用进化算法优化量化模型权重，提升低精度部署下的准确率。
Evolutionary fine tuning of quantized convolution-based deep learning models
- 用进化策略迭代调整少量权重至更优量化状态。
- 在VGG、ResNet等模型上实现量化后准确率显著提升。
- 适合需要轻量化部署的边缘设备开发人员参考。
深度学习模型在诸多机器学习任务中表现最优，但在物联网、移动设备及实时系统中因复杂度高、内存占用大而受限。为此，研究聚焦于压缩技术，尤其是量化。现有方法多采用最近邻量化，但该方式未必达到最佳精度。本文提出基于进化策略的微调方法：每轮迭代仅调整少量权重值，使其跃迁至更优的量化级别。实验表明，通过合理设置算子与参数，该方法能快速提升量化模型的准确率。结果涵盖VGG、ResNet等主流图像分类与检测模型，以及自编码器架构的仿真验证。
原文摘要 · Abstract (English)
Deep learning models are the most efficient models in many machine learning tasks. The main disadvantage when using them in IoT, mobile devices, independent autonomous or real-time systems is their complexity and memory size. Therefore, much research has concentrated on compression techniques of deep learning architectures. One of the most popular technique is quantization. In most of the works, the quantization is done based on the nearest neighbour quantization technique. This work focuses on improving the quantization efficiency in pretrained and quantized models. This approach has the potential to improve the final accuracy of quantized models. The main postulate of the work is that final quantization states of the network based on nearest neighbour rounding does not guarantee optimal accuracy. In the presented work, the evolution strategy is used as an optimization approach. The evolution in each iteration changes the values of the small percentage of weights. It shifts theirs values to different quantization states. The work shows that proposed evolution with an appropriate set of operators and parameters can fast improve the accuracy of the quantized models. The results are presented for popular architectures such as VGG and Resnet for image classification and detection. Additionally, simulations were carried out for the autoencoder architecture.
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。