Section: New Software and Platforms

BlitzNet

A Real-Time Deep Network for Scene Understanding

Keyword: Computer vision

Functional Description: Real-time scene understanding has become crucial in many applications such as autonomous driving. This deep architecture, called BlitzNet, jointly performs object detection and semantic segmentation in one forward pass, allowing real-time computations. Besides the computational gain of having a single network to perform several tasks, object detection and semantic segmentation benefit from each other in terms of accuracy.

• Participants: Mikita Dvornik, Konstantin Shmelkov, Julien Mairal and Cordelia Schmid

• Contact: Mikita Dvornik

• Publication: BlitzNet: A Real-Time Deep Network for Scene Understanding

• URL: https://github.com/dvornikita/blitznet