Know Where To Drop Your Weights: Towards Faster Uncertainty Estimation
This work addresses the challenge of efficient uncertainty estimation for low-latency applications and out-of-distribution detection, offering an incremental improvement over existing methods.
The paper tackles the problem of computationally expensive uncertainty estimation for low-latency applications by proposing Select-DC, which uses a subset of layers with Monte Carlo DropConnect to reduce GFLOPS significantly with marginal performance trade-offs, as demonstrated on CIFAR and SVHN datasets.
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.