ResNet: Enabling Deep Convolutional Neural Networks through Residual Learning

2025/10/28 by Xingyu Liu, Liu, Xingyu, Kun Ming Goh +1 · 1 voice
Computer Science · #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #cs.AI #cs.CV

paper · pdf · doi:10.48550/arxiv.2510.24036

Abstract

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.

Citations

• Aggregated Residual Transformations for Deep Neural Networks
• Densely Connected Convolutional Networks
• Wide Residual Networks
• Deep Residual Learning for Image Recognition
• Training Very Deep Networks
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Going Deeper with Convolutions
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• ImageNet classification with deep convolutional neural networks
• Gradient-based learning applied to document recognition

Discussions

• What the hell is that? arxiv.org/pdf/2510.24036 Is this some kind of bibliometric optimization strategy? Students pushing fake plagiarized papers to bootstrap their Google Scholar account? I don't und [bsky, 0 points, 1 comments]

Related

• Study of Residual Networks for Image Recognition
• Resnet in Resnet: Generalizing Residual Architectures
• Improved Residual Networks for Image and Video Recognition
• Biologically inspired deep residual networks for computer vision applications
• DiracNets: Training Very Deep Neural Networks Without Skip-Connections