Concept icon
Concept

Deep ResNet Scaling with Bottleneck Blocks

Bottleneck blocks enable the construction of substantially deeper networks, specifically 50-layer, 101-layer, and 152-layer ResNets:

  • ResNet-50: Created by replacing each 2-layer block of the 34-layer network with the 3-layer bottleneck block, utilizing projection shortcuts (Option B) for increasing dimensions and requiring 3.8×1093.8\times 10^9 FLOPs.
  • ResNet-101 and ResNet-152: Built by stacking significantly more 3-layer blocks, particularly across feature maps of size 14×1414\times 14 and 28×2828\times 28.

Even with 152 layers, ResNet-152 requires 11.3×10911.3\times 10^9 FLOPs, maintaining lower computational complexity than VGG-16 (15.3×10915.3\times 10^9 FLOPs) and VGG-19 (19.6×10919.6\times 10^9 FLOPs). Across these configurations, the networks show no degradation problem and yield substantial accuracy improvements as depth increases.

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

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

Ch.4 Residual Network Experiments and Applications - Foundational Deep Learning Architectures: Transformers and Residual Networks @ University of Michigan - Ann Arbor

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