mlsanityData to 7 Oct 2026

A ConvNet for the 2020s

arXiv 2201.03545 ↗First posted 10 Jan 2022cs.CVcited by 3,545

Not on the map. Why?

Cited by 146 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

The "Roaring 20s" of visual recognition began with the introduction of Vision Transformers (ViTs), which quickly superseded ConvNets as the state-of-the-art image classification model. A vanilla ViT, on the other hand, faces difficulties when applied to general computer vision tasks such as object detection and semantic segmentation. It is the hierarchical Transformers (e.g., Swin Transformers) that reintroduced several ConvNet priors, making Transformers practically viable as a generic vision backbone and demonstrating remarkable performance on a wide variety of vision tasks. However, the effectiveness of such hybrid approaches is still largely credited to the intrinsic superiority of Transformers, rather than the inherent inductive biases of convolutions. In this work, we reexamine the design spaces and test the limits of what a pure ConvNet can achieve. 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 Swin Transformers on COCO detection and ADE20K segmentation, while maintaining the simplicity and efficiency of standard ConvNets.

Key facts. Cited by 3,545 papers in the map (data through 7 Oct 2026). Builds on 71 of its 92 references that are in the map. First posted on arXiv 10 Jan 2022.

Builds on

71 of 92 references.

References · 71

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  5. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  6. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  7. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  8. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  9. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  10. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  11. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  12. 2017Mask R-CNNcited by 7,259
38 more
  1. 2016Densely Connected Convolutional Networkscited by 6,691
  2. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  3. 2016Layer Normalizationcited by 5,579
  4. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  5. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  6. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  7. 2017Squeeze-and-Excitation Networkscited by 4,763
  8. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  9. 2014Going Deeper with Convolutionscited by 4,231
  10. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  11. 2016Gaussian Error Linear Units (GELUs)cited by 3,431
  12. 2015Fast R-CNNcited by 2,930
  13. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  14. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  15. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  16. 2021BEiT: BERT Pre-Training of Image Transformerscited by 2,360
  17. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,320
  18. 2017Non-local Neural Networkscited by 2,290
  19. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,261
  20. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
  21. 2016Identity Mappings in Deep Residual Networkscited by 1,960
  22. 2020The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalizationcited by 1,842
  23. 2018Group Normalizationcited by 1,514
  24. 2019Natural Adversarial Examplescited by 1,401
  25. 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,379
  26. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,275
  27. 2018Unified Perceptual Parsing for Scene Understandingcited by 1,265
  28. 2017Random Erasing Data Augmentationcited by 1,235
  29. 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,187
  30. 2021EfficientNetV2: Smaller Models and Faster Trainingcited by 1,127
  31. 2014Two-Stream Convolutional Networks for Action Recognition in Videoscited by 1,067
  32. 2016Semantic Understanding of Scenes through the ADE20K Datasetcited by 1,063
  33. 2019Learning Robust Global Representations by Penalizing Local Predictive Powercited by 1,010
  34. 2016Deep Networks with Stochastic Depthcited by 973
  35. 2020Designing Network Design Spacescited by 954
  36. 2021CvT: Introducing Convolutions to Vision Transformerscited by 946
  37. 2018MnasNet: Platform-Aware Neural Architecture Search for Mobilecited by 937
  38. 2021Multiscale Vision Transformerscited by 896

50 most cited of 71 All 71 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 395; 2023: 814; 2024: 864; 2025: 778; 2026: 694.

3,545 papers.

Sort:

By area:

  1. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,534
  2. 2022Visual Prompt Tuningcited by 1,674
  3. 2024Depth Anything V2cited by 1,385
  4. 2024Depth Anything: Unleashing the Power of Large-Scale Unlabeled Datacited by 1,346
  5. 2024Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Modelcited by 1,051
  6. 2022TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysiscited by 1,030
  7. 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 978
  8. 2024VMamba: Visual State Space Modelcited by 955
  9. 2024Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMscited by 822
  10. 2023A Simple and Effective Pruning Approach for Large Language Modelscited by 776
  11. 2023GLIGEN: Open-Set Grounded Text-to-Image Generationcited by 774
  12. 2023ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoderscited by 703
38 more
  1. 2022Simple Baselines for Image Restorationcited by 701
  2. 2022EVA: Exploring the Limits of Masked Visual Representation Learning at Scalecited by 685
  3. 2023DataComp: In search of the next generation of multimodal datasetscited by 635
  4. 2022BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detectioncited by 568
  5. 2022Vision Transformer Adapter for Dense Predictionscited by 564
  6. 2024YOLOv10: Real-Time End-to-End Object Detectioncited by 508
  7. 2022InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutionscited by 479
  8. 2022TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Drivingcited by 477
  9. 2022MaxViT: Multi-Axis Vision Transformercited by 476
  10. 2022Git Re-Basin: Merging Models modulo Permutation Symmetriescited by 460
  11. 2022PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategiescited by 432
  12. 2024YOLOv9: Learning What You Want to Learn Using Programmable Gradient Informationcited by 422
  13. 2022DeiT III: Revenge of the ViTcited by 417
  14. 2023Towards Stable Test-Time Adaptation in Dynamic Wild Worldcited by 409
  15. 2023Florence-2: Advancing a Unified Representation for a Variety of Vision Taskscited by 403
  16. 2024Depth Pro: Sharp Monocular Metric Depth in Less Than a Secondcited by 395
  17. 2024Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimationcited by 389
  18. 2024SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inferencecited by 378
  19. 2023EVA-02: A Visual Representation for Neon Genesiscited by 377
  20. 2025Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Modelscited by 376
  21. 2024UniDepth: Universal Monocular Metric Depth Estimationcited by 375
  22. 2023Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Modelscited by 371
  23. 2024Mini-Gemini: Mining the Potential of Multi-modality Vision Language Modelscited by 361
  24. 2023An Embodied Generalist Agent in 3D Worldcited by 355
  25. 2024F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matchingcited by 353
  26. 2022OneFormer: One Transformer to Rule Universal Image Segmentationcited by 327
  27. 2024VideoMamba: State Space Model for Efficient Video Understandingcited by 325
  28. 2025Perception Encoder: The best visual embeddings are not at the output of the networkcited by 315
  29. 2022Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectivescited by 314
  30. 2023Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detectioncited by 313
  31. 2023Driving into the Future: Multiview Visual Forecasting and Planning with World Model for Autonomous Drivingcited by 309
  32. 2022BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervisioncited by 302
  33. 2022Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learningcited by 302
  34. 2024LayerSkip: Enabling Early Exit Inference and Self-Speculative Decodingcited by 302
  35. 2024VisionZip: Longer is Better but Not Necessary in Vision Language Modelscited by 298
  36. 2022Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuningcited by 292
  37. 2022MultiMAE: Multi-modal Multi-task Masked Autoencoderscited by 287
  38. 2024DepthSplat: Connecting Gaussian Splatting and Depthcited by 275

50 most cited of 3,545 All 3,545 (JSON)