mlsanityData to 7 Oct 2026

Conv2Former: A Simple Transformer-Style ConvNet for Visual Recognition

arXiv 2211.11943 ↗First posted 22 Nov 2022cs.CVcited by 81

Not on the map. Why?

Abstract (arXiv)

This paper does not attempt to design a state-of-the-art method for visual recognition but investigates a more efficient way to make use of convolutions to encode spatial features. By comparing the design principles of the recent convolutional neural networks ConvNets) and Vision Transformers, we propose to simplify the self-attention by leveraging a convolutional modulation operation. We show that such a simple approach can better take advantage of the large kernels (>=7x7) nested in convolutional layers. We build a family of hierarchical ConvNets using the proposed convolutional modulation, termed Conv2Former. Our network is simple and easy to follow. Experiments show that our Conv2Former outperforms existent popular ConvNets and vision Transformers, like Swin Transformer and ConvNeXt in all ImageNet classification, COCO object detection and ADE20k semantic segmentation.

Key facts. Cited by 81 papers in the map (data through 7 Oct 2026). Builds on 96 of its 112 references that are in the map. First posted on arXiv 22 Nov 2022.

Builds on

96 of 112 references.

References · 96

  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. 2017Mask R-CNNcited by 7,259
  10. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  11. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  12. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
38 more
  1. 2016Layer Normalizationcited by 5,579
  2. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  3. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  4. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  5. 2017Squeeze-and-Excitation Networkscited by 4,763
  6. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  7. 2014Going Deeper with Convolutionscited by 4,231
  8. 2022A ConvNet for the 2020scited by 3,545
  9. 2016Gaussian Error Linear Units (GELUs)cited by 3,431
  10. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,923
  11. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  12. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  13. 2018CBAM: Convolutional Block Attention Modulecited by 2,463
  14. 2021BEiT: BERT Pre-Training of Image Transformerscited by 2,360
  15. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,320
  16. 2017Non-local Neural Networkscited by 2,290
  17. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,261
  18. 2019Searching for MobileNetV3cited by 1,984
  19. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,960
  20. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,509
  21. 2016Neural Architecture Search with Reinforcement Learningcited by 1,489
  22. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,441
  23. 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,379
  24. 2019Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regressioncited by 1,361
  25. 2018Unified Perceptual Parsing for Scene Understandingcited by 1,265
  26. 2017Random Erasing Data Augmentationcited by 1,235
  27. 2021Swin Transformer V2: Scaling Up Capacity and Resolutioncited by 1,215
  28. 2021EfficientNetV2: Smaller Models and Faster Trainingcited by 1,127
  29. 2021Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNetcited by 1,096
  30. 2021Transformers in Vision: A Surveycited by 1,009
  31. 2021Scaling Vision Transformerscited by 993
  32. 2016Deep Networks with Stochastic Depthcited by 973
  33. 2020Designing Network Design Spacescited by 954
  34. 2021CvT: Introducing Convolutions to Vision Transformerscited by 946
  35. 2021CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classificationcited by 806
  36. 2021Going deeper with Image Transformerscited by 759
  37. 2020A Survey on Visual Transformercited by 653
  38. 2021MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformercited by 636

50 most cited of 96 All 96 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 20; 2024: 25; 2025: 32; 2026: 4.

81 papers.

Sort:

By area:

  1. 2024MambaOut: Do We Really Need Mamba for Vision?cited by 142
  2. 2023RepViT: Revisiting Mobile CNN From ViT Perspectivecited by 123
  3. 2023Large Selective Kernel Network for Remote Sensing Object Detectioncited by 98
  4. 2023InceptionNeXt: When Inception Meets ConvNeXtcited by 84
  5. 2023RMT: Retentive Networks Meet Vision Transformerscited by 68
  6. 2023DFormer: Rethinking RGBD Representation Learning for Semantic Segmentationcited by 58
  7. 2024Rewrite the Starscited by 55
  8. 2023Scale-Aware Modulation Meet Transformercited by 49
  9. 2024LSKNet: A Foundation Lightweight Backbone for Remote Sensingcited by 44
  10. 2023YOLO-MS: Rethinking Multi-Scale Representation Learning for Real-time Object Detectioncited by 33
  11. 2024Breaking the Low-Rank Dilemma of Linear Attentioncited by 31
  12. 2025DFormerv2: Geometry Self-Attention for RGBD Semantic Segmentationcited by 30
38 more
  1. 2023Lightweight Vision Transformer with Bidirectional Interactioncited by 25
  2. 2025OverLoCK: An Overview-first-Look-Closely-next ConvNet with Context-Mixing Dynamic Kernelscited by 24
  3. 2024See More Details: Efficient Image Super-Resolution by Experts Miningcited by 23
  4. 2023TransXNet: Learning Both Global and Local Dynamics with a Dual Dynamic Token Mixer for Visual Recognitioncited by 21
  5. 2024Parameter-Efficient Fine-Tuning for Pre-Trained Vision Models: A Survey and Benchmarkcited by 21
  6. 2025DefMamba: Deformable Visual State Space Modelcited by 18
  7. 2023PMAA: A Progressive Multi-scale Attention Autoencoder Model for High-performance Cloud Removal from Multi-temporal Satellite Imagerycited by 16
  8. 2024Efficient Modulation for Vision Networkscited by 16
  9. 2025LSNet: See Large, Focus Smallcited by 15
  10. 2023ADNet: Lane Shape Prediction via Anchor Decompositioncited by 14
  11. 2024SparX: A Sparse Cross-Layer Connection Mechanism for Hierarchical Vision Mamba and Transformer Networkscited by 14
  12. 2025Strip R-CNN: Large Strip Convolution for Remote Sensing Object Detectioncited by 14
  13. 2024Transforming Image Super-Resolution: A ConvFormer-based Efficient Approachcited by 13
  14. 2024ViG: Linear-complexity Visual Sequence Learning with Gated Linear Attentioncited by 13
  15. 2023Recaptured Raw Screen Image and Video Demoir'eing via Channel and Spatial Modulationscited by 12
  16. 2024Efficient Degradation-aware Any Image Restorationcited by 11
  17. 2025FreCT: Frequency-augmented Convolutional Transformer for Robust Time Series Anomaly Detectioncited by 10
  18. 2025Frequency-Dynamic Attention Modulation for Dense Predictioncited by 10
  19. 2025iFormer: Integrating ConvNet and Transformer for Mobile Applicationcited by 9
  20. 2024Recurrent Aligned Network for Generalized Pedestrian Trajectory Predictioncited by 8
  21. 2024Vision Transformer with Sparse Scan Priorcited by 6
  22. 2024PADRe: A Unifying Polynomial Attention Drop-in Replacement for Efficient Vision Transformercited by 5
  23. 2024DeBiFormer: Vision Transformer with Deformable Agent Bi-level Routing Attentioncited by 4
  24. 2024Monocular Lane Detection Based on Deep Learning: A Surveycited by 4
  25. 2025Deep Tree Tensor Networkscited by 4
  26. 2025OmniSegmentor: A Flexible Multi-Modal Learning Framework for Semantic Segmentationcited by 4
  27. 2024Multi-Token Enhancing for Vision Representation Learningcited by 3
  28. 2025All-in-One Image Compression and Restorationcited by 3
  29. 2025S2AFormer: Strip Self-Attention for Efficient Vision Transformercited by 3
  30. 2025SAGA: Selective Adaptive Gating for Efficient and Expressive Linear Attentioncited by 3
  31. 2025Language-Guided Graph Representation Learning for Video Summarizationcited by 3
  32. 2023A Simple Adaptive Unfolding Network for Hyperspectral Image Reconstructioncited by 2
  33. 2023Traffic Scene Parsing through the TSP6K Datasetcited by 2
  34. 2023Towards an Effective and Efficient Transformer for Rain-by-snow Weather Removalcited by 2
  35. 2024Infinite-Dimensional Feature Interactioncited by 2
  36. 2024DuoFormer: Leveraging Hierarchical Visual Representations by Local and Global Attentioncited by 2
  37. 2025Multi-Timescale Motion-Decoupled Spiking Transformer for Audio-Visual Zero-Shot Learningcited by 2
  38. 2025A Gravity-informed Spatiotemporal Transformer for Human Activity Intensity Predictioncited by 2

50 most cited of 81 All 81 (JSON)