Search Results for author: Julian Zilly

Found 4 papers, 0 papers with code

Quantifying the effect of representations on task complexity

no code implementations19 Dec 2019 Julian Zilly, Lorenz Hetzel, Andrea Censi, Emilio Frazzoli

To quantify this alignment effect of data representations on the difficulty of a learning task, we make use of an existing task complexity score and show its connection to the representation-dependent information coding length of the input.

The Frechet Distance of training and test distribution predicts the generalization gap

no code implementations25 Sep 2019 Julian Zilly, Hannes Zilly, Oliver Richter, Roger Wattenhofer, Andrea Censi, Emilio Frazzoli

Empirically across several data domains, we substantiate this viewpoint by showing that test performance correlates strongly with the distance in data distributions between training and test set.

Learning Theory Transfer Learning

Inspiring Computer Vision System Solutions

no code implementations22 Jul 2017 Julian Zilly, Amit Boyarski, Micael Carvalho, Amir Atapour Abarghouei, Konstantinos Amplianitis, Aleksandr Krasnov, Massimiliano Mancini, Hernán Gonzalez, Riccardo Spezialetti, Carlos Sampedro Pérez, Hao Li

Reviewing this project with modern eyes provides us with the opportunity to reflect on several issues, relevant now as then to the field of computer vision and research in general, that go beyond the technical aspects of the work.

Cannot find the paper you are looking for? You can Submit a new open access paper.