398 citations
- Data61AU6 papers
- Ghent UniversityBE3 papers
- University of Applied Sciences and Arts of Southern SwitzerlandCH3 papers
- Hokkaido UniversityJP2 papers
- Technical University of MunichDE2 papers
- ArcelorMittal (France)FR1 paper
- École Nationale Supérieure des Mines de ParisFR1 paper
- Indian Institute of Technology GuwahatiIN1 paper
- Laboratoire d’Informatique Fondamentale de MarseilleFR1 paper
- Max Planck SocietyDE1 paper
- McGill UniversityCA1 paper
- Tata Institute of Fundamental ResearchIN1 paper
5 papers · 1 filter
Deep Networks with Internal Selective Attention through Feedback Connections
Marijn Stollenga, Jonathan Masci, Faustino Gomez +1
Traditional convolutional neural networks (CNN) are stationary and feedforward. They neither change their parameters during evaluation nor use feedback from higher to lower layers.…
A Fast Learning Algorithm for Image Segmentation with Max-Pooling Convolutional Networks
Jonathan Masci, Alessandro Giusti, Dan Cireşan +2
We present a fast algorithm for training MaxPooling Convolutional Networks to segment images. This type of network yields record-breaking performance in a variety of tasks, but is…
A Learning Framework for Morphological Operators using Counter-Harmonic Mean
Jonathan Masci, Jesús Angulo, Jürgen Schmidhuber
We present a novel framework for learning morphological operators using counter-harmonic mean. It combines concepts from morphology and convolutional neural networks. A thorough ex…
Object Recognition with Multi-Scale Pyramidal Pooling Networks
Jonathan Masci, Ueli Meier, Gabriel Fricout +1
We present a Multi-Scale Pyramidal Pooling Network, featuring a novel pyramidal pooling layer at multiple scales and a novel encoding layer. Thanks to the former the network does n…
Multimodal similarity-preserving hashing
Jonathan Masci, Michael M. Bronstein, Alexander A. Bronstein +1
We introduce an efficient computational framework for hashing data belonging to multiple modalities into a single representation space where they become mutually comparable. The pr…