3.1k citations · 3.4k across the 5 of their papers we have counts for
3 papers · 1 filter
VisualBackProp: efficient visualization of CNNs
Mariusz Bojarski, Anna Choromanska, Krzysztof Choromanski +4
This paper proposes a new method, that we call VisualBackProp, for visualizing which sets of pixels of the input image contribute most to the predictions made by the convolutional…
Fast Incremental Learning for Off-Road Robot Navigation
Artem Provodin, Liila Torabi, Beat Flepp +5
A promising approach to autonomous driving is machine learning. In such systems, training datasets are created that capture the sensory input to a vehicle as well as the desired re…
End to End Learning for Self-Driving Cars
Mariusz Bojarski, Davide Del Testa, Daniel Dworakowski +10
We trained a convolutional neural network (CNN) to map raw pixels from a single front-facing camera directly to steering commands. This end-to-end approach proved surprisingly powe…