השוואת שיטות

	רשת קונבולוציה מלאה (FCN)	ResNet (רשת שיורית)
תחום	למידה עמוקה	למידה עמוקה
משפחה	Machine learning	Machine learning
שנת המקור	2015	2016
הוגה השיטה	Long, J.; Shelhamer, E.; Darrell, T.	He, K.; Zhang, X.; Ren, S.; Sun, J.
סוג	Dense pixel-wise prediction convolutional network	Deep Convolutional Neural Network with skip connections
מקור מכונן	Long, J., Shelhamer, E., & Darrell, T. (2015). Fully Convolutional Networks for Semantic Segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 3431–3440.	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.
כינויים	FCN, fully convolutional network, FCN-32s, FCN-16s	ResNet, Residual Network, Deep Residual Learning, ResNet-50
קשורות	2	4
תקציר	The Fully Convolutional Network (FCN), introduced by Long, Shelhamer, and Darrell at CVPR 2015, was the first end-to-end deep learning architecture trained to produce dense pixel-wise semantic segmentation maps from images of arbitrary size. By replacing the fully connected layers of a classification CNN with convolutional layers and adding learned upsampling through transposed convolutions and skip connections, FCN enabled the direct prediction of a class label for every pixel in an image, establishing the template for all subsequent segmentation architectures including U-Net and DeepLab.	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.