1 code implementation • 27 Apr 2024 • Junyi Gu, Mauro Bellone, Tomáš Pivoňka, Raivo Sell
Our proposal uses the novel progressive-assemble strategy of vision transformers on a double-direction network and then integrates the results in a cross-fusion strategy over the transformer decoder layers.
1 code implementation • 21 Sep 2018 • Luca Caltagirone, Mauro Bellone, Lennart Svensson, Mattias Wahde
Whereas in the former two fusion approaches, the integration of multimodal information is carried out at a predefined depth level, the cross fusion FCN is designed to directly learn from data where to integrate information; this is accomplished by using trainable cross connections between the LIDAR and the camera processing branches.
no code implementations • 27 Mar 2017 • Luca Caltagirone, Mauro Bellone, Lennart Svensson, Mattias Wahde
The fully convolutional neural network trained using all the available sensors together with driving directions achieved the best MaxF score of 88. 13% when considering a region of interest of 60x60 meters.