So sánh phương pháp

	DenseNet	ResNet (Mạng Tích chập Tái sinh)
Lĩnh vực	Học sâu	Học sâu
Họ	Machine learning	Machine learning
Năm ra đời	2017	2016
Người khởi xướng	Huang, G.; Liu, Z.; van der Maaten, L.; Weinberger, K. Q.	He, K.; Zhang, X.; Ren, S.; Sun, J.
Loại	Dense convolutional neural network (feed-forward dense connectivity)	Deep Convolutional Neural Network with skip connections
Công trình gốc	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.	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.
Tên gọi khác	DenseNet, Dense Convolutional Network, densely connected CNN, DenseNet-121	ResNet, Residual Network, Deep Residual Learning, ResNet-50
Liên quan	2	4
Tóm tắt	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.	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.