轻量版ConvNeXt通过跨阶段连接提升效率，兼顾精度与速度。
E-ConvNeXt: A Lightweight and Efficient ConvNeXt Variant with Cross-Stage Partial Connections
- 引入跨阶段部分连接机制，重构网络结构降低复杂度。
- 在0.9GFLOPs下达78.3%准确率，3.1GFLOPs下达81.9%。
- 适合移动端、边缘设备等资源受限场景部署。
许多高性能网络未从设计之初考虑轻量化应用，限制了其使用范围。本文以ConvNeXt为研究对象，通过融合跨阶段部分连接（CSPNet）机制与一系列优化设计，显著降低模型参数规模与网络复杂度，提出新型轻量网络E-ConvNeXt，可在不同复杂度配置下保持高精度。核心创新包括：(1) 将CSPNet与ConvNeXt结合并调整结构，使网络复杂度最高降低80%；(2) 优化Stem与Block结构，提升特征表达能力与运行效率；(3) 用通道注意力替代层尺度。ImageNet分类实验表明，E-ConvNeXt-mini在0.9GFLOPs下达到78.3% Top-1准确率，E-ConvNeXt-small在3.1GFLOPs下达到81.9% Top-1准确率。目标检测任务的迁移学习测试进一步验证其泛化能力。
原文摘要 · Abstract (English)
Many high-performance networks were not designed with lightweight application scenarios in mind from the outset, which has greatly restricted their scope of application. This paper takes ConvNeXt as the research object and significantly reduces the parameter scale and network complexity of ConvNeXt by integrating the Cross Stage Partial Connections mechanism and a series of optimized designs. The new network is named E-ConvNeXt, which can maintain high accuracy performance under different complexity configurations. The three core innovations of E-ConvNeXt are : (1) integrating the Cross Stage Partial Network (CSPNet) with ConvNeXt and adjusting the network structure, which reduces the model's network complexity by up to 80%; (2) Optimizing the Stem and Block structures to enhance the model's feature expression capability and operational efficiency; (3) Replacing Layer Scale with channel attention. Experimental validation on ImageNet classification demonstrates E-ConvNeXt's superior accuracy-efficiency balance: E-ConvNeXt-mini reaches 78.3% Top-1 accuracy at 0.9GFLOPs. E-ConvNeXt-small reaches 81.9% Top-1 accuracy at 3.1GFLOPs. Transfer learning tests on object detection tasks further confirm its generalization capability.
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。