mlsanityData to 7 Oct 2026

Image Transformer

arXiv 1802.05751 ↗First posted 15 Feb 2018cs.CVcited by 770

Not on the map. Why?

Cited by 54 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Image generation has been successfully cast as an autoregressive sequence generation or transformation problem. Recent work has shown that self-attention is an effective way of modeling textual sequences. In this work, we generalize a recently proposed model architecture based on self-attention, the Transformer, to a sequence modeling formulation of image generation with a tractable likelihood. By restricting the self-attention mechanism to attend to local neighborhoods we significantly increase the size of images the model can process in practice, despite maintaining significantly larger receptive fields per layer than typical convolutional neural networks. While conceptually simple, our generative models significantly outperform the current state of the art in image generation on ImageNet, improving the best published negative log-likelihood on ImageNet from 3.83 to 3.77. We also present results on image super-resolution with a large magnification ratio, applying an encoder-decoder configuration of our architecture. In a human evaluation study, we find that images generated by our super-resolution model fool human observers three times more often than the previous state of the art.

Key facts. Cited by 770 papers in the map (data through 7 Oct 2026). First posted on arXiv 15 Feb 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 252; 2022: 193; 2023: 118; 2024: 95; 2025: 79; 2026: 33.

770 papers.

Sort:

By area:

  1. 2022Scalable Diffusion Models with Transformerscited by 5,931
  2. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,736
  3. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,007
  4. 2021Vision Transformers for Dense Predictioncited by 1,789
  5. 2021ViViT: A Video Vision Transformercited by 1,610
  6. 2021Is Space-Time Attention All You Need for Video Understanding?cited by 1,609
  7. 2021TransUNet: Transformers Make Strong Encoders for Medical Image Segmentationcited by 1,552
  8. 2021Image Super-Resolution via Iterative Refinementcited by 1,506
  9. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,441
  10. 2021Palette: Image-to-Image Diffusion Modelscited by 1,296
  11. 2021Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrievalcited by 1,175
  12. 2021Variational Diffusion Modelscited by 1,145
38 more
  1. 2021Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNetcited by 1,096
  2. 2021Perceiver: General Perception with Iterative Attentioncited by 1,089
  3. 2022MaskGIT: Masked Generative Image Transformercited by 1,082
  4. 2021Transformers in Vision: A Surveycited by 1,009
  5. 2021CvT: Introducing Convolutions to Vision Transformerscited by 946
  6. 2021Vector Quantized Diffusion Model for Text-to-Image Synthesiscited by 773
  7. 2021Going deeper with Image Transformerscited by 759
  8. 2024Show-o: One Single Transformer to Unify Multimodal Understanding and Generationcited by 734
  9. 2024SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformerscited by 707
  10. 2022What Can Transformers Learn In-Context? A Case Study of Simple Function Classescited by 700
  11. 2021CogView: Mastering Text-to-Image Generation via Transformerscited by 691
  12. 2021Do Vision Transformers See Like Convolutional Neural Networks?cited by 671
  13. 2021Maximum Likelihood Training of Score-Based Diffusion Modelscited by 670
  14. 2021Vector-quantized Image Modeling with Improved VQGANcited by 656
  15. 2021VideoGPT: Video Generation using VQ-VAE and Transformerscited by 651
  16. 2021Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modelingcited by 647
  17. 2024Autoregressive Image Generation without Vector Quantizationcited by 644
  18. 2024Simplified and Generalized Masked Diffusion for Discrete Datacited by 606
  19. 2021Twins: Revisiting the Design of Spatial Attention in Vision Transformerscited by 565
  20. 2024Latte: Latent Diffusion Transformer for Video Generationcited by 536
  21. 2021TrackFormer: Multi-Object Tracking with Transformerscited by 515
  22. 2022Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priorscited by 487
  23. 2021LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inferencecited by 475
  24. 2021PointCLIP: Point Cloud Understanding by CLIPcited by 461
  25. 2021TransReID: Transformer-based Object Re-Identificationcited by 432
  26. 2021Transformer Trackingcited by 412
  27. 2021Conditional Positional Encodings for Vision Transformerscited by 402
  28. 2021A Survey of Transformerscited by 399
  29. 2022Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioningcited by 362
  30. 2021Random Feature Attentioncited by 350
  31. 2021FNet: Mixing Tokens with Fourier Transformscited by 343
  32. 2021ResMLP: Feedforward networks for image classification with data-efficient trainingcited by 338
  33. 2021XCiT: Cross-Covariance Image Transformerscited by 335
  34. 2021An End-to-End Transformer Model for 3D Object Detectioncited by 329
  35. 2021Focal Self-attention for Local-Global Interactions in Vision Transformerscited by 286
  36. 2025Diffusion Transformers with Representation Autoencoderscited by 275
  37. 2021TransVG: End-to-End Visual Grounding with Transformerscited by 269
  38. 2021DeepCAD: A Deep Generative Network for Computer-Aided Design Modelscited by 266

50 most cited of 770 All 770 (JSON)