通过捷径连接让深度卷积网络更易训练，准确率显著提升
ResNet: Enabling Deep Convolutional Neural Networks through Residual Learning
- 引入残差学习结构，用捷径连接跳过中间层
- 在CIFAR-10上达到89.9%准确率，比传统网络高5.8个百分点
- 适合需要训练极深网络的计算机视觉任务
卷积神经网络（CNN）已彻底改变计算机视觉领域，但训练非常深的网络一直受梯度消失问题困扰。本文探讨了由He等人（2015）提出的残差网络（ResNet），通过引入跳跃连接克服这一限制。ResNet利用捷径连接使梯度能直接穿过中间层，从而实现数百层网络的训练。在CIFAR-10数据集上的实现中，ResNet-18达到89.9%的准确率，远超同深度传统深层CNN的84.1%，且收敛更快、训练更稳定。
原文摘要 · Abstract (English)
Convolutional Neural Networks (CNNs) has revolutionized computer vision, but training very deep networks has been challenging due to the vanishing gradient problem. This paper explores Residual Networks (ResNet), introduced by He et al. (2015), which overcomes this limitation by using skip connections. ResNet enables the training of networks with hundreds of layers by allowing gradients to flow directly through shortcut connections that bypass intermediate layers. In our implementation on the CIFAR-10 dataset, ResNet-18 achieves 89.9% accuracy compared to 84.1% for a traditional deep CNN of similar depth, while also converging faster and training more stably.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。