NAIS: Neural Architecture and Implementation Search and its Applications in Autonomous Driving

no code implementations • 18 Nov 2019 • Cong Hao, Yao Chen, Xinheng Liu, Atif Sarwari, Daryl Sew, Ashutosh Dhar, Bryan Wu, Dongdong Fu, JinJun Xiong, Wen-mei Hwu, Junli Gu, Deming Chen

The rapidly growing demands for powerful AI algorithms in many application domains have motivated massive investment in both high-quality deep neural network (DNN) models and high-efficiency implementations.

Autonomous Driving

Self-Supervised Learning of Depth and Ego-motion with Differentiable Bundle Adjustment

no code implementations • 28 Sep 2019 • Yunxiao Shi, Jing Zhu, Yi Fang, Kuochin Lien, Junli Gu

Learning to predict scene depth and camera motion from RGB inputs only is a challenging task.

Depth And Camera Motion Self-Supervised Learning

Structure-Attentioned Memory Network for Monocular Depth Estimation

no code implementations • 10 Sep 2019 • Jing Zhu, Yunxiao Shi, Mengwei Ren, Yi Fang, Kuo-Chin Lien, Junli Gu

To this end, we introduce a new Structure-Oriented Memory (SOM) module to learn and memorize the structure-specific information between RGB image domain and the depth domain.

Domain Adaptation Monocular Depth Estimation

Learning Object-specific Distance from a Monocular Image

no code implementations • ICCV 2019 • Jing Zhu, Yi Fang, Husam Abu-Haimed, Kuo-Chin Lien, Dongdong Fu, Junli Gu

Environment perception, including object detection and distance estimation, is one of the most crucial tasks for autonomous driving.

Autonomous Driving Object +2