mlsanityData to 7 Oct 2026

GhostNet: More Features from Cheap Operations

arXiv 1911.11907 ↗First posted 27 Nov 2019cs.CVcited by 410

Not on the map. Why?

Abstract (arXiv)

Deploying convolutional neural networks (CNNs) on embedded devices is difficult due to the limited memory and computation resources. The redundancy in feature maps is an important characteristic of those successful CNNs, but has rarely been investigated in neural architecture design. This paper proposes a novel Ghost module to generate more feature maps from cheap operations. Based on a set of intrinsic feature maps, we apply a series of linear transformations with cheap cost to generate many ghost feature maps that could fully reveal information underlying intrinsic features. The proposed Ghost module can be taken as a plug-and-play component to upgrade existing convolutional neural networks. Ghost bottlenecks are designed to stack Ghost modules, and then the lightweight GhostNet can be easily established. Experiments conducted on benchmarks demonstrate that the proposed Ghost module is an impressive alternative of convolution layers in baseline models, and our GhostNet can achieve higher recognition performance (e.g. 75.7% top-1 accuracy) than MobileNetV3 with similar computational cost on the ImageNet ILSVRC-2012 classification dataset. Code is available at https://github.com/huawei-noah/ghostnet

Key facts. Cited by 410 papers in the map (data through 7 Oct 2026). First posted on arXiv 27 Nov 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 77; 2022: 81; 2023: 66; 2024: 76; 2025: 72; 2026: 38.

410 papers.

Sort:

By area:

  1. 2021Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNetcited by 1,096
  2. 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 978
  3. 2021Transformer in Transformercited by 632
  4. 2021Towards Real-World Blind Face Restoration with Generative Facial Priorcited by 347
  5. 2021CMT: Convolutional Neural Networks Meet Vision Transformerscited by 310
  6. 2021Mobile-Former: Bridging MobileNet and Transformercited by 234
  7. 2023EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attentioncited by 172
  8. 2024EfficientVMamba: Atrous Selective Scan for Light Weight Visual Mambacited by 146
  9. 2023Run, Don't Walk: Chasing Higher FLOPS for Faster Neural Networkscited by 129
  10. 2021Rethinking BiSeNet For Real-time Semantic Segmentationcited by 124
  11. 2021Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformercited by 115
  12. 2022MobileOne: An Improved One millisecond Mobile Backbonecited by 109
38 more
  1. 2021Distilling Object Detectors via Decoupled Featurescited by 105
  2. 2024MobileNetV4 -- Universal Models for the Mobile Ecosystemcited by 98
  3. 2023InceptionNeXt: When Inception Meets ConvNeXtcited by 84
  4. 2022TopFormer: Token Pyramid Transformer for Mobile Semantic Segmentationcited by 82
  5. 2023One-for-All: Bridge the Gap Between Heterogeneous Architectures in Knowledge Distillationcited by 77
  6. 2021MobRecon: Mobile-Friendly Hand Mesh Reconstruction from Monocular Imagecited by 74
  7. 2024Wavelet Convolutions for Large Receptive Fieldscited by 74
  8. 2024SHViT: Single-Head Vision Transformer with Memory Efficient Macro Designcited by 55
  9. 2024Rewrite the Starscited by 55
  10. 2022Pro-tuning: Unified Prompt Tuning for Vision Taskscited by 53
  11. 2021ReCU: Reviving the Dead Weights in Binary Neural Networkscited by 51
  12. 2023Gold-YOLO: Efficient Object Detector via Gather-and-Distribute Mechanismcited by 51
  13. 2021FaceX-Zoo: A PyTorch Toolbox for Face Recognitioncited by 49
  14. 2022Improving the Transferability of Targeted Adversarial Examples through Object-Based Diverse Inputcited by 49
  15. 2021AdaFuse: Adaptive Temporal Fusion Network for Efficient Action Recognitioncited by 48
  16. 2022Beyond Attentive Tokens: Incorporating Token Importance and Diversity for Efficient Vision Transformerscited by 47
  17. 2021Combined Depth Space based Architecture Search For Person Re-identificationcited by 44
  18. 2022Exploring Inter-Channel Correlation for Diversity-preserved KnowledgeDistillationcited by 44
  19. 2022GhostNetV2: Enhance Cheap Operation with Long-Range Attentioncited by 44
  20. 2021Manifold Regularized Dynamic Network Pruningcited by 43
  21. 2022EfficientViT: Multi-Scale Linear Attention for High-Resolution Dense Predictioncited by 42
  22. 2023Adaptive Sparse Convolutional Networks with Global Context Enhancement for Faster Object Detection on Drone Imagescited by 41
  23. 2023EdgeSAM: Prompt-In-the-Loop Distillation for SAMcited by 40
  24. 2021Learning Frequency Domain Approximation for Binary Neural Networkscited by 38
  25. 2022AdaBin: Improving Binary Neural Networks with Adaptive Binary Setscited by 38
  26. 2022Visual Attention Methods in Deep Learning: An In-Depth Surveycited by 37
  27. 2023Rethinking Mobile Block for Efficient Attention-based Modelscited by 36
  28. 2021Revisiting Dynamic Convolution via Matrix Decompositioncited by 35
  29. 2022DUET: A Tuning-Free Device-Cloud Collaborative Parameters Generation Framework for Efficient Device Model Generalizationcited by 35
  30. 2021YOLOStereo3D: A Step Back to 2D for Efficient Stereo 3D Detectioncited by 34
  31. 2021CondenseNet V2: Sparse Feature Reactivation for Deep Networkscited by 34
  32. 2023EdgeFace: Efficient Face Recognition Model for Edge Devicescited by 33
  33. 2021Prioritized Architecture Sampling with Monto-Carlo Tree Searchcited by 32
  34. 2023Focus the Discrepancy: Intra- and Inter-Correlation Learning for Image Anomaly Detectioncited by 32
  35. 2021Dynamic Resolution Networkcited by 31
  36. 2022ParC-Net: Position Aware Circular Convolution with Merits from ConvNets and Transformercited by 28
  37. 2021PP-LCNet: A Lightweight CPU Convolutional Neural Networkcited by 27
  38. 2021Face.evoLVe: A High-Performance Face Recognition Librarycited by 26

50 most cited of 410 All 410 (JSON)