Know Where To Drop Your Weights: Towards Faster Uncertainty Estimation

Abstract

Estimating epistemic uncertainty of models used in low-latency applications and Out-Of-Distribution samples detection is a challenge due to the computationally demanding nature of uncertainty estimation techniques. Estimating model uncertainty using approximation techniques like Monte Carlo Dropout (MCD), DropConnect (MCDC) requires a large number of forward passes through the network, rendering them inapt for low-latency applications. We propose Select-DC which uses a subset of layers in a neural network to model epistemic uncertainty with MCDC. Through our experiments, we show a significant reduction in the GFLOPS required to model uncertainty, compared to Monte Carlo DropConnect, with marginal trade-off in performance. We perform a suite of experiments on CIFAR 10, CIFAR 100, and SVHN datasets with ResNet and VGG models. We further show how applying DropConnect to various layers in the network with different drop probabilities affects the networks performance and the entropy of the predictive distribution.

arXiv comment8 pages, 6 figures, 1 table, with appendix, submitted to a NeurIPS workshop

References in corpus (6)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
• On Calibration of Modern Neural Networks
• Weight Uncertainty in Neural Networks
• Learning Confidence for Out-of-Distribution Detection in Neural Networks
• Radial Bayesian Neural Networks: Beyond Discrete Support In Large-Scale Bayesian Deep Learning