7 citations · 10 across the 2 of their papers we have counts for
3 papers · 1 filter
Leveraging Expert Models for Training Deep Neural Networks in Scarce Data Domains: Application to Offline Handwritten Signature Verification
Dimitrios Tsourounis, Ilias Theodorakopoulos, Elias N. Zois +1
This paper introduces a novel approach to leverage the knowledge of existing expert models for training new Convolutional Neural Networks, on domains where task-specific data are l…
A comprehensive study of sparse representation techniques for offline signature verification
Elias N. Zois, Dimitrios Tsourounis, Ilias Theodorakopoulos +2
In this work, a feature extraction method for offline signature verification is presented that harnesses the power of sparse representation in order to deliver state-of-the-art ver…
Parsimonious Inference on Convolutional Neural Networks: Learning and applying on-line kernel activation rules
I. Theodorakopoulos, V. Pothos, D. Kastaniotis +1
A new, radical CNN design approach is presented in this paper, considering the reduction of the total computational load during inference. This is achieved by a new holistic interv…