压缩ConvNeXt模型，让图像分类在边缘设备上又快又准。
Edge AI: Evaluation of Model Compression Techniques for Convolutional Neural Networks
- 用结构化剪枝和动态量化压缩模型，保留准确率。
- 最高减少95%参数量，模型大小降89.7%，推理仅20毫秒。
- 适合部署在资源受限的边缘设备，如手机、IoT终端。
本研究在CIFAR-10数据集上评估了针对图像分类任务中ConvNeXt模型的压缩技术，包括结构化剪枝、非结构化剪枝和动态量化，旨在降低模型尺寸与计算复杂度的同时保持准确性。实验在云平台与边缘设备上进行。结果表明，结构化剪枝可实现高达75%的模型尺寸缩减；动态量化则使参数量最多减少95%。微调后的模型表现出更优的压缩性能，说明预训练结合压缩具有优势。非结构化剪枝虽提升压缩率，但对计算复杂度改善有限。结合OTOV3剪枝与动态量化后，模型尺寸减少89.7%，参数量与乘加操作（MACs）下降95%，准确率反而提升3.8%。最终压缩模型在边缘设备上部署，实现92.5%准确率与20毫秒推理时间，验证了压缩技术在真实边缘计算场景中的有效性。
原文摘要 · Abstract (English)
This work evaluates the compression techniques on ConvNeXt models in image classification tasks using the CIFAR-10 dataset. Structured pruning, unstructured pruning, and dynamic quantization methods are evaluated to reduce model size and computational complexity while maintaining accuracy. The experiments, conducted on cloud-based platforms and edge device, assess the performance of these techniques. Results show significant reductions in model size, with up to 75% reduction achieved using structured pruning techniques. Additionally, dynamic quantization achieves a reduction of up to 95% in the number of parameters. Fine-tuned models exhibit improved compression performance, indicating the benefits of pre-training in conjunction with compression techniques. Unstructured pruning methods reveal trends in accuracy and compression, with limited reductions in computational complexity. The combination of OTOV3 pruning and dynamic quantization further enhances compression performance, resulting 89.7% reduction in size, 95% reduction with number of parameters and MACs, and 3.8% increase with accuracy. The deployment of the final compressed model on edge device demonstrates high accuracy 92.5% and low inference time 20 ms, validating the effectiveness of compression techniques for real-world edge computing 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。