深度网络的训练难易，不取决于层数多少，而在于结构设计是否合理。
The Effective Depth Paradox: Evaluating the Relationship between Architectural Topology and Trainability in Deep CNNs
- 用有效深度衡量实际信息传递能力，比名义层数更准确
- 带跳跃连接或分支结构的网络能保持梯度稳定
- 适合研究模型可扩展性与训练优化的工程师
本文通过对比VGG、ResNet和GoogLeNet三类卷积神经网络架构，探究网络拓扑与图像识别性能的关系。采用统一实验框架，剥离实现细节干扰，明确区分名义深度（$D_{\mathrm{nom}}$，即物理层数）与有效深度（$D_{\mathrm{eff}}$，即实际序列变换次数）。实验证明，使用恒等跳跃连接或分支模块的架构能通过解耦$D_{\mathrm{eff}}$与$D_{\mathrm{nom}}$，维持优化稳定性。结果表明，有效深度是预测模型可扩展性和实际可训练性的更优指标，揭示了网络拓扑结构而非单纯层数，才是决定深层模型梯度健康性的关键因素。
原文摘要 · Abstract (English)
This paper investigates the relationship between convolutional neural network (CNN) topology and image recognition performance through a comparative study of the VGG, ResNet, and GoogLeNet architectural families. Utilizing a unified experimental framework, the study isolates the impact of depth from confounding implementation variables. A formal distinction is introduced between nominal depth ($D_{\mathrm{nom}}$), representing the physical layer count, and effective depth ($D_{\mathrm{eff}}$), an operational metric quantifying the expected number of sequential transformations. Empirical results demonstrate that architectures utilizing identity shortcuts or branching modules maintain optimization stability by decoupling $D_{\mathrm{eff}}$ from $D_{\mathrm{nom}}$. These findings suggest that effective depth serves as a superior framework for predicting scaling potential and practical trainability, ultimately indicating that architectural topology - rather than sheer layer volume - is the primary determinant of gradient health in deep learning models.
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。