no code implementations • 4 Oct 2023 • Hao Sha, Yao Mu, YuXuan Jiang, Li Chen, Chenfeng Xu, Ping Luo, Shengbo Eben Li, Masayoshi Tomizuka, Wei Zhan, Mingyu Ding
Existing learning-based autonomous driving (AD) systems face challenges in comprehending high-level information, generalizing to rare events, and providing interpretability.
no code implementations • 19 Feb 2021 • Baohua Sun, Tao Zhang, Jiapeng Su, Hao Sha
Object detection is widely used on embedded devices.
no code implementations • 9 Jan 2021 • Baohua Sun, Weixiong Lin, Hao Sha, Jiapeng Su
In this paper, we optimize the semantic segmentation model in order to fully utilize the limited memory and the supported operators on the CNN accelerator chips, and at the same time reduce the CPU load of the CNN model to zero.
no code implementations • 21 Nov 2020 • Baohua Sun, Michael Lin, Hao Sha, Lin Yang
The existing methods normally detect where the characters are, and then recognize the character for each detected location.
no code implementations • 28 Jan 2020 • Baohua Sun, Lin Yang, Hao Sha, Michael Lin
Recent years NLP research has witnessed the record-breaking accuracy improvement by DNN models.