mlsanityData to 7 Oct 2026

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

arXiv 2301.00808 ↗First posted 2 Jan 2023cs.CVcited by 703

Not on the map. Why?

Cited by 48 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

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.

Key facts. Cited by 703 papers in the map (data through 7 Oct 2026). Builds on 62 of its 83 references that are in the map. First posted on arXiv 2 Jan 2023.

Builds on

62 of 83 references.

References · 62

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  5. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  6. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  7. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  8. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  9. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  10. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  11. 2017Mask R-CNNcited by 7,259
  12. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
38 more
  1. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  2. 2016Densely Connected Convolutional Networkscited by 6,691
  3. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  4. 2016Layer Normalizationcited by 5,579
  5. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  6. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  7. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  8. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  9. 2017Squeeze-and-Excitation Networkscited by 4,763
  10. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  11. 2014Going Deeper with Convolutionscited by 4,231
  12. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  13. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  14. 2022A ConvNet for the 2020scited by 3,545
  15. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  16. 2020Exploring Simple Siamese Representation Learningcited by 2,853
  17. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
  18. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  19. 2018CBAM: Convolutional Block Attention Modulecited by 2,463
  20. 2021BEiT: BERT Pre-Training of Image Transformerscited by 2,360
  21. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,261
  22. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
  23. 2021An Empirical Study of Training Self-Supervised Vision Transformerscited by 1,610
  24. 2018Group Normalizationcited by 1,514
  25. 2017Accurate, Large Minibatch SGD: Training ImageNet in 1 Hourcited by 1,479
  26. 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,379
  27. 2018Unified Perceptual Parsing for Scene Understandingcited by 1,265
  28. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
  29. 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,187
  30. 2021SimMIM: A Simple Framework for Masked Image Modelingcited by 1,147
  31. 2021EfficientNetV2: Smaller Models and Faster Trainingcited by 1,127
  32. 2016Semantic Understanding of Scenes through the ADE20K Datasetcited by 1,063
  33. 2016Deep Networks with Stochastic Depthcited by 973
  34. 2020Designing Network Design Spacescited by 954
  35. 2021Multiscale Vision Transformerscited by 896
  36. 2021Going deeper with Image Transformerscited by 759
  37. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 746
  38. 2020Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentationcited by 595

50 most cited of 62 All 62 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 88; 2024: 194; 2025: 221; 2026: 200.

703 papers.

Sort:

By area:

  1. 2023Medical SAM Adapter: Adapting Segment Anything Model for Medical Image Segmentationcited by 485
  2. 2024YOLOv9: Learning What You Want to Learn Using Programmable Gradient Informationcited by 422
  3. 2023Florence-2: Advancing a Unified Representation for a Variety of Vision Taskscited by 403
  4. 2024Depth Pro: Sharp Monocular Metric Depth in Less Than a Secondcited by 395
  5. 2023EVA-02: A Visual Representation for Neon Genesiscited by 377
  6. 2024F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matchingcited by 353
  7. 2023Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistlescited by 287
  8. 2023SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Modelscited by 283
  9. 2023A Cookbook of Self-Supervised Learningcited by 248
  10. 2024LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Controlcited by 202
  11. 2024Probing the 3D Awareness of Visual Foundation Modelscited by 175
  12. 2023CROMA: Remote Sensing Representations with Contrastive Radar-Optical Masked Autoencoderscited by 167
38 more
  1. 2024JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generationcited by 162
  2. 2024Medical SAM 2: Segment medical images as video via Segment Anything Model 2cited by 151
  3. 2024PlainMamba: Improving Non-Hierarchical Mamba in Visual Recognitioncited by 141
  4. 2024Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoderscited by 137
  5. 2024AMEX: Android Multi-annotation Expo Dataset for Mobile GUI Agentscited by 110
  6. 2024RoboMamba: Efficient Vision-Language-Action Model for Robotic Reasoning and Manipulationcited by 102
  7. 2023Large Selective Kernel Network for Remote Sensing Object Detectioncited by 98
  8. 2026Generative Modeling via Driftingcited by 98
  9. 2024EscherNet: A Generative Model for Scalable View Synthesiscited by 94
  10. 2024ChartAssisstant: A Universal Chart Multimodal Language Model via Chart-to-Table Pre-training and Multitask Instruction Tuningcited by 79
  11. 2023An Inverse Scaling Law for CLIP Trainingcited by 76
  12. 2024MMEarth: Exploring Multi-Modal Pretext Tasks For Geospatial Representation Learningcited by 76
  13. 2025Vision-Language-Action (VLA) Models: Concepts, Progress, Applications and Challengescited by 72
  14. 2025A Survey on Vision-Language-Action Models for Autonomous Drivingcited by 72
  15. 2024SwitchLight: Co-design of Physics-driven Architecture and Pre-training Framework for Human Portrait Relightingcited by 66
  16. 2023UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image Recognitioncited by 64
  17. 2025Scaling Language-Free Visual Representation Learningcited by 62
  18. 2024Scaling Spike-driven Transformer with Efficient Spike Firing Approximation Trainingcited by 57
  19. 2024Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?cited by 56
  20. 2023Gold-YOLO: Efficient Object Detector via Gather-and-Distribute Mechanismcited by 51
  21. 2026One-step Latent-free Image Generation with Pixel Mean Flowscited by 49
  22. 2024reBEN: Refined BigEarthNet Dataset for Remote Sensing Image Analysiscited by 48
  23. 2024Scaling Transformers for Low-Bitrate High-Quality Speech Codingcited by 48
  24. 2023Robust Principles: Architectural Design Principles for Adversarially Robust CNNscited by 46
  25. 2024XoFTR: Cross-modal Feature Matching Transformercited by 45
  26. 2024Do Vision and Language Encoders Represent the World Similarly?cited by 44
  27. 2024LSKNet: A Foundation Lightweight Backbone for Remote Sensingcited by 44
  28. 2024OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentationcited by 43
  29. 2023Learned representation-guided diffusion models for large-image generationcited by 39
  30. 2023DreamTeacher: Pretraining Image Backbones with Deep Generative Modelscited by 37
  31. 2025UniAVGen: Unified Audio and Video Generation with Asymmetric Cross-Modal Interactionscited by 35
  32. 2024Revisiting MAE pre-training for 3D medical image segmentationcited by 33
  33. 2024Neural Networks Learn Statistics of Increasing Complexitycited by 30
  34. 2025Mahalanobis++: Improving OOD Detection via Feature Normalizationcited by 30
  35. 2025ZipVoice: Fast and High-Quality Zero-Shot Text-to-Speech with Flow Matchingcited by 30
  36. 2024NTIRE 2024 Challenge on Short-form UGC Video Quality Assessment: Methods and Resultscited by 29
  37. 2024Masked Image Modeling: A Surveycited by 28
  38. 2024RadarDistill: Boosting Radar-based Object Detection Performance via Knowledge Distillation from LiDAR Featurescited by 27

50 most cited of 703 All 703 (JSON)