no code implementations • 9 Dec 2020 • Naif Alshammari, Samet Akcay, Toby P. Breckon
Using this architectural formulation with dense skip connections, our model achieves comparable performance to contemporary approaches at a fraction of the overall model complexity.
no code implementations • 9 Dec 2020 • Naif Alshammari, Samet Akcay, Toby P. Breckon
For optimal performance in semantic segmentation, our model generates depth to be used as complementary source information with RGB in the segmentation network.
no code implementations • 17 Sep 2019 • Naif Alshammari, Samet Akçay, Toby P. Breckon
Joint scene understanding and segmentation for automotive applications is a challenging problem in two key aspects:- (1) classifying every pixel in the entire scene and (2) performing this task under unstable weather and illumination changes (e. g. foggy weather), which results in poor outdoor scene visibility.