mlsanityData to 14 Oct 2026

PVT v2: Improved Baselines with Pyramid Vision Transformer

arXiv 2106.13797 ↗First posted 25 Jun 2021cs.CVcited by 751

Not on the map. Why?

Cited by 35 in State-space sequence models (S4, Mamba), but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Transformer recently has presented encouraging progress in computer vision. In this work, we present new baselines by improving the original Pyramid Vision Transformer (PVT v1) by adding three designs, including (1) linear complexity attention layer, (2) overlapping patch embedding, and (3) convolutional feed-forward network. With these modifications, PVT v2 reduces the computational complexity of PVT v1 to linear and achieves significant improvements on fundamental vision tasks such as classification, detection, and segmentation. Notably, the proposed PVT v2 achieves comparable or better performances than recent works such as Swin Transformer. We hope this work will facilitate state-of-the-art Transformer researches in computer vision. Code is available at https://github.com/whai362/PVT.

Key facts. Cited by 751 papers in the map (data through 14 Oct 2026). Builds on 36 of its 42 references that are in the map. First posted on arXiv 25 Jun 2021.

Builds on

36 of 42 references.

References · 36

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  6. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  7. 2017Mask R-CNNcited by 7,277
  8. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  9. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  10. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  11. 2020Training data-efficient image transformers & distillation through attentioncited by 4,586
  12. 2014Going Deeper with Convolutionscited by 4,241
24 more
  1. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
  2. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,611
  3. 2016Gaussian Error Linear Units (GELUs)cited by 3,502
  4. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
  5. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,546
  6. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,962
  7. 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,385
  8. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,276
  9. 2017Random Erasing Data Augmentationcited by 1,239
  10. 2021Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNetcited by 1,101
  11. 2020Designing Network Design Spacescited by 960
  12. 2021CvT: Introducing Convolutions to Vision Transformerscited by 947
  13. 2021CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classificationcited by 806
  14. 2017Focal Loss for Dense Object Detectioncited by 752
  15. 2019Panoptic Feature Pyramid Networkscited by 645
  16. 2021Transformer in Transformercited by 633
  17. 2021Twins: Revisiting the Design of Spatial Attention in Vision Transformerscited by 565
  18. 2019Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selectioncited by 540
  19. 2020Sparse R-CNN: End-to-End Object Detection with Learnable Proposalscited by 495
  20. 2021LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inferencecited by 475
  21. 2020Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detectioncited by 409
  22. 2021Conditional Positional Encodings for Vision Transformerscited by 406
  23. 2021Co-Scale Conv-Attentional Image Transformerscited by 224
  24. 2020How Much Position Information Do Convolutional Neural Networks Encode?cited by 172

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 32; 2022: 134; 2023: 188; 2024: 167; 2025: 142; 2026: 88.

751 papers.

Sort:

By area:

  1. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,565
  2. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,351
  3. 2024VMamba: Visual State Space Modelcited by 969
  4. 2023PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesiscited by 864
  5. 2022Vision Transformer Adapter for Dense Predictionscited by 565
  6. 2021MViTv2: Improved Multiscale Vision Transformers for Classification and Detectioncited by 519
  7. 2023VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Taskscited by 501
  8. 2022InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutionscited by 482
  9. 2024YOLOv9: Learning What You Want to Learn Using Programmable Gradient Informationcited by 425
  10. 2024PixArt-Sigma: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generationcited by 329
  11. 2022Vision Transformer with Deformable Attentioncited by 295
  12. 2022SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentationcited by 252
38 more
  1. 2021K-Net: Towards Unified Image Segmentationcited by 212
  2. 2022Visual Attention Networkcited by 210
  3. 2022UniFormer: Unifying Convolution and Self-attention for Visual Recognitioncited by 206
  4. 2022Medical Image Segmentation Review: The success of U-Netcited by 191
  5. 2022Focal Modulation Networkscited by 186
  6. 2022DaViT: Dual Attention Vision Transformerscited by 175
  7. 2023EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attentioncited by 172
  8. 2023FLatten Transformer: Vision Transformer using Focused Linear Attentioncited by 171
  9. 2022Stratified Transformer for 3D Point Cloud Segmentationcited by 167
  10. 2024RGBleftrightarrowX: Image decomposition and synthesis using material- and lighting-aware diffusion modelscited by 161
  11. 2021Polyp-PVT: Polyp Segmentation with Pyramid Vision Transformerscited by 159
  12. 2022Audio-Visual Segmentationcited by 151
  13. 2023BiFormer: Vision Transformer with Bi-Level Routing Attentioncited by 151
  14. 2024EfficientVMamba: Atrous Selective Scan for Light Weight Visual Mambacited by 146
  15. 2024MambaOut: Do We Really Need Mamba for Vision?cited by 143
  16. 2022More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsitycited by 142
  17. 2024PlainMamba: Improving Non-Hierarchical Mamba in Visual Recognitioncited by 141
  18. 2023Meta-Transformer: A Unified Framework for Multimodal Learningcited by 136
  19. 2022QuadTree Attention for Vision Transformerscited by 129
  20. 2021CycleMLP: A MLP-like Architecture for Dense Predictioncited by 126
  21. 2023Spherical Transformer for LiDAR-based 3D Recognitioncited by 125
  22. 2021MPViT: Multi-Path Vision Transformer for Dense Predictioncited by 122
  23. 2021A Survey of Visual Transformerscited by 117
  24. 2022ViTAEv2: Vision Transformer Advanced by Exploring Inductive Bias for Image Recognition and Beyondcited by 117
  25. 2022EdgeViTs: Competing Light-weight CNNs on Mobile Devices with Vision Transformerscited by 116
  26. 2023VideoLLM: Modeling Video Sequence with Large Language Modelscited by 116
  27. 2021Panoptic SegFormer: Delving Deeper into Panoptic Segmentation with Transformerscited by 109
  28. 2023OctFormer: Octree-based Transformers for 3D Point Cloudscited by 109
  29. 2021MISSFormer: An Effective Medical Image Segmentation Transformercited by 103
  30. 2021Long-Short Transformer: Efficient Transformers for Language and Visioncited by 102
  31. 2024Demystify Mamba in Vision: A Linear Attention Perspectivecited by 102
  32. 2022Inception Transformercited by 99
  33. 2022Global Context Vision Transformerscited by 98
  34. 2023Extracting Motion and Appearance via Inter-Frame Attention for Efficient Video Frame Interpolationcited by 98
  35. 2023Large Selective Kernel Network for Remote Sensing Object Detectioncited by 98
  36. 2024Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architecturescited by 98
  37. 2023InternGPT: Solving Vision-Centric Tasks by Interacting with ChatGPT Beyond Languagecited by 96
  38. 2021Shunted Self-Attention via Multi-Scale Token Aggregationcited by 90

50 most cited of 751 All 751 (JSON)