方法对比

	EfficientNet	神经架构搜索	迁移学习
领域	深度学习	深度学习	机器学习
方法族	Machine learning	Machine learning	Machine learning
起源年份	2019	2017	2010 (formalized); 1990s (early roots)
提出者	Tan, M. & Le, Q. V.	Zoph, B. & Le, Q.V.	Pan, S. J. & Yang, Q. (survey); Bengio, Y. (deep learning framing)
类型	Compound-scaled convolutional neural network architecture	Automated architecture optimization (deep learning)	Learning paradigm
开创性文献	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.	Zoph, B. & Le, Q.V. (2017). Neural Architecture Search with Reinforcement Learning. ICLR.	Pan, S. J., & Yang, Q. (2010). A Survey on Transfer Learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359.
别名	EfficientNet, compound scaling CNN, EfficientNet-B0 through B7, EfficientNetV2	Nöral Mimari Arama (NAS), NAS, automated architecture design, differentiable architecture search	TL, domain adaptation, fine-tuning, pre-trained model adaptation
相关	4	5	3
摘要	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.	Neural Architecture Search (NAS), introduced by Zoph and Le in 2017, automatically optimizes architectural decisions such as a network's depth, width, and connection structure instead of hand-designing them. Leading methods in the field include DARTS, ENAS, and Once-for-All.	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.