We open source an AutoML toolkit StarLight. StarLight helps in obtaining lightweight deep neural networks. StarLight consists primarily of three modules: network compression, neural architecture search, and visualization.
We are collaborating with Zhijiang Lab on autonomous driving techniques.
This is a news report from Zhijiang Lab (in Chinese). The following three GIFs (from left to right) demonstrate the effectiveness of our few-shot, zero-shot, and CLIP-enhanced object detection algorithms on our SiTi dataset.
Our autonomous driving car is equipped with a variety of sensors including GNSS, IMU, LIDARs, Radars and cameras. We developed autonomous driving algorithms, which were then validated and deployed in the autonomous driving car. The following GIFs demonstrate the car self-drives on the internal road of ICT.
(supported by the Innovation Project of Institute of Computing Technology, Chinese Academy of Sciences)
Please check out the video for a full-length demo of the very first step (Youtube). The following GIF is a clip of the demo: