Exploring the power of lightweight YOLOv4
Journal
Proceedings of the IEEE International Conference on Computer Vision
Journal Volume
2021-October
Pages
779-788
Date Issued
2021
Author(s)
Abstract
Research on deep learning has always had two main streams: (1) design a powerful network architecture and train it with existing learning methods to achieve the best results, and (2) design better learning methods so that the existing network architecture can achieve the best capbility after training. In recent years, because mobile device has become popular, the requirement of low power consumption becomes a must. Under the requirement of low power consumption, we hope to design low-cost lightweight networks that can be effectively deployed at the edge, while it must have enough resources to be used and the inference speed must be fast enough. In this work, we set a very ambitious goal of exploring the power of lightweight neural networks. We utilize the analysis of data space, model's representational capacity, and knowledge projection space to construct an automated machine learning pipeline. Through this mechanism, we systematically derive the most suitable knowledge projection space between the data and the model. Our method can indeed automatically find learning strategies suitable for the target model and target application through exploration. Experiment results show that the proposed method can significantly enhance the accuracy of lightweight neural networks for object detection. We directly apply the lightweight model trained by our proposed method to a Jetson Xavier NX embedded module and a Kneron KL720 edge AI SoC as system solutions. ? 2021 IEEE.
Research on deep learning has always had two main streams: (1) design a powerful network architecture and train it with existing learning methods to achieve the best results, and (2) design better learning methods so that the existing network architecture can achieve the best capbility after training. In recent years, because mobile device has become popular, the requirement of low power consumption becomes a must. Under the requirement of low power consumption, we hope to design low-cost lightweight networks that can be effectively deployed at the edge, while it must have enough resources to be used and the inference speed must be fast enough. In this work, we set a very ambitious goal of exploring the power of lightweight neural networks. We utilize the analysis of data space, model's representational capacity, and knowledge projection space to construct an automated machine learning pipeline. Through this mechanism, we systematically derive the most suitable knowledge projection space between the data and the model. Our method can indeed automatically find learning strategies suitable for the target model and target application through exploration. Experiment results show that the proposed method can significantly enhance the accuracy of lightweight neural networks for object detection. We directly apply the lightweight model trained by our proposed method to a Jetson Xavier NX embedded module and a Kneron KL720 edge AI SoC as system solutions. © 2021 IEEE.
Subjects
Deep learning
Electric power utilization
Low power electronics
Object detection
System-on-chip
Analysis of data
Data space
Learning methods
Low-costs
Low-power consumption
Lower-power consumption
Neural-networks
Power
Projection space
Space models
Network architecture
Other Subjects
Deep learning; Electric power utilization; Low power electronics; Object detection; System-on-chip; Analysis of data; Data space; Learning methods; Low-costs; Low-power consumption; Lower-power consumption; Neural-networks; Power; Projection space; Space models; Network architecture
Type
conference paper