The Effective Depth Paradox: Evaluating the Relationship between Architectural Topology and Trainability in Deep CNNs

arXiv:2602.13298v3 Announce Type: replace-cross Abstract: 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_{nom}), representing the physical layer count, and effective depth (D_{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_{eff} from D_{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.

Source: arXiv cs.AI | 2026-05-11