Scaling Up Your Kernels to 31×31: Revisiting Large Kernel Design in CNNs

We revisit large kernel design in modern convolutional neural networks (CNNs). Our study further reveals that, in contrast to small-kernel CNNs, large-kernel CNNs have much larger effective receptive fields and higher shape bias rather than texture bias.

⚡ This is an original paraphrased summary — not copied from the abstract. Full paper available at the source link below.

• 1 Inspired by recent advances in vision transformers (ViTs), in this paper, we demonstrate that using a few large convolutional kernels instead of a stack of small kernels could be a more powerful paradigm.
• 2 We suggested five guidelines, e.g., applying re-parameterized large depthwise convolutions, to design efficient high-performance large-kernel CNNs.
• 3 Following the guidelines, we propose RepLKNet, a pure CNN architecture whose kernel size is as large as 31×31, in contrast to commonly used 3×3.

This research advances how AI systems learn, reason, and solve problems — with direct implications for automation and scientific discovery.

This summary is based on publicly available metadata and abstract. For the full research paper, visit the original source: