論文

2020年7月

Retraining Quantized Neural Network Models with Unlabeled Data

Proceedings of the International Joint Conference on Neural Networks
  • Kundjanasith Thonglek
  • ,
  • Keichi Takahashi
  • ,
  • Kohei Ichikawa
  • ,
  • Chawanat Nakasan
  • ,
  • Hidemoto Nakada
  • ,
  • Ryousei Takano
  • ,
  • Hajimu Iida

開始ページ
1
終了ページ
8
記述言語
掲載種別
研究論文(国際会議プロシーディングス)
DOI
10.1109/IJCNN48605.2020.9207190

Running neural network models on edge devices is attracting much attention by neural network researchers since edge computing technology is becoming more powerful than ever. However, deploying large neural network models on edge devices is challenging due to the limitation in available computing resources and storage space. Therefore, model compression techniques have been recently studied to reduce the model size and fit models on resource-limited edge devices. Compressing neural network models reduces the size of a model, but also degrades the accuracy of the model since it reduces the precision of weights in the model. Consequently, a retraining method is required to recover the accuracy of compressed models. Most existing retraining methods require the original labeled training datasets to retrain the models, but labeling is a time-consuming process. In particular, we cannot always access the original labeled datasets because of privacy policies and license limitations. In this paper, we propose a method to retrain a compressed neural network model with an unlabeled dataset that is different from the original labeled dataset. We compress the neural network model using quantization to decrease the size of the model. Subsequently, the compressed model is retrained by our proposed retraining method without using a labeled dataset to recover the accuracy of the model. We compared the proposed retraining method against the conventional retraining. The proposed method reduced the size of VGG-16 and ResNet-50 by 81.10% and 52.45%, respectively without significant accuracy loss. In addition, our proposed retraining method is clearly faster than the conventional retraining method.

リンク情報
DOI
https://doi.org/10.1109/IJCNN48605.2020.9207190
Scopus
https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85093841251&origin=inward
Scopus Citedby
https://www.scopus.com/inward/citedby.uri?partnerID=HzOxMe3b&scp=85093841251&origin=inward
URL
https://dblp.uni-trier.de/conf/ijcnn/2020
URL
https://dblp.uni-trier.de/db/conf/ijcnn/ijcnn2020.html#ThonglekTINNTI20

エクスポート
BibTeX RIS