方法对比

	ResNeXt	DenseNet	MobileNet：面向移动视觉的高效卷积神经网络
领域	深度学习	深度学习	深度学习
方法族	Machine learning	Machine learning	Machine learning
起源年份	2017	2017	2017
提出者	Xie, S.; Girshick, R.; Dollár, P.; Tu, Z.; He, K.	Huang, G.; Liu, Z.; van der Maaten, L.; Weinberger, K. Q.	Andrew Howard et al. (Google)
类型	Convolutional neural network with grouped/cardinality-based residual blocks	Dense convolutional neural network (feed-forward dense connectivity)	Lightweight CNN architecture
开创性文献	Xie, S., Girshick, R., Dollár, P., Tu, Z., & He, K. (2017). Aggregated Residual Transformations for Deep Neural Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 5987–5995.	Huang, G., Liu, Z., van der Maaten, L., & Weinberger, K. Q. (2017). Densely Connected Convolutional Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 4700–4708.	Howard, A. G., et al. (2017). MobileNets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint.
别名	ResNeXt, Aggregated Residual Transformations, grouped convolution residual network, cardinality-based ResNet	DenseNet, Dense Convolutional Network, densely connected CNN, DenseNet-121	MobileNets, Depthwise Separable CNN, Efficient Mobile Vision Network, Mobil Evrişimli Sinir Ağı
相关	4	2	2
摘要	ResNeXt is a deep convolutional neural network architecture introduced by Xie, Girshick, Dollár, Tu, and He at CVPR 2017. It extends the residual network (ResNet) design by introducing a new architectural dimension called cardinality — the number of independent, parallel transformation paths within each residual block — enabling higher accuracy with fewer parameters and a simpler, more uniform design than its predecessors.	DenseNet (Densely Connected Convolutional Network), introduced by Huang, Liu, van der Maaten, and Weinberger at CVPR 2017 (Best Paper Award), connects every layer to every subsequent layer within a dense block so that each layer receives the concatenated feature maps of all preceding layers — maximising feature reuse, strengthening gradient flow, and achieving competitive accuracy with substantially fewer parameters than comparable architectures such as ResNet.	MobileNet is a family of lightweight convolutional neural network architectures introduced by Howard et al. at Google in 2017. It is designed to run image classification, object detection, and other vision tasks directly on mobile devices and embedded systems with limited computational budgets. By replacing standard convolutions with depthwise separable convolutions and exposing two global hyperparameters, MobileNet dramatically reduces multiply-add operations and model size while retaining competitive accuracy.