Skip to content

This is the project on OOD Detection done as part of the CSC 591 course at NC State University.

Notifications You must be signed in to change notification settings

rishi2019194/Deep_Learning_Project

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Deep_Learning_Project

This is the project on OOD Detection done as part of the CSC 591 course at NC State University.

Abstract

OOD detection has become more pertinent with advances in network design and increased task complexity. Identifying which parts of the data a given network is misclassifying has become as valuable as the network’s overall performance. We can compress the model with quantization, but it suffers minor performance loss. The loss of performance further necessitates the need to derive the confidence estimate of the network’s predictions. In line with this thinking, we introduce an Uncertainty Quantification(UQ) technique to quantify the uncertainty in the predictions from a pre-trained vision model. We subsequently leverage this information to extract valuable predictions while ignoring the non-confident predictions. We observe that our technique saves up to 80% of ignored samples from being misclassified.

Doubts and Collaboration

For any queries/doubt or if you want to do some further collaboration, feel free to mail me at rsingha4@ncsu.edu

About

This is the project on OOD Detection done as part of the CSC 591 course at NC State University.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published