activity
20192026
most citedAccelerating Monte Carlo Bayesian Inference via Approximating Predictive Uncertainty over Simplex

9 citations · 9 across the 5 of their papers we have counts for

collaborators
Showing cs.CVShow all

1 paper · 1 filter

cs.CV2020

Direct Quantization for Training Highly Accurate Low Bit-width Deep Neural Networks

Tuan Hoang, Thanh-Toan Do, Tam V. Nguyen +1

This paper proposes two novel techniques to train deep convolutional neural networks with low bit-width weights and activations. First, to obtain low bit-width weights, most existi…