PP-LCNet: A Lightweight CPU Convolutional Neural Network

Cheng Cui, Tingquan Gao, Shengyu Wei, Yuning Du, Ruoyu Guo +8 more
9/17/2021
cs.CV

Official code: PaddlePaddle/PaddleClas (5,851 stars, Apache-2.0, last commit 2026-10-13).

Abstract

We propose a lightweight CPU network based on the MKLDNN acceleration strategy, named PP-LCNet, which improves the performance of lightweight models on multiple tasks. This paper lists technologies which can improve network accuracy while the latency is almost constant. With these improvements, the accuracy of PP-LCNet can greatly surpass the previous network structure with the same inference time for classification. As shown in Figure 1, it outperforms the most state-of-the-art models. And for downstream tasks of computer vision, it also performs very well, such as object detection, semantic segmentation, etc. All our experiments are implemented based on PaddlePaddle. Code and pretrained models are available at PaddleClas.

View on arXivView PDF

Code Implementations(1)

PaddlePaddle/PaddleClasOfficial100%
Apache-2.0

A treasure chest for visual classification and recognition powered by PaddlePaddle

5,8511,192C, C#Mar 30, 20201 weeks agoApache-2.0
autoaugmentcutmixdeitfastdeploygridmask+9 more

Similar Papers

A lightweight model FDM-YOLO for small target improvement based on YOLOv8

87% match2025

HarDNet: A Low Memory Traffic Network

86% match1 repo3742019

A Low-cost and Ultra-lightweight Binary Neural Network for Traffic Signal Recognition

86% match2025

PP-PicoDet: A Better Real-Time Object Detector on Mobile Devices

86% match1 repo14.3k2021

RepNeXt: A Fast Multi-Scale CNN using Structural Reparameterization

86% match1 repo502024

Sebica: Lightweight Spatial and Efficient Bidirectional Channel Attention Super Resolution Network

85% match1 repo142024

Cite this paper

@article{cui2021pplcnet,
  title  = {PP-LCNet: A Lightweight CPU Convolutional Neural Network},
  author = {Cheng Cui and Tingquan Gao and Shengyu Wei and Yuning Du and Ruoyu Guo and Shuilong Dong and Bin Lu and Ying Zhou and Xueying Lv and Qiwen Liu and Xiaoguang Hu and Dianhai Yu and Yanjun Ma},
  year   = {2021},
  eprint = {2109.15099},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/2109.15099}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2109.15099.svg)](https://codeofpaper.com/paper/2109.15099)

Discussion