Usporedite metode

	VGGNet (Very Deep Convolutional Networks)	DenseNet	MobileNet: Učinkoviti konvolucijski neuralni mreže za mobilnu viziju
Područje	Duboko učenje	Duboko učenje	Duboko učenje
Obitelj	Machine learning	Machine learning	Machine learning
Godina nastanka	2014	2017	2017
Tvorac	Simonyan, K. & Zisserman, A. (Visual Geometry Group, Oxford)	Huang, G.; Liu, Z.; van der Maaten, L.; Weinberger, K. Q.	Andrew Howard et al. (Google)
Vrsta	Deep Convolutional Neural Network (image classification)	Dense convolutional neural network (feed-forward dense connectivity)	Lightweight CNN architecture
Temeljni izvor	Simonyan, K., & Zisserman, A. (2014). Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv:1409.1556 [cs.CV]. Published at ICLR 2015.	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.
Drugi nazivi	VGG, VGG-16, VGG-19, Very Deep ConvNet	DenseNet, Dense Convolutional Network, densely connected CNN, DenseNet-121	MobileNets, Depthwise Separable CNN, Efficient Mobile Vision Network, Mobil Evrişimli Sinir Ağı
Srodne	4	2	2
Sažetak	VGGNet is a deep convolutional neural network architecture introduced by Karen Simonyan and Andrew Zisserman at the Visual Geometry Group, Oxford, in 2014 (published at ICLR 2015). It demonstrated that network depth — achieved exclusively through stacking small 3x3 convolutional filters — is the single most critical factor for high image-classification accuracy, and its two canonical variants (VGG-16 and VGG-19) became the dominant benchmark architectures for CNN design throughout the mid-2010s.	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.