Brief · Saturday, Sep 12, 2026 · Day 43

Deep Residual Learning for Image Recognition

AI research · He, Zhang, Ren, Sun · 2015 · CVPR 2016 · 35 min · Moderate
Summary

Plain networks got worse as they got deeper, not from overfitting but from optimisation difficulty. Residual connections let each block learn a correction to its input instead of a whole new mapping, and suddenly networks with over a hundred layers trained cleanly.

Key ideas
  • Degradation with depth is an optimisation problem, not a capacity problem
  • Identity shortcuts add no parameters and almost no compute
  • Bottleneck blocks make very deep networks affordable
Why read it now

The skip connection is the single most reused architectural idea in the field. Transformers, diffusion U-Nets, and modern vision models all depend on it.

Question to keep in mind

What does a residual block learn when the best thing it can do is nothing?

124 online