2 papers
cs.AR2022
Going Further With Winograd Convolutions: Tap-Wise Quantization for Efficient Inference on 4x4 Tile
Renzo Andri, Beatrice Bussolino, Antonio Cipolletta +2
Most of today's computer vision pipelines are built around deep neural networks, where convolution operations require most of the generally high compute effort. The Winograd convol…
cs.LG2022
Dynamic ConvNets on Tiny Devices via Nested Sparsity
Matteo Grimaldi, Luca Mocerino, Antonio Cipolletta +1
This work introduces a new training and compression pipeline to build Nested Sparse ConvNets, a class of dynamic Convolutional Neural Networks (ConvNets) suited for inference tasks…