ReActXGB: A Hybrid Binary Convolutional Neural Network Architecture for Improved Performance and Computational Efficiency

Po Hsun Chu, Ching Han Chen

研究成果: 書貢獻/報告類型會議論文篇章同行評審

摘要

Binary convolutional neural networks (BCNNs) provide a potential solution to reduce the memory requirements and computational costs associated with deep neural networks (DNNs). However, achieving a trade-off between performance and computational resources remains a significant challenge. Furthermore, the fully connected layer of BCNNs has evolved into a significant computational bottleneck. This is mainly due to the conventional practice of excluding the input layer and fully connected layer from binarization to prevent a substantial loss in accuracy. In this paper, we propose a hybrid model named ReActXGB, where we replace the fully convolutional layer of ReActNet-A with XGBoost. This modification targets to narrow the performance gap between BCNNs and real-valued networks while maintaining lower computational costs. Experimental results on the FashionMNIST benchmark demonstrate that ReActXGB outperforms ReActNet-A by 1.47% in top-1 accuracy, along with a reduction of 7.14% in floating-point operations (FLOPs) and 1.02% in model size.

原文???core.languages.en_GB???
主出版物標題11th IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2024
發行者Institute of Electrical and Electronics Engineers Inc.
頁面327-328
頁數2
ISBN(電子)9798350386844
DOIs
出版狀態已出版 - 2024
事件11th IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2024 - Taichung, Taiwan
持續時間: 9 7月 202411 7月 2024

出版系列

名字11th IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2024

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???11th IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2024
國家/地區Taiwan
城市Taichung
期間9/07/2411/07/24

指紋

深入研究「ReActXGB: A Hybrid Binary Convolutional Neural Network Architecture for Improved Performance and Computational Efficiency」主題。共同形成了獨特的指紋。

引用此