ResNet: Enabling Deep Convolutional Neural Networks through Residual Learning
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
A Kernel Perspective of Skip Connections in Convolutional Networks
Over-parameterized residual networks (ResNets) are amongst the most successful convolutional neural architectures for image processing. Here we study their properties through their Gaussian Process and Neural Tangent ker…
Classifying galaxies in the Galaxy10 DECals dataset using Inception and Residual CNNs
Image data regarding galactic morphology is expected to increase both in quantity and quality for the next foreseeable years; thus it is important to explore which deep learning architectures adapted for image classifica…
Computational EfficiencyImage ClassificationHiResNets: Native Full-HD Video Recognition with Foveal Residual Streams
Much of the recent progress in image and video recognition has come at the cost of memory: larger models, increased resolution, and longer temporal contexts. An inevitable component is the quadratic (or larger) growth of…
ShaResNet: reducing residual network parameter number by sharing weights
Deep Residual Networks have reached the state of the art in many image processing tasks such image classification. However, the cost for a gain in accuracy in terms of depth and memory is prohibitive as it requires a hig…
image-classificationImage ClassificationAdaResNet: Enhancing Residual Networks with Dynamic Weight Adjustment for Improved Feature Integration
In very deep neural networks, gradients can become extremely small during backpropagation, making it challenging to train the early layers. ResNet (Residual Network) addresses this issue by enabling gradients to flow dir…