Deploying Convolutional Neural Network (CNN) models on ubiquitous Internet of Things (IoT) devices in a cloud-assisted manner to provide users with a variety of high-quality services has become mainstream. Most existing studies speed up model cloud training/on-device inference by reducing the number of convolution (Conv) parameters and floating-point operations (FLOPs). However, they usually employ two or more lightweight operations (e.g., depthwise Conv, $1\times1$ cheap Conv) to replace a Conv, which can still affect the model's speedup even with fewer parameters and FLOPs. To this end, we propose the Grouped NonLinear transformation generation method (GroupNL), leveraging data-agnostic, hyperparameters-fixed, and lightweight Nonlinear Transformation Functions (NLFs) to generate diversified feature maps on demand via grouping, thereby reducing resource consumption while improving the robustness of CNNs. First, in a GroupNL Conv layer, a small set of feature maps, i.e., seed feature maps, are generated based on the seed Conv operation. Then, we split seed feature maps into several groups, each with a set of different NLFs, to generate the required number of diversified feature maps with tensor manipulation operators and nonlinear processing in a lightweight manner without additional Conv operations. We further introduce a sparse GroupNL Conv to speed up by reasonably designing the seed Conv groups between the number of input channels and seed feature maps. Experiments conducted on benchmarks and on-device resource measurements demonstrate that the GroupNL Conv is an impressive alternative to Conv layers in baseline models. Specifically, on Icons-50 dataset, the accuracy of GroupNL-ResNet-18 is 2.86% higher than ResNet-18; on ImageNet-C dataset, the accuracy of GroupNL-EfficientNet-ES achieves about 1.1% higher than EfficientNet-ES.

翻译：以云辅助方式在泛在物联网设备上部署卷积神经网络模型，为用户提供多样化高质量服务已成为主流范式。现有研究大多通过减少卷积参数量和浮点运算量来加速模型的云端训练与设备端推理。然而，这些方法通常采用两个及以上轻量级操作替代标准卷积，即使参数量和运算量降低，仍可能影响实际加速效果。为此，我们提出分组非线性变换生成方法，通过数据无关、超参数固定的轻量级非线性变换函数，借助分组机制按需生成多样化特征图，在降低资源消耗的同时提升CNN的鲁棒性。首先，在GroupNL卷积层中，基于种子卷积操作生成少量特征图作为种子特征图；随后将种子特征图划分为若干组，每组配备不同的非线性变换函数集合，通过张量操作算子和非线性处理以轻量化方式生成所需数量的多样化特征图，无需额外卷积操作。我们进一步提出稀疏GroupNL卷积，通过在输入通道数与种子特征图之间合理设计种子卷积分组以提升速度。基准测试与设备端资源测量实验表明，GroupNL卷积可作为基线模型中标准卷积层的优异替代方案。具体而言，在Icons-50数据集上，GroupNL-ResNet-18的准确率较ResNet-18提升2.86%；在ImageNet-C数据集上，GroupNL-EfficientNet-ES的准确率较EfficientNet-ES提升约1.1%。