ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders

Code

• github.com/facebookresearch/convnext-v2
  OfficialIn paperpytorch★ 1,994
• github.com/rwightman/pytorch-image-models
  In paperpytorch★ 36,538
• github.com/Westlake-AI/openmixup
  pytorch★ 657
• github.com/vishalned/MMEarth-train
  pytorch★ 63
• github.com/Jacky-Android/convnext-v2-pytorch
  pytorch★ 48
• github.com/chenller/mmseg-extension
  pytorch★ 24
• github.com/zibbini/convnext-v2_tensorflow
  tf★ 13
• github.com/IMvision12/keras-vision-models
  pytorch★ 8
• github.com/lyqcom/convnext
  mindspore★ 0
• github.com/2024-MindSpore-1/Code2/tree/main/model-1/convnextv2
  mindspore★ 0

Abstract

Driven by improved architectures and better representation learning frameworks, the field of visual recognition has enjoyed rapid modernization and performance boost in the early 2020s. For example, modern ConvNets, represented by ConvNeXt, have demonstrated strong performance in various scenarios. While these models were originally designed for supervised learning with ImageNet labels, they can also potentially benefit from self-supervised learning techniques such as masked autoencoders (MAE). However, we found that simply combining these two approaches leads to subpar performance. In this paper, we propose a fully convolutional masked autoencoder framework and a new Global Response Normalization (GRN) layer that can be added to the ConvNeXt architecture to enhance inter-channel feature competition. This co-design of self-supervised learning techniques and architectural improvement results in a new model family called ConvNeXt V2, which significantly improves the performance of pure ConvNets on various recognition benchmarks, including ImageNet classification, COCO detection, and ADE20K segmentation. We also provide pre-trained ConvNeXt V2 models of various sizes, ranging from an efficient 3.7M-parameter Atto model with 76.7% top-1 accuracy on ImageNet, to a 650M Huge model that achieves a state-of-the-art 88.9% accuracy using only public training data.

Tasks

Benchmark Results

Reproductions