Neural Pruning Search for Real-Time Object Detection of Autonomous Vehicles
TimeThursday, December 9th2:10pm - 2:30pm PST
DescriptionObject detection plays an important role in self-driving cars. However, mobile systems on self-driving cars with limited resources lead to difficulties for object detection. To facilitate this, we propose a compiler-aware neural pruning search framework to achieve high-speed inference on autonomous vehicles for 2D and 3D object detection. The framework automatically searches the pruning scheme and rate for each layer to find a best-suited pruning for optimizing detection accuracy and speed performance under compiler optimization. Our experiments demonstrate that for the first time, the proposed method achieves (close-to) real-time on an off-the-shelf mobile phone with minor accuracy loss.