# RepGhost: A Hardware-Efficient Ghost Module via Re-parameterization

arXiv: https://arxiv.org/abs/2211.06088 · HTML: https://mlsanity.com/paper/2211.06088/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 41 of its 55 references that are in the map.
- First posted on arXiv 11 Nov 2022.

## Builds on (most cited first, 30 of 41)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices](https://mlsanity.com/paper/1707.01083/) (2017)
- [ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design](https://mlsanity.com/paper/1807.11164/) (2018)
- [Designing Network Design Spaces](https://mlsanity.com/paper/2003.13678/) (2020)
- [MnasNet: Platform-Aware Neural Architecture Search for Mobile](https://mlsanity.com/paper/1807.11626/) (2018)
- [AutoAugment: Learning Augmentation Policies from Data](https://mlsanity.com/paper/1805.09501/) (2018)
- [Channel Pruning for Accelerating Very Deep Neural Networks](https://mlsanity.com/paper/1707.06168/) (2017)
- [RepVGG: Making VGG-style ConvNets Great Again](https://mlsanity.com/paper/2101.03697/) (2021)
- [FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search](https://mlsanity.com/paper/1812.03443/) (2018)
- [Single Path One-Shot Neural Architecture Search with Uniform Sampling](https://mlsanity.com/paper/1904.00420/) (2019)
- [GhostNet: More Features from Cheap Operations](https://mlsanity.com/paper/1911.11907/) (2019)
- [Highway Networks](https://mlsanity.com/paper/1505.00387/) (2015)
- [MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning](https://mlsanity.com/paper/1903.10258/) (2019)
- [ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks](https://mlsanity.com/paper/1908.03930/) (2019)
- [FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions](https://mlsanity.com/paper/2004.05565/) (2020)
- [Structured Pruning of Deep Convolutional Neural Networks](https://mlsanity.com/paper/1512.08571/) (2015)

## Built on by (most cited first, 13 of 13)

- [Breaking the Ceiling of the LLM Community by Treating Token Generation as a Classification for Ensembling](https://mlsanity.com/paper/2406.12585/) (2024)
- [RefConv: Re-parameterized Refocusing Convolution for Powerful ConvNets](https://mlsanity.com/paper/2310.10563/) (2023)
- [Efficient HDR Reconstruction from Real-World Raw Images](https://mlsanity.com/paper/2306.10311/) (2023)
- [MoENAS: Mixture-of-Expert based Neural Architecture Search for jointly Accurate, Fair, and Robust Edge Deep Neural Networks](https://mlsanity.com/paper/2502.07422/) (2025)
- [Towards Fundamentally Scalable Model Selection: Asymptotically Fast Update and Selection](https://mlsanity.com/paper/2406.07536/) (2024)
- [Exploring Superposition and Interference in State-of-the-Art Low-Parameter Vision Models](https://mlsanity.com/paper/2507.15798/) (2025)
- [RepCNN: Micro-sized, Mighty Models for Wakeword Detection](https://mlsanity.com/paper/2406.02652/) (2024)
- [FedRepOpt: Gradient Re-parametrized Optimizers in Federated Learning](https://mlsanity.com/paper/2409.15898/) (2024)
- [Lightweight Design and Optimization methods for DCNNs: Progress and Futures](https://mlsanity.com/paper/2412.16886/) (2024)
- [SugarcaneShuffleNet: A Very Fast, Lightweight Convolutional Neural Network for Diagnosis of 15 Sugarcane Leaf Diseases](https://mlsanity.com/paper/2508.17107/) (2025)
- [ShellfishNet: A Domain-Specific Benchmark for Visual Recognition of Marine Molluscs](https://mlsanity.com/paper/2605.07338/) (2026)
- [AgroVisNet: A lightweight Convolutional Network and the BD-PlantDX Expert-Validated Benchmark for Radish, Potato and Pointed Gourd Disease Classification](https://mlsanity.com/paper/2609.10469/) (2026)
- [RIPE-MambaSpike: Resolution-Independent Spiking-State-Space Interfaces for Parameter-Efficient Event-Based Vision](https://mlsanity.com/paper/2609.32537/) (2026)

## Abstract (arXiv)

Feature reuse has been a key technique in light-weight convolutional neural networks (CNNs) architecture design. Current methods usually utilize a concatenation operator to keep large channel numbers cheaply (thus large network capacity) by reusing feature maps from other layers. Although concatenation is parameters- and FLOPs-free, its computational cost on hardware devices is non-negligible. To address this, this paper provides a new perspective to realize feature reuse implicitly and more efficiently instead of concatenation. A novel hardware-efficient RepGhost module is proposed for implicit feature reuse via reparameterization, instead of using concatenation operator. Based on the RepGhost module, we develop our efficient RepGhost bottleneck and RepGhostNet. Experiments on ImageNet and COCO benchmarks demonstrate that our RepGhostNet is much more effective and efficient than GhostNet and MobileNetV3 on mobile devices. Specially, our RepGhostNet surpasses GhostNet 0.5x by 2.5% Top-1 accuracy on ImageNet dataset with less parameters and comparable latency on an ARM-based mobile device. Code and model weights are available at https://github.com/ChengpengChen/RepGhost.