Ming Ji
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Ming Ji has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Chenghui Zhen
College of Information Science and Engineering, Huaqiao University, Xiamen, China
6 shared publications - Weiwei Zhang
College of Engineering, Huaqiao University, Quanzhou, China
6 shared publications - Haoran Yu
College of Information Science and Engineering, HuaQiao University, Fujian, QuanZhou 362000, P. R. China
1 shared publication - Haoran Yu
School of Cyberspace Security, Beijing University of Posts and Telecommunications, Beijing, China
1 shared publication - Hongbo Zhou
College of Engineering, Huaqiao University, Quanzhou 362021, China
1 shared publication - Hongbo Zhou
College of Engineering, Huaqiao University, Quanzhou, 362021, Fujian, China; Intelligent Software Research Center, Institute of Software Chinese Academy of Sciences, 100190, Beijing, China
1 shared publication
Latest Publications
- 9 September 2023
- Published by Elsevier in Neural Networks
- Vol. 168, 1-13
RASP: Regularization-based Amplitude Saliency Pruning
- 9 September 2023
- Published by Elsevier in Neural Networks
- Vol. 168, 1-13
RASP: Regularization-based Amplitude Saliency Pruning
- 13 August 2023
- Published by Springer Nature in International Journal of Machine Learning and Cybernetics
- Vol. 15 (2) , 573-588
AFMPM: adaptive feature map pruning method based on feature distillation
- 13 August 2023
- Published by Springer Nature in International Journal of Machine Learning and Cybernetics
- Vol. 15 (2) , 573-588
AFMPM: adaptive feature map pruning method based on feature distillation
- 28 October 2022
- Published by Springer Nature in Neural Processing Letters
- Vol. 55 (4) , 4661-4678
ReLP: Reinforcement Learning Pruning Method Based on Prior Knowledge
- 28 October 2022
- Published by Springer Nature in Neural Processing Letters
- Vol. 55 (4) , 4661-4678
ReLP: Reinforcement Learning Pruning Method Based on Prior Knowledge
- Open Access
- 24 August 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (17) , 8424
Accelerated Inference of Face Detection under Edge-Cloud Collaboration
Model compression makes it possible to deploy face detection models on devices with limited computing resources. Edge–cloud collaborative inference, as a new paradigm of neural network inference, can significantly reduce neural network inference latency. Inspired by these two techniques, this paper adopts a two-step acceleration strategy for the CenterNet model. Firstly, the model pruning method is used to prune the convolutional layer and the deconvolutional layer to obtain a preliminary acceleration effect. Secondly, the neural network is segmented by the optimizer to make full use of the computing resources on the edge and the cloud to further accelerate the inference of the neural network. In the first strategy, we achieve a 62.12% reduction in inference latency compared to the state-of-the-art object detection model Blazeface. Additionally, with a two-step speedup strategy, our method is only 26.5% of the baseline when the bandwidth is 500 kbps.
- 24 August 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (17) , 8424
Open AccessAccelerated Inference of Face Detection under Edge-Cloud Collaboration
Model compression makes it possible to deploy face detection models on devices with limited computing resources. Edge–cloud collaborative inference, as a new paradigm of neural network inference, can significantly reduce neural network inference latency. Inspired by these two techniques, this paper adopts a two-step acceleration strategy for the CenterNet model. Firstly, the model pruning method is used to prune the convolutional layer and the deconvolutional layer to obtain a preliminary acceleration effect. Secondly, the neural network is segmented by the optimizer to make full use of the computing resources on the edge and the cloud to further accelerate the inference of the neural network. In the first strategy, we achieve a 62.12% reduction in inference latency compared to the state-of-the-art object detection model Blazeface. Additionally, with a two-step speedup strategy, our method is only 26.5% of the baseline when the bandwidth is 500 kbps.
- 5 July 2022
- Published by Springer Nature in Neural Processing Letters
- Vol. 55 (2) , 1071-1085
ACP: Automatic Channel Pruning Method by Introducing Additional Loss for Deep Neural Networks
- 5 July 2022
- Published by Springer Nature in Neural Processing Letters
- Vol. 55 (2) , 1071-1085
ACP: Automatic Channel Pruning Method by Introducing Additional Loss for Deep Neural Networks
- Open Access
- 4 January 2022
- Published by MDPI AG in Future Internet
- Vol. 14 (1) , 21
SMYOLO: Lightweight Pedestrian Target Detection Algorithm in Low-Altitude Scenarios
Due to the arbitrariness of the drone’s shooting angle of view and camera movement and the limited computing power of the drone platform, pedestrian detection in the drone scene poses a greater challenge. This paper proposes a new convolutional neural network structure, SMYOLO, which achieves the balance of accuracy and speed from three aspects: (1) By combining deep separable convolution and point convolution and replacing the activation function, the calculation amount and parameters of the original network are reduced; (2) by adding a batch normalization (BN) layer, SMYOLO accelerates the convergence and improves the generalization ability; and (3) through scale matching, reduces the feature loss of the original network. Compared with the original network model, SMYOLO reduces the accuracy of the model by only 4.36%, the model size is reduced by 76.90%, the inference speed is increased by 43.29%, and the detection target is accelerated by 33.33%, achieving minimization of the network model volume while ensuring the detection accuracy of the model.
- 4 January 2022
- Published by MDPI AG in Future Internet
- Vol. 14 (1) , 21
Open AccessSMYOLO: Lightweight Pedestrian Target Detection Algorithm in Low-Altitude Scenarios
Due to the arbitrariness of the drone’s shooting angle of view and camera movement and the limited computing power of the drone platform, pedestrian detection in the drone scene poses a greater challenge. This paper proposes a new convolutional neural network structure, SMYOLO, which achieves the balance of accuracy and speed from three aspects: (1) By combining deep separable convolution and point convolution and replacing the activation function, the calculation amount and parameters of the original network are reduced; (2) by adding a batch normalization (BN) layer, SMYOLO accelerates the convergence and improves the generalization ability; and (3) through scale matching, reduces the feature loss of the original network. Compared with the original network model, SMYOLO reduces the accuracy of the model by only 4.36%, the model size is reduced by 76.90%, the inference speed is increased by 43.29%, and the detection target is accelerated by 33.33%, achieving minimization of the network model volume while ensuring the detection accuracy of the model.