Designed Dithering Sign Activation for Binary Neural Networks

arXiv:2405.02220v1 Announce Type: cross
Abstract: Binary Neural Networks emerged as a cost-effective and energy-efficient solution for computer vision tasks by binarizing either network weights or activations. However, common binary activations, such as the Sign activation function, abruptly binarize the values with a single threshold, losing fine-grained details in the feature outputs. This work proposes an activation that applies multiple thresholds following dithering principles, shifting the Sign activation function for each pixel according to a spatially periodic threshold kernel. Unlike literature …

abstract arxiv binary computer computer vision cost cs.cv cs.lg energy feature fine-grained function however network networks neural networks solution tasks threshold type values vision