Extracting Usable Predictions from Quantized Networks through Uncertainty Quantification for OOD Detection
This addresses the need for reliable confidence estimates in compressed models for computer vision applications, though it appears incremental as it builds on existing quantization and uncertainty methods.
The paper tackles the problem of identifying unreliable predictions from quantized neural networks for out-of-distribution (OOD) detection by introducing an uncertainty quantification technique that saves up to 80% of ignored samples from misclassification.
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.