论文标题
repghost：通过重新参数化的硬件有效的幽灵模块
RepGhost: A Hardware-Efficient Ghost Module via Re-parameterization
论文作者
论文摘要
功能再利用一直是轻质卷积神经网络（CNNS）体系结构设计中的关键技术。当前的方法通常利用串联操作员通过重复其他层的特征图来廉价地保持大型通道数（从而大大网络容量）。尽管串联是无参数和拖放的，但其硬件设备上的计算成本是不可忽略的。为了解决这个问题，本文提供了一种新的观点，可以隐含，更有效地实现功能重复使用而不是串联。提出了一种新型的硬件效率repghost模块，以通过重新聚体化而不是使用串联操作员来重复使用。根据Repghost模块，我们开发了高效的Repghost瓶颈和Repghostnet。 ImageNet和Coco基准测试的实验表明，与移动设备上的ghostnet和Mobilenetv3相比，我们的repghostnet更加有效。特别是，我们的repghostnet超过了Ghostnet 0.5倍，在Imagenet数据集上具有较少参数和基于ARM的移动设备的可比延迟的ImageNet数据集上的2.5％Top-1精度。代码和模型权重可在https://github.com/chengpengchen/repghost上找到。
Feature reuse has been a key technique in light-weight convolutional neural networks (CNNs) architecture design. Current methods usually utilize a concatenation operator to keep large channel numbers cheaply (thus large network capacity) by reusing feature maps from other layers. Although concatenation is parameters- and FLOPs-free, its computational cost on hardware devices is non-negligible. To address this, this paper provides a new perspective to realize feature reuse implicitly and more efficiently instead of concatenation. A novel hardware-efficient RepGhost module is proposed for implicit feature reuse via reparameterization, instead of using concatenation operator. Based on the RepGhost module, we develop our efficient RepGhost bottleneck and RepGhostNet. Experiments on ImageNet and COCO benchmarks demonstrate that our RepGhostNet is much more effective and efficient than GhostNet and MobileNetV3 on mobile devices. Specially, our RepGhostNet surpasses GhostNet 0.5x by 2.5% Top-1 accuracy on ImageNet dataset with less parameters and comparable latency on an ARM-based mobile device. Code and model weights are available at https://github.com/ChengpengChen/RepGhost.
