深度学习卷积神经网络中的高效变换
摘要
本研究探讨了将信号处理变换——快速傅里叶变换(FFT)、沃尔什哈达德变换(WHT)和离散余弦变换(DCT)——集成到 ResNet50 卷积神经网络(CNN)模型用于图像分类的方案。 primary objective is to assess the trade-offs between computational efficiency, energy consumption, and classification accuracy during training and inference. Using the CIFAR-100 dataset (100 classes, 60,000 images), experiments demonstrated that incorporating WHT significantly reduced energy consumption while improving accuracy. Specifically, a baseline ResNet50 model achieved a testing accuracy of 66%, consuming an average of 25,606 kJ per model. In contrast, a modified ResNet50 incorporating WHT in the early convolutional layers achieved 74% accuracy, and an enhanced version with WHT applied to both early and late layers achieved 79% accuracy, with an average energy consumption of only 39 kJ per model. These results demonstrate the potential of WHT as a highly efficient and effective approach for energy-constrained CNN applications.
引用
@article{arxiv.2506.16418,
title = {Efficient Transformations in Deep Learning Convolutional Neural Networks},
author = {Berk Yilmaz and Daniel Fidel Harvey and Prajit Dhuri},
journal= {arXiv preprint arXiv:2506.16418},
year = {2025}
}
备注
All authors contributed equally to this work. 17 pages, 36 references, 10 figures, 1 appendix