ConvNeXt
A modernized convolutional neural network architecture that adapts design ideas from Transformers to reform the traditional CNN, demonstrating that purely convolutional networks remain competitive.
Timeline (last 90 days)
The genealogy of computer vision models is more miscellaneous than that of language models, including LeNet, AlexNet, VGG, ResNet, DenseNet, EfficientNet, Vision Transformer, Swin, ConvNeXt, and others, with each architecture solving a specific defect exposed by the previous architecture.
CNN架构从LeNet-5到AlexNet（2012）、VGGNet（2014）、GoogLeNet/Inception（2014）、ResNet（2015），再到EfficientNet和ConvNeXt经历了演进过程
All Facts (2)
The genealogy of computer vision models is more miscellaneous than that of language models, including LeNet, AlexNet, VGG, ResNet, DenseNet, EfficientNet, Vision Transformer, Swin, ConvNeXt, and others, with each architecture solving a specific defect exposed by the previous architecture.
50%UnverifiedCNN架构从LeNet-5到AlexNet（2012）、VGGNet（2014）、GoogLeNet/Inception（2014）、ResNet（2015），再到EfficientNet和ConvNeXt经历了演进过程
50%