深度学习 – 归纳轻量级神经网络（长期更新）

SqueezeNet

论文标题：SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and< 0.5 MB model size

论文：

Iandola F N, Han S, Moskewicz M W, et al. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and< 0.5 MB model size[J]. arXiv preprint arXiv:1602.07360, 2016.

论文链接：https://arxiv.org/pdf/1602.07360.pdf

ShuffleNet

ShuffleNet V1

论文标题：Shufflenet: An extremely efficient convolutional neural network for mobile devices

论文：

Zhang X, Zhou X, Lin M, et al. Shufflenet: An extremely efficient convolutional neural network for mobile devices[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 6848-6856.

论文链接：http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhang_ShuffleNet_An_Extremely_CVPR_2018_paper.pdf

ShuffleNet V2

论文标题：Shufflenet v2: Practical guidelines for efficient cnn architecture design

论文：

Ma N, Zhang X, Zheng H T, et al. Shufflenet v2: Practical guidelines for efficient cnn architecture design[C]//Proceedings of the European conference on computer vision (ECCV). 2018: 116-131.

论文链接：https://openaccess.thecvf.com/content_ECCV_2018/papers/Ningning_Light-weight_CNN_Architecture_ECCV_2018_paper.pdf

MobileNet

MobileNet系列详解可参考：https://blog.51cto.com/u_15671528/5528810

MobileNet V1

论文标题：Efficient convolutional neural networks for mobile vision applications

论文：

Howard A G, Zhu M, Chen B, et al. Mobilenets: Efficient convolutional neural networks for mobile vision applications[J]. arXiv preprint arXiv:1704.04861, 2017.

论文链接：https://arxiv.org/pdf/1704.04861.pdf

MobileNet V2

论文标题：Mobilenetv2: Inverted residuals and linear bottlenecks

论文：

Sandler M, Howard A, Zhu M, et al. Mobilenetv2: Inverted residuals and linear bottlenecks[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 4510-4520.

论文链接：https://openaccess.thecvf.com/content_cvpr_2018/papers/Sandler_MobileNetV2_Inverted_Residuals_CVPR_2018_paper.pdf

MobileNet V3

论文标题：Searching for mobilenetv3

论文：

Howard A, Sandler M, Chu G, et al. Searching for mobilenetv3[C]//Proceedings of the IEEE/CVF international conference on computer vision. 2019: 1314-1324.

论文链接：http://openaccess.thecvf.com/content_ICCV_2019/papers/Howard_Searching_for_MobileNetV3_ICCV_2019_paper.pdf

Xception

论文标题：Xception: Deep learning with depthwise separable convolutions

论文：

Chollet F. Xception: Deep learning with depthwise separable convolutions[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 1251-1258.

论文链接：https://openaccess.thecvf.com/content_cvpr_2017/papers/Chollet_Xception_Deep_Learning_CVPR_2017_paper.pdf

EfficientNet

论文标题：Efficientnet: Rethinking model scaling for convolutional neural networks

论文：

Tan M, Le Q. Efficientnet: Rethinking model scaling for convolutional neural networks[C]//International conference on machine learning. PMLR, 2019: 6105-6114.

论文链接：http://proceedings.mlr.press/v97/tan19a/tan19a.pdf

GhostNet

论文标题：Ghostnet: More features from cheap operations

论文：

Han K, Wang Y, Tian Q, et al. Ghostnet: More features from cheap operations[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2020: 1580-1589.

论文链接：https://openaccess.thecvf.com/content_CVPR_2020/papers/Han_GhostNet_More_Features_From_Cheap_Operations_CVPR_2020_paper.pdf

RegNet

论文标题：Designing network design spaces

论文：

Radosavovic I, Kosaraju R P, Girshick R, et al. Designing network design spaces[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2020: 10428-10436.

论文链接：https://openaccess.thecvf.com/content_CVPR_2020/papers/Radosavovic_Designing_Network_Design_Spaces_CVPR_2020_paper.pdf

MobileViT

MobileViT V1

论文标题：Mobilevit: light-weight, general-purpose, and mobile-friendly vision transformer

论文：

Mehta S, Rastegari M. Mobilevit: light-weight, general-purpose, and mobile-friendly vision transformer[J]. arXiv preprint arXiv:2110.02178, 2021.

论文链接：https://arxiv.org/pdf/2110.02178.pdf

MobileViT V2

论文标题：Separable self-attention for mobile vision transformers

论文：

Mehta S, Rastegari M. Separable self-attention for mobile vision transformers[J]. arXiv preprint arXiv:2206.02680, 2022.

论文链接：https://arxiv.org/pdf/2206.02680.pdf

MobileViT V3

论文标题：Mobilevitv3: Mobile-friendly vision transformer with simple and effective fusion of local, global and input features

论文：

Wadekar S N, Chaurasia A. Mobilevitv3: Mobile-friendly vision transformer with simple and effective fusion of local, global and input features[J]. arXiv preprint arXiv:2209.15159, 2022.

论文链接：https://arxiv.org/pdf/2209.15159.pdf

参考链接

• https://www.zhihu.com/people/ren-jun-da/posts