1 code implementation • 31 May 2021 • David Peer, Sebastian Stabinger, Stefan Engl, Antonio Rodriguez-Sanchez
Knowledge distillation maintains high performance and reaches high compression rates, nevertheless, the size of the student model is fixed after pre-training and can not be changed individually for a given downstream task and use-case to reach a desired performance/speedup ratio.
1 code implementation • 15 Apr 2021 • Josef Gugglberger, David Peer, Antonio Rodriguez-Sanchez
Capsule networks are a type of neural network that have recently gained increased popularity.
1 code implementation • 7 Mar 2021 • David Peer, Sebastian Stabinger, Antonio Rodriguez-Sanchez
In the worst-case scenario, we prove that such a layer could lead to a network that cannot be trained at all.
1 code implementation • 5 Nov 2020 • David Peer, Sebastian Stabinger, Antonio Rodriguez-Sanchez
In this paper, we introduce a novel theory and metric to identify layers that decrease the test accuracy of the trained models, this identification is done as early as at the beginning of training.
no code implementations • 21 May 2019 • David Peer, Sebastian Stabinger, Antonio Rodriguez-Sanchez
A recently proposed method in deep learning groups multiple neurons to capsules such that each capsule represents an object or part of an object.
1 code implementation • 23 Dec 2018 • David Peer, Sebastian Stabinger, Antonio Rodriguez-Sanchez
In this paper we introduce a new inductive bias for capsule networks and call networks that use this prior $\gamma$-capsule networks.
no code implementations • 6 Dec 2017 • Sebastian Stabinger, Antonio Rodriguez-Sanchez
Over the last couple of years, deep learning and especially convolutional neural networks have become one of the work horses of computer vision.
no code implementations • 25 Aug 2017 • Sebastian Stabinger, Antonio Rodriguez-Sanchez
Convolutional Neural Networks have become state of the art methods for image classification over the last couple of years.
no code implementations • 17 Jun 2016 • Sebastian Stabinger, Antonio Rodriguez-Sanchez, Justus Piater
Humans are generally good at learning abstract concepts about objects and scenes (e. g.\ spatial orientation, relative sizes, etc.).