Out-of-Distribution Detection

Efficient Unknown Object Detection with Discrepancy Networks for Semantic Segmentation
Detecting unknown objects such as lost cargo is essential for improving the safety of self-driving cars. This is the first work …
Ryo Kamoi, Takumi Iida, Kaname Tomite
PDF Cite
Out-of-Distribution Detection with Likelihoods Assigned by Deep Generative Models Using Multimodal Prior Distributions
Ryo Kamoi, Kei Kobayashi
PDF Cite
Why is the Mahalanobis Distance Effective for Anomaly Detection?
The Mahalanobis distance-based confidence score, a recently proposed anomaly detection method for pre-trained neural classifiers, …
Ryo Kamoi, Kei Kobayashi
PDF Cite
Likelihood Assignment for Out-of-Distribution Inputs in Deep Generative Models is Sensitive to Prior Distribution Choice
Recent work has shown that deep generative models assign higher likelihood to out-of-distribution inputs than to training data. We show …
Ryo Kamoi, Kei Kobayashi
PDF Cite