ConvNeXts: A Modern ConvNet for Vision

Home

Discover

Bookmarks

Keep Up With Latest Trending Papers. Computer Science, AI and Machine Learning and more.Subscribe

Bookmarked bySatish

CC BY

Source arXiv

Computer Vision

ConvNeXts: A Modern ConvNet for Vision

A ConvNet for the 2020s

We reexamine the design spaces and test the limits of what a pure convnet can achieve on general computer vision tasks such as object detection and semantic segmentation.

We gradually"modernize"a standard resnet toward the design of a vision transformer, and discover several key components that contribute to the performance difference along the way.

The outcome of this exploration is a family of pure convnet models dubbed convnext.constructed entirely from standard convnet modules, convnexts compete favorably with transformers in terms of accuracy and scalability, achieving 87.8% imagenet top-1 accuracy and outperforming hierarchical transformers on object detection and semantic segmentation.