Porównaj metody

	ResNet (Residual Network)	AlexNet	EfficientNet
Dziedzina	Uczenie głębokie	Uczenie głębokie	Uczenie głębokie
Rodzina	Machine learning	Machine learning	Machine learning
Rok powstania	2016	2012	2019
Twórca	He, K.; Zhang, X.; Ren, S.; Sun, J.	Krizhevsky, A.; Sutskever, I.; Hinton, G. E.	Tan, M. & Le, Q. V.
Typ	Deep Convolutional Neural Network with skip connections	Deep Convolutional Neural Network (CNN)	Compound-scaled convolutional neural network architecture
Źródło pierwotne	He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep Residual Learning for Image Recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 770–778.	Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). ImageNet Classification with Deep Convolutional Neural Networks. Advances in Neural Information Processing Systems, 25, 1097–1105. (Republished: Communications of the ACM, 60(6), 84–90, 2017.)	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.
Inne nazwy	ResNet, Residual Network, Deep Residual Learning, ResNet-50	AlexNet, Krizhevsky net, SuperVision CNN, ImageNet CNN 2012	EfficientNet, compound scaling CNN, EfficientNet-B0 through B7, EfficientNetV2
Pokrewne	4	3	4
Podsumowanie	ResNet (Residual Network) is a deep convolutional neural network architecture introduced by Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun at CVPR 2016. By inserting shortcut (skip) connections that carry the input of a block directly to its output — defining the block's task as learning a residual correction rather than a full mapping — ResNet enabled training of networks with hundreds or even thousands of layers without the vanishing-gradient degradation that had previously made very deep networks impractical. It won the ILSVRC 2015 image recognition competition with a top-5 error of 3.57% and remains the most widely used backbone architecture in computer vision.	AlexNet is a deep convolutional neural network (CNN) introduced by Alex Krizhevsky, Ilya Sutskever, and Geoffrey Hinton in 2012. It won the ImageNet Large Scale Visual Recognition Challenge (ILSVRC 2012) with a top-5 error rate of 15.3%, outstripping the runner-up by more than 10 percentage points and reigniting broad interest in deep learning. The architecture introduced or popularised several techniques — ReLU activations, dropout regularisation, and multi-GPU training — that became standard practice across the field.	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.