2 papers
cs.CV2021
Adaptive Test-Time Augmentation for Low-Power CPU
Luca Mocerino, Roberto G. Rizzo, Valentino Peluso +2
Convolutional Neural Networks (ConvNets) are trained offline using the few available data and may therefore suffer from substantial accuracy loss when ported on the field, where un…
cs.LG2019
EAST: Encoding-Aware Sparse Training for Deep Memory Compression of ConvNets
Matteo Grimaldi, Valentino Peluso, Andrea Calimera
The implementation of Deep Convolutional Neural Networks (ConvNets) on tiny end-nodes with limited non-volatile memory space calls for smart compression strategies capable of shrin…