用沃尔什-哈达玛变换提升ResNet50的能效与准确率
Efficient Transformations in Deep Learning Convolutional Neural Networks
- 在ResNet50中引入WHT替代部分卷积，降低计算开销
- 早期+晚期应用WHT使准确率达79%，能耗降至39 kJ/模型
- 适合边缘设备等能源受限场景的高效模型设计
本研究探讨了快速傅里叶变换（FFT）、沃尔什-哈达玛变换（WHT）和离散余弦变换（DCT）在ResNet50卷积神经网络中的集成应用，目标是评估训练与推理过程中计算效率、能耗与分类准确率之间的权衡。基于CIFAR-100数据集（100类，6万张图像）的实验表明，引入WHT显著降低了能耗并提升了准确率。基准ResNet50模型测试准确率为66%，平均能耗25,606 kJ/模型；而在早期卷积层引入WHT的改进模型达到74%准确率；进一步在早期和后期层均使用WHT的版本，准确率达到79%，平均能耗仅为39 kJ/模型。结果证明WHT在能效约束的CNN应用中具有高度有效性。
原文摘要 · Abstract (English)
This study investigates the integration of signal processing transformations -- Fast Fourier Transform (FFT), Walsh-Hadamard Transform (WHT), and Discrete Cosine Transform (DCT) -- within the ResNet50 convolutional neural network (CNN) model for image classification. The 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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。