---
title: "群共享低秩近似：实现大核CNN在移动端的轻量级逐点卷积"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2608.26069v1"
permalink: "https://feed.astralor.com/items/itm_8b027dc0bc37a8eab8f839c3"
published: "2026-08-26T17:36:35.000Z"
score: 72
channel: "tech"
tags: ["ConvNeXt","RepLKNet","SLaK","低秩近似","参数共享","边缘部署"]
---

# 群共享低秩近似：实现大核CNN在移动端的轻量级逐点卷积

## AI 点评

> 这篇论文的洞察很关键——大家忙着压深度卷积时，逐点卷积才是真正的'重量级'。对做端侧模型部署的工程师来说，CGS的群共享思路简单有效，值得在自家模型上试一试。

## 速览

大型卷积核CNN在视觉任务上表现优异，但其参数随核尺寸二次增长，严重阻碍边缘端部署。现有高效架构聚焦于深度可分离卷积中的深度卷积压缩，却忽视了逐点卷积占据参数量超过87%的事实。本文提出基于SVD的通道群共享低秩近似策略，通过跨群共享上下投影矩阵、保留群特有对角缩放矩阵，大幅压缩参数量，在不显著损失性能的前提下降低存储和内存带宽压力，使RepLKNet、ConvNeXt、SLaK等大核CNN可在智能手机等资源受限设备上部署。

## 关键点

- 指出大核CNN中逐点卷积占参数量的87%以上，是边缘部署的主要瓶颈
- 提出通道群共享低秩近似，结构化模拟SVD分解，跨群共享投影矩阵
- 在RepLKNet、ConvNeXt、SLaK上验证了性能与存储成本的平衡

## 全文

Large-kernel Convolutional Neural Networks (CNNs) deliver remarkable performance in vision tasks by significantly expanding receptive fields, yet their quadratic parameter growth critically impedes storage-efficient edge deployment. While existing efficient architectures adopt parameter-efficient depthwise separable convolution backbones that leverage techniques like low-rank approximation and weight sharing to compress depthwise convolutions, we identify a critical oversight: pointwise convolutions dominate parameter volume (>87% in models like RepLKNet-31B) and constitute the primary deployment bottleneck on resource-constrained edge devices. This results in prohibitive storage costs and severe memory-loading constraints on resource-limited devices (e.g., smartphones with 4-12 GB Random Access Memory (RAM)). To overcome this, we propose Channel Group-Shared (CGS) low-rank approximation, a novel Singular Value Decomposition (SVD)-based parameter-sharing strategy. CGS constructs a structured low-rank paradigm isomorphic to SVD decomposition, comprising shared (high-parameter-cost) down/up-projection matrices across channel groups within a layer and channel-group-specific (low-parameter-cost) scalable diagonal matrices. This group-sharing design achieves significant parameter reduction. Extensive experiments demonstrate that large-kernel CNNs (RepLKNet, ConvNeXt, SLaK) enhanced with CGS strike an empirically favorable balance between competitive performance and substantially reduced storage costs. Crucially, by alleviating storage constraints, reducing memory bandwidth pressure during loading, and minimizing model loading latency, CGS enables the feasible deployment of pre-trained large-kernel CNN models on edge devices, thereby bridging the gap between high-performance vision models and practical edge deployment.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_8b027dc0bc37a8eab8f839c3