A Deeper Look into Convolutions via Eigenvalue-based Pruning. (arXiv:2102.02804v2 [cs.CV] UPDATED)

Convolutional neural networks (CNNs) are able to attain better visual
recognition performance than fully connected neural networks despite having
much fewer parameters due to their parameter sharing principle. Modern
architectures usually contain a small number of fully-connected layers, often
at the end, after multiple layers of convolutions. In some cases, most of the
convolutions can be eliminated without suffering any loss in recognition
performance. However, there is no solid recipe to detect the hidden subset of
convolutional neurons that is …

arxiv eigenvalue pruning