Concept icon
Concept

Empirical Performance of Identity vs. Projection Shortcuts

Evaluation on ImageNet demonstrates that all three shortcut variants (A, B, and C) considerably outperform the 34-layer plain baseline (28.54% top-1 validation error). Specifically, ResNet-34 Option A attains 25.03% top-1 error, Option B achieves 24.52%, and Option C achieves 24.19%.

Option B performs slightly better than Option A because the zero-padded dimensions in Option A do not participate in residual learning. Option C is marginally better than Option B, which is attributed to the extra parameters introduced by thirteen projection shortcuts.

Because the performance differences among Options A, B, and C are small, projection shortcuts are shown to be non-essential for addressing the network degradation problem. To prevent unnecessary memory overhead, computational time complexity, and model size growth, Option C is rejected for deeper architectures.

0

1

Concept icon
Updated 2026-09-07

Tags

Prep Sessions

Foundational Deep Learning Architectures: Transformers and Residual Networks @ University of Michigan - Ann Arbor

Ch.3 Deep Residual Network Architecture - Foundational Deep Learning Architectures: Transformers and Residual Networks @ University of Michigan - Ann Arbor

Identity versus Projection Shortcuts - Foundational Deep Learning Architectures: Transformers and Residual Networks @ University of Michigan - Ann Arbor