Research map / Architectures and efficiency / CNN design
Brain-inspired $L_p$-Convolution benefits large kernels and aligns better with visual cortex
Jea Kwon, Sungjun Lim, Kyungwoo Song, C. Justin Lee
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes Lp-Convolution, a brain-inspired convolution whose kernel connectivity is shaped by a multivariate p-generalized normal distribution, to help large-kernel CNNs and improve alignment with visual cortex representations.
Problem
Differences in local connectivity between CNNs and the biological visual system; how to make CNN convolutions brain-like so that large kernels work well and representations align better with visual cortex.
Approach
Replace standard convolution kernels with Lp-Convolution, where the kernel weights are constrained by a multivariate p-generalized normal distribution whose p value controls the shape of the receptive field (from square-like to Gaussian-like local connectivity), enabling large kernels that align with biological receptive fields.
Experimental setup
Builds on: convolutional neural networks large kernel CNNs
Closest papers by meaning
- Convolution Goes Higher-Order: A Biologically Inspired Mechanism Empowers Image Classification (NeurIPS 2025 · similarity 0.89)
- Surround Modulation: A Bio-inspired Connectivity Structure for Convolutional Neural Networks (NeurIPS 2019 · similarity 0.87)
- Non-Linear Convolution Filters for CNN-Based Learning (ICCV 2017 · similarity 0.87)
- Bridging Critical Gaps in Convergent Learning: How Representational Alignment Evolves Across Layers, Training, and Distribution Shifts (NeurIPS 2025 · similarity 0.85)
- Explicitly Modeling Subcortical Vision with a Neuro-Inspired Front-End Improves CNN Robustness (NeurIPS 2025 · similarity 0.85)
- Unveiling the Unseen: Identifiable Clusters in Trained Depthwise Convolutional Kernels (ICLR 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
