Cheng He
Assistant Professor
Biography
Dr. is currently an Associate Professor with the School of Electrical and Electronic Engineering, Huazhong University of Science and Technology, Wuhan, China. His current research interests include model-based evolutionary algorithms, multiobjective optimization, large-scale optimization, deep learning, and their applications. He is a recipient of the SUSTech Presidential Outstanding Postdoctoral Award from Southern University of Science and Technology, and the leading Guest Editor for “Special Issue: Emerging Topics in Evolutionary Multiobjective Optimization” of the Complex and Intelligent Systems.
Download my resumé.
- Model-based/data-driven optimization
- Multi/many-objective optimization
- Large-scale optimization
- Combination of deep learning and evolutionary algorithm
PhD, Control Theory and Engineering, 2012 - 2018
Huazhong University of Science and Technology, China
BEng, Automation, 2008 - 2012
Wuhan University of Science and Technology, China
Work Experiences
Committee Services
Editorial Services
Conference Organizers
Awards
Featured Publications
Despite the remarkable successes of convolutional neural networks (CNNs) in computer vision, it is time-consuming and error-prone to manually design a CNN. Among various neural architecture search (NAS) methods that are motivated to automate designs of high-performance CNNs, the differentiable NAS and population-based NAS are attracting increasing interests due to their unique characters. To benefit from the merits while overcoming the deficiencies of both, this work proposes a novel NAS method, RelativeNAS. As the key to efficient search, RelativeNAS performs joint learning between fast learners (i.e., decoded networks with relatively lower loss value) and slow learners in a pairwise manner. Moreover, since RelativeNAS only requires low-fidelity performance estimation to distinguish each pair of fast learner and slow learner, it saves certain computation costs for training the candidate architectures. The proposed RelativeNAS brings several unique advantages: 1) it achieves state-of-the-art performances on ImageNet with top-1 error rate of 24.88%, that is, outperforming DARTS and AmoebaNet-B by 1.82% and 1.12%, respectively; 2) it spends only 9 h with a single 1080Ti GPU to obtain the discovered cells, that is, 3.75x and 7875x faster than DARTS and AmoebaNet, respectively; and 3) it provides that the discovered cells obtained on CIFAR-10 can be directly transferred to object detection, semantic segmentation, and keypoint detection, yielding competitive results of 73.1% mAP on PASCAL VOC, 78.7% mIoU on Cityscapes, and 68.5% AP on MSCOCO, respectively. The implementation of RelativeNAS is available at https://github.com/EMI-Group/RelativeNAS.