
Diffusion for Out-of-Distribution Detection on Road Scenes and BeyondCode1
Dream the Impossible: Outlier Imagination with Diffusion ModelsCode1
Combine and Conquer: A Meta-Analysis on Data Shift and Out-of-Distribution DetectionCode1
A Theoretical Study on Solving Continual LearningCode1
Agree to Disagree: Diversity through Disagreement for Better TransferabilityCode1
Augmenting Softmax Information for Selective Classification with Out-of-Distribution DataCode1
Improving GAN Training via Feature Space ShrinkageCode1
Demo Abstract: Real-Time Out-of-Distribution Detection on a Mobile RobotCode1
LAPT: Label-driven Automated Prompt Tuning for OOD Detection with Vision-Language ModelsCode1
Adversarially Robust Out-of-Distribution Detection Using Lyapunov-Stabilized EmbeddingsCode1
Learning Structured Representations with Hyperbolic EmbeddingsCode1
Distribution Shifts at Scale: Out-of-distribution Detection in Earth ObservationCode1
Likelihood Ratios for Out-of-Distribution DetectionCode1
Continual Learning Based on OOD Detection and Task MaskingCode1
Background Data Resampling for Outlier-Aware ClassificationCode1
A Multi-Head Model for Continual Learning via Out-of-Distribution ReplayCode1
Contrastive Out-of-Distribution Detection for Pretrained TransformersCode1
Balanced Energy Regularization Loss for Out-of-distribution DetectionCode1
EAT: Towards Long-Tailed Out-of-Distribution DetectionCode1
Accuracy on In-Domain Samples Matters When Building Out-of-Domain detectors: A Reply to Marek et al. (2021)Code1
Detection of out-of-distribution samples using binary neuron activation patternsCode1
Show:102550
← PrevPage 4 of 26Next →

No leaderboard results yet.