Saved in:
Bibliographic Details
Main Authors: Singhal, Rishi, Srinivasan, Srinath
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2403.01076
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911787844108288
author Singhal, Rishi
Srinivasan, Srinath
author_facet Singhal, Rishi
Srinivasan, Srinath
contents 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. The code for the same is available here.
format Preprint
id arxiv_https___arxiv_org_abs_2403_01076
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Extracting Usable Predictions from Quantized Networks through Uncertainty Quantification for OOD Detection
Singhal, Rishi
Srinivasan, Srinath
Computer Vision and Pattern Recognition
Machine Learning
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. The code for the same is available here.
title Extracting Usable Predictions from Quantized Networks through Uncertainty Quantification for OOD Detection
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2403.01076