Uporedite metode
Pregledajte izabrane metode jednu pored druge; redovi koji se razlikuju su istaknuti.
| ResNet (Rezidualna Mreža)× | VGGNet (veoma duboke konvolucione mreže)× | |
|---|---|---|
| Oblast | Duboko učenje | Duboko učenje |
| Porodica | Machine learning | Machine learning |
| Godina nastanka≠ | 2016 | 2014 |
| Tvorac≠ | He, K.; Zhang, X.; Ren, S.; Sun, J. | Simonyan, K. & Zisserman, A. (Visual Geometry Group, Oxford) |
| Tip≠ | Deep Convolutional Neural Network with skip connections | Deep Convolutional Neural Network (image classification) |
| Temeljni izvor≠ | 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. DOI ↗ | Simonyan, K., & Zisserman, A. (2014). Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv:1409.1556 [cs.CV]. Published at ICLR 2015. DOI ↗ |
| Drugi nazivi≠ | ResNet, Residual Network, Deep Residual Learning, ResNet-50 | VGG, VGG-16, VGG-19, Very Deep ConvNet |
| Srodne | 4 | 4 |
| Sažetak≠ | 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. | VGGNet is a deep convolutional neural network architecture introduced by Karen Simonyan and Andrew Zisserman at the Visual Geometry Group, Oxford, in 2014 (published at ICLR 2015). It demonstrated that network depth — achieved exclusively through stacking small 3x3 convolutional filters — is the single most critical factor for high image-classification accuracy, and its two canonical variants (VGG-16 and VGG-19) became the dominant benchmark architectures for CNN design throughout the mid-2010s. |
| ScholarGateSkup podataka ↗ |
|
|