Vertaile menetelmiä

	DenseNet	MobileNet: Tehokkaat konvoluutionaaliset neuroverkot mobiilinäköön
Tieteenala	Syväoppiminen	Syväoppiminen
Menetelmäperhe	Machine learning	Machine learning
Syntyvuosi	2017	2017
Kehittäjä	Huang, G.; Liu, Z.; van der Maaten, L.; Weinberger, K. Q.	Andrew Howard et al. (Google)
Tyyppi	Dense convolutional neural network (feed-forward dense connectivity)	Lightweight CNN architecture
Alkuperäislähde	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.
Rinnakkaisnimet	DenseNet, Dense Convolutional Network, densely connected CNN, DenseNet-121	MobileNets, Depthwise Separable CNN, Efficient Mobile Vision Network, Mobil Evrişimli Sinir Ağı
Liittyvät	2	2
Tiivistelmä	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.