18.2k citations
- University of Applied Sciences and Arts of Southern SwitzerlandCH65 papers
- Università della Svizzera italianaCH39 papers
- ETH ZurichCH9 papers
- Data61AU8 papers
- Politecnico di MilanoIT7 papers
- University of BolognaIT7 papers
- Centre National de la Recherche ScientifiqueFR4 papers
- Ghent UniversityBE3 papers
- Google (United States)US3 papers
- Hokkaido UniversityJP3 papers
- IMT School for Advanced Studies LuccaIT3 papers
- King Abdullah University of Science and TechnologySA3 papers
6 papers · 1 filter
Profile extrema for visualizing and quantifying uncertainties on excursion regions. Application to coastal flooding
Dario Azzimonti, David Ginsbourger, Jérémy Rohmer +1
We consider the problem of describing excursion sets of a real-valued function , i.e. the set of inputs where is above a fixed threshold. Such regions are hard to visualize…
Learning Ground Traversability from Simulations
R. Omar Chavez-Garcia, Jerome Guzzi, Luca M. Gambardella +1
Mobile ground robots operating on unstructured terrain must predict which areas of the environment they are able to pass in order to plan feasible paths. We address traversability…
Hierarchical Multinomial-Dirichlet model for the estimation of conditional probability tables
L. Azzimonti, G. Corani, M. Zaffalon
We present a novel approach for estimating conditional probability tables, based on a joint, rather than independent, estimate of the conditional distributions belonging to the sam…
Improving Speaker-Independent Lipreading with Domain-Adversarial Training
Michael Wand, Juergen Schmidhuber
We present a Lipreading system, i.e. a speech recognition system using only visual features, which uses domain-adversarial training for speaker independence. Domain-adversarial tra…
A constructive approach to Schaeffer's conjecture
Oleg Szehr, Rachid Zarouf
J.J. Schaeffer proved that for induced matrix norm and invertible the inequality \[\left|\det T\right|\left\Vert T^{-1}\right\Vert \leq\mathcal{S}\left\Vert T\…
Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
Antti Tarvainen, Harri Valpola
The recently proposed Temporal Ensembling has achieved state-of-the-art results in several semi-supervised learning benchmarks. It maintains an exponential moving average of label…