Methods › Computer Vision › Light-weight neural networks › GhostNet

GhostNet

22 papers tagged archive 2025-07-28

Introduced by Kai Han et al. in GhostNet: More Features from Cheap Operations

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

A GhostNet is a type of convolutional neural network that is built using Ghost modules, which aim to generate more features by using fewer parameters (allowing for greater efficiency).

GhostNet mainly consists of a stack of Ghost bottlenecks with the Ghost modules as the building block. The first layer is a standard convolutional layer with 16 filters, then a series of Ghost bottlenecks with gradually increased channels follow. These Ghost bottlenecks are grouped into different stages according to the sizes of their input feature maps. All the Ghost bottlenecks are applied with stride=1 except that the last one in each stage is with stride=2. At last a global average pooling and a convolutional layer are utilized to transform the feature maps to a 1280-dimensional feature vector for final classification. The squeeze and excite (SE) module is also applied to the residual layer in some ghost bottlenecks.

In contrast to MobileNetV3, GhostNet does not use hard-swish nonlinearity function due to its large latency.

PaperSourceSee Code · osmr/imgclsmob

Papers archive 2025-07-28

22 shown of 22, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Tasks archive 2025-07-28

20 shown of 40 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Image Classification8
image-classification5
Object Detection3
GPU2
Segmentation2
Semantic Segmentation2
object-detection2
Acoustic Scene Classification1
Action Recognition1
CPU1
Data Augmentation1
Defect Detection1
Denoising1
Depth Estimation1
EEG1
Emotion Recognition1
Human Detection1
Image Segmentation1
Image Super-Resolution1
Instance Segmentation1

Usage over time archive 2025-07-28

Papers per year tagged with GhostNet: 2019 to 2024, peak 7 7 0 2019: 1 paper 2019 2020: 4 papers 2020 2021: 5 papers 2021 2022: 7 papers 2022 2023: 1 paper 2023 2024: 4 papers 2024
Papers per year the archive tags with this method, by the paper's archive date (22 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Light-weight neural networksConvolutional Neural Networks

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections