We describe the approach that won the preliminary phase of the German traffic sign recognition benchmark with a better-than-human recognition rate of 98.98%.We obtain an even better recognition rate of 99.15% by further training the nets. Our fast, fully parameterizable GPU implementation of a Convolutional Neural Network does not require careful design of pre-wired feature extractors, which are rather learned in a supervised way. A CNN/MLP committee further boosts recognition performance.
Building similarity graph...
Analyzing shared references across papers
Loading...
Dan Cireşan
University of Applied Sciences and Arts of Southern Switzerland
Ueli Meier
University of Bern
Jonathan Masci
University of Applied Sciences and Arts of Southern Switzerland
Dalle Molle Institute for Artificial Intelligence Research
University of Applied Sciences and Arts of Southern Switzerland
Building similarity graph...
Analyzing shared references across papers
Loading...
Cireşan et al. (Fri,) studied this question.
synapsesocial.com/papers/69d908da183921ebcaae4776 — DOI: https://doi.org/10.1109/ijcnn.2011.6033458
Synapse has enriched 4 closely related papers on similar clinical questions. Consider them for comparative context: