English

Extracting Usable Predictions from Quantized Networks through Uncertainty Quantification for OOD Detection

Computer Vision and Pattern Recognition 2024-03-05 v1 Machine Learning

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. The code for the same is available here.

Keywords

Cite

@article{arxiv.2403.01076,
  title  = {Extracting Usable Predictions from Quantized Networks through Uncertainty Quantification for OOD Detection},
  author = {Rishi Singhal and Srinath Srinivasan},
  journal= {arXiv preprint arXiv:2403.01076},
  year   = {2024}
}
R2 v1 2026-06-28T15:06:53.308Z