Vertaile menetelmiä

	EfficientNet	MobileNet: Tehokkaat konvoluutionaaliset neuroverkot mobiilinäköön	Siirto-oppiminen
Tieteenala	Syväoppiminen	Syväoppiminen	Koneoppiminen
Menetelmäperhe	Machine learning	Machine learning	Machine learning
Syntyvuosi	2019	2017	2010 (formalized); 1990s (early roots)
Kehittäjä	Tan, M. & Le, Q. V.	Andrew Howard et al. (Google)	Pan, S. J. & Yang, Q. (survey); Bengio, Y. (deep learning framing)
Tyyppi	Compound-scaled convolutional neural network architecture	Lightweight CNN architecture	Learning paradigm
Alkuperäislähde	Tan, M. & Le, Q. V. (2019). EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. Proceedings of the 36th International Conference on Machine Learning (ICML 2019), PMLR 97, 6105–6114.	Howard, A. G., et al. (2017). MobileNets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint.	Pan, S. J., & Yang, Q. (2010). A Survey on Transfer Learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359.
Rinnakkaisnimet	EfficientNet, compound scaling CNN, EfficientNet-B0 through B7, EfficientNetV2	MobileNets, Depthwise Separable CNN, Efficient Mobile Vision Network, Mobil Evrişimli Sinir Ağı	TL, domain adaptation, fine-tuning, pre-trained model adaptation
Liittyvät	4	2	3
Tiivistelmä	EfficientNet is a family of convolutional neural network architectures introduced by Mingxing Tan and Quoc V. Le (Google Brain) at ICML 2019 that systematically co-scales network depth, width, and input resolution using a single compound coefficient, achieving state-of-the-art image classification accuracy with substantially fewer parameters and FLOPs than prior networks such as ResNet and Inception.	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.	Transfer learning is a machine learning paradigm in which knowledge gained from training a model on a source task or domain is reused to improve learning on a different but related target task or domain. It is especially powerful when labeled data for the target task is scarce, and it underlies most modern deep learning applications in computer vision, natural language processing, and beyond.