Jingmin Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Jingmin Li has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Liping Xiong
School of Electronics and Information Engineering, Wuyi University, Jiangmen 529020, Guangdong P. R. China
1 shared publication - Yingwei Feng
College of Electronic and Information Engineering , Wuyi University , Jiangmen, Guangdong , China
1 shared publication - Zhiqiang Zeng
School of Mechanical Engineering, Dongguan University of Technology, Dongguan, China
1 shared publication - Zhiyong Hong
School of Electronics and Information Engineering, Wuyi University, Jiangmen 529020, China
1 shared publication
Latest Publications
- Open Access
- 1 June 2024
- Published by Walter de Gruyter GmbH in Journal of Artificial Intelligence and Soft Computing Research
- Vol. 14 (3) , 191-205
Shufflemono: Rethinking Lightweight Network for Self-Supervised Monocular Depth Estimation
Self-supervised monocular depth estimation has been widely applied in autonomous driving and automated guided vehicles. It offers the advantages of low cost and extended effective distance compared with alternative methods. However, like automated guided vehicles, devices with limited computing resources struggle to leverage state-of-the-art large model structures. In recent years, researchers have acknowledged this issue and endeavored to reduce model size. Model lightweight techniques aim to decrease the number of parameters while maintaining satisfactory performance. In this paper, to enhance the model’s performance in lightweight scenarios, a novel approach to encompassing three key aspects is proposed: (1) utilizing LeakyReLU to involve more neurons in manifold representation; (2) employing large convolution for improved recognition of edges in lightweight models; (3) applying channel grouping and shuffling to maximize the model efficiency. Experimental results demonstrate that our proposed method achieves satisfactory outcomes on KITTI and Make3D benchmarks while having only 1.6M trainable parameters, representing a reduction of 27% compared with the previous smallest model, Lite-Mono-tiny, in monocular depth estimation.
- 1 June 2024
- Published by Walter de Gruyter GmbH in Journal of Artificial Intelligence and Soft Computing Research
- Vol. 14 (3) , 191-205
Open AccessShufflemono: Rethinking Lightweight Network for Self-Supervised Monocular Depth Estimation
Self-supervised monocular depth estimation has been widely applied in autonomous driving and automated guided vehicles. It offers the advantages of low cost and extended effective distance compared with alternative methods. However, like automated guided vehicles, devices with limited computing resources struggle to leverage state-of-the-art large model structures. In recent years, researchers have acknowledged this issue and endeavored to reduce model size. Model lightweight techniques aim to decrease the number of parameters while maintaining satisfactory performance. In this paper, to enhance the model’s performance in lightweight scenarios, a novel approach to encompassing three key aspects is proposed: (1) utilizing LeakyReLU to involve more neurons in manifold representation; (2) employing large convolution for improved recognition of edges in lightweight models; (3) applying channel grouping and shuffling to maximize the model efficiency. Experimental results demonstrate that our proposed method achieves satisfactory outcomes on KITTI and Make3D benchmarks while having only 1.6M trainable parameters, representing a reduction of 27% compared with the previous smallest model, Lite-Mono-tiny, in monocular depth estimation.