השוואת שיטות

	VGGNet (רשתות קונבולוציה עמוקות מאוד)	MobileNet: רשתות קונבולוציה יעילות למחשוב ראייה נייד
תחום	למידה עמוקה	למידה עמוקה
משפחה	Machine learning	Machine learning
שנת המקור	2014	2017
הוגה השיטה	Simonyan, K. & Zisserman, A. (Visual Geometry Group, Oxford)	Andrew Howard et al. (Google)
סוג	Deep Convolutional Neural Network (image classification)	Lightweight CNN architecture
מקור מכונן	Simonyan, K., & Zisserman, A. (2014). Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv:1409.1556 [cs.CV]. Published at ICLR 2015.	Howard, A. G., et al. (2017). MobileNets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint.
כינויים	VGG, VGG-16, VGG-19, Very Deep ConvNet	MobileNets, Depthwise Separable CNN, Efficient Mobile Vision Network, Mobil Evrişimli Sinir Ağı
קשורות	4	2
תקציר	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.	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.