RepNeXt：使用结构重参数化的快速多尺度卷积神经网络
RepNeXt: A Fast Multi-Scale CNN using Structural Reparameterization
AI总结：
针对资源受限移动视觉任务，提出RepNeXt模型系列，融合多尺度特征与串并行结构重参数化，在保持低延迟的同时提升精度，在ImageNet和MS-COCO上超越现有轻量级CNN和ViT。
摘要：
在资源受限的移动视觉任务领域，对效率和性能的追求持续推动轻量级卷积神经网络（CNN）和视觉变换器（ViT）的创新。虽然ViT通过自注意力机制擅长捕获全局上下文，但其在资源有限环境中的部署受到计算复杂性和延迟的阻碍。相反，轻量级CNN因其参数效率和低延迟而受到青睐。本研究探讨了CNN和ViT的互补优势，以开发一种适用于资源受限应用的多功能视觉骨干网络。我们引入了RepNeXt，这是一个新颖的模型系列，它集成了多尺度特征表示，并结合了串行和并行结构重参数化（SRP），以增强网络深度和宽度而不牺牲推理速度。大量实验表明，RepNeXt优于当前领先的轻量级CNN和ViT，在各种视觉基准上提供了有利的延迟。RepNeXt-M4在iPhone 12上以1.5毫秒内匹配了RepViT-M1.5在ImageNet上的82.3%准确率，在MS-COCO上其AP$^{box}$超出1.3，并减少了0.7M参数。代码和模型可在https://github.com/suous/RepNeXt获取。
英文摘要：
In the realm of resource-constrained mobile vision tasks, the pursuit of efficiency and performance consistently drives innovation in lightweight Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs). While ViTs excel at capturing global context through self-attention mechanisms, their deployment in resource-limited environments is hindered by computational complexity and latency. Conversely, lightweight CNNs are favored for their parameter efficiency and low latency. This study investigates the complementary advantages of CNNs and ViTs to develop a versatile vision backbone tailored for resource-constrained applications. We introduce RepNeXt, a novel model series integrates multi-scale feature representations and incorporates both serial and parallel structural reparameterization (SRP) to enhance network depth and width without compromising inference speed. Extensive experiments demonstrate RepNeXt's superiority over current leading lightweight CNNs and ViTs, providing advantageous latency across various vision benchmarks. RepNeXt-M4 matches RepViT-M1.5's 82.3\% accuracy on ImageNet within 1.5ms on an iPhone 12, outperforms its AP$^{box}$ by 1.3 on MS-COCO, and reduces parameters by 0.7M. Codes and models are available at https://github.com/suous/RepNeXt.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
