计算机科学
残余物
基线(sea)
深度学习
卷积神经网络
人工智能
块(置换群论)
编码(集合论)
图层(电子)
上下文图像分类
投影(关系代数)
趋同(经济学)
模式识别(心理学)
网络体系结构
机器学习
图像(数学)
算法
海洋学
化学
几何学
数学
计算机安全
集合(抽象数据类型)
有机化学
经济增长
经济
程序设计语言
地质学
作者
Ionut Cosmin Duta,Li Liu,Fan Zhu,Ling Shao
标识
DOI:10.1109/icpr48806.2021.9412193
摘要
Residual networks (ResNets) represent a powerful type of convolutional neural network (CNN) architecture, widely adopted and used in various tasks. In this work we propose an improved version of ResNets. Our proposed improvements address all three main components of a ResNet: the flow of information through the network layers, the residual building block, and the projection shortcut. We are able to show consistent improvements in accuracy and learning convergence over the baseline. For instance, on ImageNet dataset, using the ResNet with 50 layers, for top-1 accuracy we can report a 1.19% improvement over the baseline in one setting and around 2% boost in another. Importantly, these improvements are obtained without increasing the model complexity. Our proposed approach allows us to train extremely deep networks, while the baseline shows severe optimization issues. We report results on three tasks over six datasets: image classification (ImageNet, CIFAR-10 and CIFAR-100), object detection (COCO) and video action recognition (Kinetics-400 and Something-Something-v2). In the deep learning era, we establish a new milestone for the depth of a CNN. We successfully train a 404-layer deep CNN on the ImageNet dataset and a 3002-layer network on CIFAR-10 and CIFAR-100, while the baseline is not able to converge at such extreme depths. Code and models are publicly available at: https://github.com/iduta/iresnet.
科研通智能强力驱动
Strongly Powered by AbleSci AI