@inproceedings{c903ac21f8164d8a81c48a95ec95a6a9,
title = "ReActXGB: A Hybrid Binary Convolutional Neural Network Architecture for Improved Performance and Computational Efficiency",
abstract = "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.",
keywords = "binary convolution neural network, fully connected layer, hybrid model, model compression, XGBoost",
author = "Chu, {Po Hsun} and Chen, {Ching Han}",
note = "Publisher Copyright: {\textcopyright} 2024 IEEE.; 11th IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2024 ; Conference date: 09-07-2024 Through 11-07-2024",
year = "2024",
doi = "10.1109/ICCE-Taiwan62264.2024.10674242",
language = "???core.languages.en_GB???",
series = "11th IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2024",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "327--328",
booktitle = "11th IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2024",
}