out-of-distribution detection
This refers to the method of determining when data points fall outside the distribution on which a model was trained. It is essential for maintaining model reliability, as it helps identify cases for which the model was not designed or is likely to fail.
- An Information-theoretical Framework for Understanding Out-of-distribution Detection with Pretrained Vision-Language Models
- Double Descent Meets Out-of-Distribution Detection: Theoretical Insights and Empirical Analysis on the Role of Model Complexity
- DualCnst: Enhancing Zero-Shot Out-of-Distribution Detection via Text-Image Consistency in Vision-Language Models
- Extremely Simple Multimodal Outlier Synthesis for Out-of-Distribution Detection and Segmentation
- Harnessing Feature Resonance under Arbitrary Target Alignment for Out-of-Distribution Node Detection
- Human Texts Are Outliers: Detecting LLM-generated Texts via Out-of-distribution Detection
- Mysteries of the Deep: Role of Intermediate Representations in Out of Distribution Detection
- Redundancy-Aware Test-Time Graph Out-of-Distribution Detection
- Refining Norms: A Post-hoc Framework for OOD Detection in Graph Neural Networks
- Revisiting Logit Distributions for Reliable Out-of-Distribution Detection
- Spurious-Aware Prototype Refinement for Reliable Out-of-Distribution Detection
- The Illusion of Progress? A Critical Look at Test-Time Adaptation for Vision-Language Models
- Tight Asymptotics of Extreme Order Statistics
- Towards Generalizable Detector for Generated Image
- Uncertainty Estimation on Graphs with Structure Informed Stochastic Partial Differential Equations
- X-Mahalanobis: Transformer Feature Mixing for Reliable OOD Detection