提出适用于微型设备的高效混合卷积与视觉变换器搜索空间
Hybrid Convolution and Vision Transformer NAS Search Space for TinyML Image Classification
- 设计可搜索的混合卷积与视觉变换器模块及新型池化层
- 在CIFAR10上实现比ResNet更优的精度与推理速度
- 适合资源受限的嵌入式图像分类任务
卷积神经网络（CNN）与视觉变换器（ViT）的混合架构已超越纯CNN或纯ViT模型。然而，这些架构参数量大、计算成本高，难以部署于微型机器学习（tinyML）场景。本文提出一种面向神经架构搜索（NAS）的新混合CNN-ViT搜索空间，用于发现适用于图像分类的高效混合架构。该搜索空间包含可学习局部与全局信息的混合CNN和ViT模块，以及一种新型可搜索池化层，用于高效特征图降维。在CIFAR10数据集上的实验表明，在严格模型尺寸约束下，所提搜索空间生成的混合架构在精度和推理速度上均优于基于ResNet的tinyML模型。
原文摘要 · Abstract (English)
Hybrids of Convolutional Neural Network (CNN) and Vision Transformer (ViT) have outperformed pure CNN or ViT architecture. However, since these architectures require large parameters and incur large computational costs, they are unsuitable for tinyML deployment. This paper introduces a new hybrid CNN-ViT search space for Neural Architecture Search (NAS) to find efficient hybrid architectures for image classification. The search space covers hybrid CNN and ViT blocks to learn local and global information, as well as the novel Pooling block of searchable pooling layers for efficient feature map reduction. Experimental results on the CIFAR10 dataset show that our proposed search space can produce hybrid CNN-ViT architectures with superior accuracy and inference speed to ResNet-based tinyML models under tight model size constraints.
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。