Zhao, FeiLiu, HuanyuHu, MoufaDeng, YingjieWith the rise of convolutional neural network (CNN) in the field of computer vision, more and more practical applications need to deploy CNN on mobile devices. However, due to the large amount of CNN computing operations and the large number of parameters, it is difficult to deploy on ordinary edge devices. The neural network model compression method has become a popular technology to reduce the computational cost and has attracted more and more attention. We specifically design a small target detection network for hardware platforms with limited computing resources, use pruning and quantization methods to compress, and demonstrate in VOC dataset and RSOD dataset on the actual hardware platform. Experiments show that the proposed method can maintain a fairly accurate rate while greatly speeding up the inference speed. The proposed model designed in this paper achieves 76.74% mAP on the VOC dataset, which is 4.76 times faster than the original model.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Channel Pruning and Quantization-Based Learning for Object Detection with Computing Source Limited Application


    Weitere Titelangaben:

    Smart Innovation, Systems and Technologies


    Beteiligte:
    Wu, Tsu-Yang (Herausgeber:in) / Ni, Shaoquan (Herausgeber:in) / Chu, Shu-Chuan (Herausgeber:in) / Chen, Chi-Hua (Herausgeber:in) / Favorskaya, Margarita (Herausgeber:in) / Zhao, Fei (Autor:in) / Liu, Huanyu (Autor:in) / Hu, Moufa (Autor:in) / Deng, Yingjie (Autor:in)


    Erscheinungsdatum :

    2021-11-30


    Format / Umfang :

    9 pages





    Medientyp :

    Aufsatz/Kapitel (Buch)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch





    Pruning training sets for learning of object categories

    Angelova, A. / Abu-Mostafam, Y. / Perona, P. | IEEE | 2005


    Pruning and Quantization for Deeper Artificial Intelligence (AI) Model Optimization

    Singh, Suryabhan / Sharma, Kirti / Karna, Brijesh Kumar et al. | Springer Verlag | 2023


    Hardware-Aware Latency Pruning for Real-Time 3D Object Detection

    Shen, Maying / Mao, Lei / Chen, Joshua et al. | IEEE | 2023


    Joint Source-Channel Optimization of Vector Quantization with Polar Codes

    Mohammadi, Mohammad Sadegh / Dutkiewicz, Eryk / Zhang, Qi | IEEE | 2016