3 papers
cs.LG2020
Tensor Reordering for CNN Compression
Matej Ulicny, Vladimir A. Krylov, Rozenn Dahyot
We show how parameter redundancy in Convolutional Neural Network (CNN) filters can be effectively reduced by pruning in spectral domain. Specifically, the representation extracted…
cs.CV2019
Harmonic Networks with Limited Training Samples
Matej Ulicny, Vladimir A. Krylov, Rozenn Dahyot
Convolutional neural networks (CNNs) are very popular nowadays for image processing. CNNs allow one to learn optimal filters in a (mostly) supervised machine learning context. Howe…
cs.CV2018
Harmonic Networks: Integrating Spectral Information into CNNs
Matej Ulicny, Vladimir A. Krylov, Rozenn Dahyot
Convolutional neural networks (CNNs) learn filters in order to capture local correlation patterns in feature space. In contrast, in this paper we propose harmonic blocks that produ…