mlsanityData to 14 Oct 2026

Peripheral Vision Transformer

arXiv 2206.06801 ↗First posted 14 Jun 2022cs.CVcited by 27

Not on the map. Why?

Abstract (arXiv)

Human vision possesses a special type of visual processing systems called peripheral vision. Partitioning the entire visual field into multiple contour regions based on the distance to the center of our gaze, the peripheral vision provides us the ability to perceive various visual features at different regions. In this work, we take a biologically inspired approach and explore to model peripheral vision in deep neural networks for visual recognition. We propose to incorporate peripheral position encoding to the multi-head self-attention layers to let the network learn to partition the visual field into diverse peripheral regions given training data. We evaluate the proposed network, dubbed PerViT, on ImageNet-1K and systematically investigate the inner workings of the model for machine perception, showing that the network learns to perceive visual data similarly to the way that human vision does. The performance improvements in image classification over the baselines across different model sizes demonstrate the efficacy of the proposed method.

Key facts. Cited by 27 papers in the map (data through 14 Oct 2026). Builds on 67 of its 93 references that are in the map. First posted on arXiv 14 Jun 2022.

Builds on

67 of 93 references.

References · 67

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  5. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  6. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  7. 2020End-to-End Object Detection with Transformerscited by 7,414
  8. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  9. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  10. 2016Layer Normalizationcited by 5,669
  11. 2017Squeeze-and-Excitation Networkscited by 4,789
  12. 2020Training data-efficient image transformers & distillation through attentioncited by 4,586
38 more
  1. 2022A ConvNet for the 2020scited by 3,579
  2. 2016Gaussian Error Linear Units (GELUs)cited by 3,502
  3. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,546
  4. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,332
  5. 2013Visualizing and Understanding Convolutional Networkscited by 2,290
  6. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,962
  7. 2019Transformer-XL: Attentive Language Models Beyond a Fixed-Length Contextcited by 1,850
  8. 2020Rethinking Attention with Performerscited by 1,601
  9. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,446
  10. 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,198
  11. 2018Self-Attention with Relative Position Representationscited by 1,120
  12. 2021Perceiver: General Perception with Iterative Attentioncited by 1,104
  13. 2021Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNetcited by 1,101
  14. 2021CvT: Introducing Convolutions to Vision Transformerscited by 947
  15. 2017Revisiting Unreasonable Effectiveness of Data in Deep Learning Eracited by 919
  16. 2021Segmenter: Transformer for Semantic Segmentationcited by 855
  17. 2021Do Vision Transformers See Like Convolutional Neural Networks?cited by 675
  18. 2021CoAtNet: Marrying Convolution and Attention for All Data Sizescited by 569
  19. 2019Stand-Alone Self-Attention in Vision Modelscited by 542
  20. 2021CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windowscited by 527
  21. 2021MetaFormer Is Actually What You Need for Visioncited by 524
  22. 2021ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biasescited by 484
  23. 2022MaxViT: Multi-Axis Vision Transformercited by 476
  24. 2021Conditional Positional Encodings for Vision Transformerscited by 406
  25. 2021Early Convolutions Help Transformers See Bettercited by 396
  26. 2021Pay Attention to MLPscited by 368
  27. 2021ResNet strikes back: An improved training procedure in timmcited by 368
  28. 2021Bottleneck Transformers for Visual Recognitioncited by 364
  29. 2021ResMLP: Feedforward networks for image classification with data-efficient trainingcited by 339
  30. 2021XCiT: Cross-Covariance Image Transformerscited by 338
  31. 2020Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentationcited by 326
  32. 2019On the Relationship between Self-Attention and Convolutional Layerscited by 300
  33. 2021Focal Self-attention for Local-Global Interactions in Vision Transformerscited by 288
  34. 2021Co-Scale Conv-Attentional Image Transformerscited by 224
  35. 2021Scaling Local Self-Attention for Parameter Efficient Visual Backbonescited by 220
  36. 2021Rethinking and Improving Relative Position Encoding for Vision Transformercited by 207
  37. 2022UniFormer: Unifying Convolution and Self-attention for Visual Recognitioncited by 206
  38. 2021Hypercorrelation Squeeze for Few-Shot Segmentationcited by 193

50 most cited of 67 All 67 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 6; 2023: 8; 2024: 3; 2025: 4; 2026: 6.

27 papers.

Sort:

By area:

  1. 2022CoBEVT: Cooperative Bird's Eye View Semantic Segmentation with Sparse Transformerscited by 227
  2. 2022More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsitycited by 142
  3. 2023TransNeXt: Robust Foveal Visual Perception for Vision Transformerscited by 61
  4. 2023SG-Former: Self-guided Transformer with Evolving Token Reallocationcited by 32
  5. 2022HiFuse: Hierarchical Multi-Scale Feature Fusion Network for Medical Image Classificationcited by 30
  6. 2024PeLK: Parameter-efficient Large Kernel ConvNets with Peripheral Convolutioncited by 28
  7. 2022EATFormer: Improving Vision Transformer Inspired by Evolutionary Algorithmcited by 27
  8. 2023Lightweight Vision Transformer with Bidirectional Interactioncited by 25
  9. 2025OverLoCK: An Overview-first-Look-Closely-next ConvNet with Context-Mixing Dynamic Kernelscited by 25
  10. 2023DAT++: Spatially Dynamic Vision Transformer with Deformable Attentioncited by 21
  11. 2023GLH-Water: A Large-Scale Dataset for Global Surface Water Detection in Large-Size Very-High-Resolution Satellite Imagerycited by 16
  12. 2023A Dual-Stream Neural Network Explains the Functional Segregation of Dorsal and Ventral Visual Pathways in Human Brainscited by 12
15 more
  1. 2025Look, Focus, Act: Efficient and Robust Robot Learning via Human Gaze and Foveated Vision Transformerscited by 11
  2. 2024LookHere: Vision Transformers with Directed Attention Generalize and Extrapolatecited by 10
  3. 20243D Geometric Shape Assembly via Efficient Point Cloud Matchingcited by 9
  4. 2026LLMind: Bio-inspired Training-free Adaptive Visual Representations for Vision-Language Modelscited by 7
  5. 2023Rethinking Local Perception in Lightweight Vision Transformercited by 5
  6. 2025Segment This Thing: Foveated Tokenization for Efficient Point-Prompted Segmentationcited by 5
  7. 2023Human Vision Based 3D Point Cloud Semantic Segmentation of Large-Scale Outdoor Scenecited by 4
  8. 2022Progressive Learning with Cross-Window Consistency for Semi-Supervised Semantic Segmentationcited by 3
  9. 2026Foveated Reasoning: Stateful, Action-based Visual Focusing for Vision-Language Modelscited by 3
  10. 2022EHSNet: End-to-End Holistic Learning Network for Large-Size Remote Sensing Image Semantic Segmentationcited by 1
  11. 2025SEDA: A Self-Adapted Entity-Centric Data Augmentation for Boosting Gird-based Discontinuous NER Modelscited by 0
  12. 2026PFGNet: A Fully Convolutional Frequency-Guided Peripheral Gating Network for Efficient Spatiotemporal Predictive Learningcited by 0
  13. 2026Deep Hierarchical Knowledge Loss for Fault Intensity Diagnosiscited by 0
  14. 2026Advancing Vision Transformer with Enhanced Spatial Priorscited by 0
  15. 2026Entropy-Guided Self-Supervised Learning for Medical Image Classificationcited by 0