The self driving challenge in 2021 is this century's technological equivalent of the space race, and is now entering the second major decade of development.
Semantic segmentation in autonomous driving predominantly focuses on learning from large-scale data with a closed set of known classes without considering unknown objects.
We present FIERY: a probabilistic future prediction model in bird's-eye view from monocular cameras.
Ranked #1 on Bird's-Eye View Semantic Segmentation on nuScenes
We formalize the task of video class agnostic segmentation from monocular video sequences in autonomous driving to account for unknown objects.
We present a novel deep learning architecture for probabilistic future prediction from video.
no code implementations • 30 Nov 2019 • Jeffrey Hawke, Richard Shen, Corina Gurau, Siddharth Sharma, Daniele Reda, Nikolay Nikolov, Przemyslaw Mazur, Sean Micklethwaite, Nicolas Griffiths, Amar Shah, Alex Kendall
As our main contribution, we present an end-to-end conditional imitation learning approach, combining both lateral and longitudinal control on a real vehicle for following urban routes with simple traffic.
Simulation can be a powerful tool for understanding machine learning systems and designing methods to solve real-world problems.
This allows us to reason holistically about the spatial configuration of the scene in a domain where scale is consistent and distances between objects are meaningful.
We demonstrate the first application of deep reinforcement learning to autonomous driving.
Numerous deep learning applications benefit from multi-task learning with multiple regression and classification objectives.
On the other hand, epistemic uncertainty accounts for uncertainty in the model -- uncertainty which can be explained away given enough data.
Ranked #59 on Semantic Segmentation on NYU Depth v2
We propose a novel deep learning architecture for regressing disparity from a rectified pair of stereo images.
Semantic segmentation is an important tool for visual scene understanding and a meaningful measure of uncertainty is essential for decision making.
We show that SegNet provides good performance with competitive inference time and more efficient inference memory-wise as compared to other architectures.
Ranked #3 on Medical Image Segmentation on RITE
Using a Bayesian convolutional neural network implementation we obtain an estimate of the model's relocalization uncertainty and improve state of the art localization accuracy on a large scale outdoor dataset.