The University of Macau (UM) said in a statement on Wednesday that it has achieved two major breakthroughs in autonomous driving research.
“A study at the university has provided new insights on autonomous driving under bad weather and complex road conditions while another study has developed new learning models that will be specifically applied to autonomous driving in Macao,” the statement said, adding that the research results will be presented at two annual conferences of artificial intelligence (AI).
In recent years, according to the statement, the development of deep-learning technology has greatly improved machine perception and machine’s cognition of the outside world.
However, real world tasks often encounter problems when the test scene is different from the training scene. For example, the statement pointed out, researchers usually obtain abundant training data from self-driving vehicles on urban roads under standard driving conditions. However, if the trained model is directly applied under rare conditions, such as bad weather or bad road conditions, there often would be significant accuracy drops, the statement said.
To tackle this problem, a research project between the University of Macao and Beijing-based tech giant Baidu has proposed a method termed RIFLE to periodically re-initialise the weight of a classifier in a learning mode. “RIFLE has been proven to provide more meaningful gradient back-propagations,” the statement said.
According to the statement, the researchers have also verified the effectiveness of RIFLE on various real-world transfer learning tasks, including several modern architectures (ResNet, Inception, MobileNet), and basic computer vision tasks (Classification, Detection, Segmentation).
ResNet means residual neural network.
UM PhD student Li Xingjian is the first author of this paper. The paper has been accepted for presentation at the 2020 International Conference on Machine Learning, a top conference in the field of AI.
The second breakthrough comes from a study on the compression of convolutional neural network (CNN) models in transfer learning. The study proposed a new compression method in which transfer and compression are used alternately. According to the statement, this method can reduce the complexity of the model and ensure high accuracy at the same time. By compressing part of the layer of the CNN model, the complexity can be further reduced. Experimental results verify that floating-point operations per second (FLOPs) of ResNet-101 can be reduced by 30 per cent on six target data sets, and the accuracy of compressed model remains almost unchanged.
ResNet-101 is a convolutional neural network that is 101 layers deep.
As FLOPs of the model are reduced by more than 90 per cent, the accuracy is maintained at around 0.70 on multiple data sets. In comparison, models generated by other methods basically failed to work. The paper has been accepted for presentation at the 2020 International Conference on Learning Representation.
Wang Kafeng, a PhD candidate supervised by Prof Xu Chengzhong, is the first author of the paper. The study was jointly conducted by the University of Macau, the Shenzhen Institutes of Advanced Technology under the Chinese Academy of Sciences (CASS), and Baidu.
Macau Connected Autonomous Driving (MoCAD), led by UM’s State Key Laboratory of Internet of Things for Smart City, is funded by the Macau Funding Scheme for Key R&D Projects of the Science and Technology Development Fund.
According to the statement, the project aims to create a swarm intelligence based first-class vehicle platform and an experimental base of vehicle-road coordination for autonomous driving in the Guangdong-Hong Kong-Macao Greater Bay Area (GBA). It is a collaborative effort between UM and leading institutions in mainland China, including Shenzhen Institutes of Advanced Technology, National University of Defense Technology, Baidu, and Shenzhen Haylion Technologies. The project is headed by Prof Xu Chengzhong, dean of UM’s Faculty of Science and Technology, the statement pointed out.
(The Macau Post Daily/Macau News)
PHOTO © University of Macau
