mlsanityData to 14 Oct 2026

A Survey on Masked Autoencoder for Self-supervised Learning in Vision and Beyond

arXiv 2208.00173 ↗First posted 30 Jul 2022cs.CV cs.AI cs.LGcited by 58

Not on the map. Why?

Abstract (arXiv)

Masked autoencoders are scalable vision learners, as the title of MAE citehe2022masked, which suggests that self-supervised learning (SSL) in vision might undertake a similar trajectory as in NLP. Specifically, generative pretext tasks with the masked prediction (e.g., BERT) have become a de facto standard SSL practice in NLP. By contrast, early attempts at generative methods in vision have been buried by their discriminative counterparts (like contrastive learning); however, the success of mask image modeling has revived the masking autoencoder (often termed denoising autoencoder in the past). As a milestone to bridge the gap with BERT in NLP, masked autoencoder has attracted unprecedented attention for SSL in vision and beyond. This work conducts a comprehensive survey of masked autoencoders to shed insight on a promising direction of SSL. As the first to review SSL with masked autoencoders, this work focuses on its application in vision by discussing its historical developments, recent progress, and implications for diverse applications.

Key facts. Cited by 58 papers in the map (data through 14 Oct 2026). Builds on 105 of its 124 references that are in the map. First posted on arXiv 30 Jul 2022.

Builds on

105 of 124 references.

References · 105

  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. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  5. 2020Language Models are Few-Shot Learnerscited by 32,419
  6. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  7. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  8. 2017Proximal Policy Optimization Algorithmscited by 15,215
  9. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  10. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  11. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  12. 2017Graph Attention Networkscited by 8,923
38 more
  1. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  2. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  3. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  4. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  5. 2017Inductive Representation Learning on Large Graphscited by 6,320
  6. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  7. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
  8. 2018How Powerful are Graph Neural Networks?cited by 4,393
  9. 2021Zero-Shot Text-to-Image Generationcited by 4,288
  10. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,864
  11. 2020Exploring Simple Siamese Representation Learningcited by 2,866
  12. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,857
  13. 2015Learning Deep Features for Discriminative Localizationcited by 2,436
  14. 2021BEiT: BERT Pre-Training of Image Transformerscited by 2,375
  15. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,962
  16. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,845
  17. 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,838
  18. 2021An Empirical Study of Training Self-Supervised Vision Transformerscited by 1,616
  19. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,591
  20. 2016Context Encoders: Feature Learning by Inpaintingcited by 1,428
  21. 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,382
  22. 2022VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Trainingcited by 1,322
  23. 2018Soft Actor-Critic Algorithms and Applicationscited by 1,240
  24. 2021SimMIM: A Simple Framework for Masked Image Modelingcited by 1,153
  25. 2016Colorful Image Colorizationcited by 1,114
  26. 2021iBOT: Image BERT Pre-Training with Online Tokenizercited by 903
  27. 2019Self-Supervised Learning of Pretext-Invariant Representationscited by 808
  28. 2022data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Languagecited by 727
  29. 2021Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modelingcited by 653
  30. 2021Masked Feature Prediction for Self-Supervised Visual Pre-Trainingcited by 576
  31. 2020Reinforcement Learning with Augmented Datacited by 468
  32. 2022Masked Autoencoders for Point Cloud Self-supervised Learningcited by 459
  33. 2022GraphMAE: Self-Supervised Masked Graph Autoencoderscited by 448
  34. 2021SLIP: Self-supervision meets Language-Image Pre-trainingcited by 436
  35. 2022Masked Autoencoders As Spatiotemporal Learnerscited by 429
  36. 2021VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Expertscited by 425
  37. 2022Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Taskscited by 421
  38. 2021Early Convolutions Help Transformers See Bettercited by 396

50 most cited of 105 All 105 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 5; 2023: 23; 2024: 16; 2025: 12; 2026: 2.

58 papers.

Sort:

By area:

  1. 2023A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?cited by 84
  2. 2023One Small Step for Generative AI, One Giant Leap for AGI: A Complete Survey on ChatGPT in AIGC Eracited by 55
  3. 2024Masked Autoencoders for Microscopy are Scalable Learners of Cellular Biologycited by 52
  4. 2023RealGen: Retrieval Augmented Generation for Controllable Traffic Scenarioscited by 46
  5. 2023A Survey on Segment Anything Model (SAM): Vision Foundation Model Meets Prompt Engineeringcited by 45
  6. 2022AdaMAE: Adaptive Masking for Efficient Spatiotemporal Learning with Masked Autoencoderscited by 43
  7. 2023MAE-DFER: Efficient Masked Autoencoder for Self-supervised Dynamic Facial Expression Recognitioncited by 43
  8. 2023Towards Compact 3D Representations via Point Feature Enhancement Masked Autoencoderscited by 42
  9. 2023A Survey on Graph Diffusion Models: Generative AI in Science for Molecule, Protein and Materialcited by 35
  10. 2022Towards All-in-one Pre-training via Maximizing Multi-modal Mutual Informationcited by 31
  11. 2023Robustness of SAM: Segment Anything Under Corruptions and Beyondcited by 31
  12. 2024A Simple yet Effective Network based on Vision Transformer for Camouflaged Object and Salient Object Detectioncited by 23
38 more
  1. 2024Self-supervised Learning for Electroencephalogram: A Systematic Surveycited by 19
  2. 2023SVFAP: Self-supervised Video Facial Affect Perceivercited by 18
  3. 2023Motif-aware Attribute Masking for Molecular Graph Pre-trainingcited by 16
  4. 2023Information Flow in Self-Supervised Learningcited by 16
  5. 2024MEGA: Masked Generative Autoencoder for Human Mesh Recoverycited by 14
  6. 2025Joint Embeddings Go Temporalcited by 14
  7. 2023Masked Modeling for Self-supervised Representation Learning on Vision and Beyondcited by 13
  8. 2025CauKer: Classification Time Series Foundation Models Can Be Pretrained on Synthetic Datacited by 13
  9. 2023Non-Parametric Representation Learning with Kernelscited by 11
  10. 2023Understanding Segment Anything Model: SAM is Biased Towards Texture Rather than Shapecited by 10
  11. 2024Emerging Property of Masked Token for Effective Pre-trainingcited by 10
  12. 2023A vector quantized masked autoencoder for speech emotion recognitioncited by 8
  13. 2023Segment Anything Meets Semantic Communicationcited by 8
  14. 2023Deblurring Masked Autoencoder is Better Recipe for Ultrasound Image Recognitioncited by 8
  15. 2022Backdoor Attacks in the Supply Chain of Masked Image Modelingcited by 7
  16. 2023A vector quantized masked autoencoder for audiovisual speech emotion recognitioncited by 7
  17. 2025TinyMyo: a Tiny Foundation Model for Flexible EMG Signal Processing at the Edgecited by 7
  18. 2023Attack-SAM: Towards Attacking Segment Anything Model With Adversarial Examplescited by 5
  19. 2023SAM Meets UAP: Attacking Segment Anything Model With Universal Adversarial Perturbationcited by 4
  20. 2024Self-Supervised Learning for Time Series: Contrastive or Generative?cited by 4
  21. 2024Pre-Training Graph Contrastive Masked Autoencoders are Strong Distillers for EEGcited by 4
  22. 2025S2Vec: Self-Supervised Geospatial Embeddings for the Built Environmentcited by 4
  23. 2023Aerial Image Object Detection With Vision Transformer Detector (ViTDet)cited by 3
  24. 2024Self-Supervised Learning for Text Recognition: A Critical Surveycited by 3
  25. 2025Frequency Matters: When Time Series Foundation Models Fail Under Spectral Shiftcited by 3
  26. 2024Automatic Cranial Defect Reconstruction with Self-Supervised Deep Deformable Masked Autoencoderscited by 2
  27. 2024Membership Inference Attack Against Masked Image Modelingcited by 2
  28. 2024AMNS: Attention-Weighted Selective Mask and Noise Label Suppression for Text-to-Image Person Retrievalcited by 2
  29. 2022RGMIM: Region-Guided Masked Image Modeling for Learning Meaningful Representations from X-Ray Imagescited by 1
  30. 2022Improved Representation Learning Through Tensorized Autoencoderscited by 1
  31. 2023AI-based automated active learning for discovery of hidden dynamic processes: A use case in light microscopycited by 1
  32. 2024Cognitive resilience: Unraveling the proficiency of image-captioning models to interpret masked visual contentcited by 1
  33. 2024Cluster Specific Representation Learningcited by 1
  34. 2025MM-Prompt: Cross-Modal Prompt Tuning for Continual Visual Question Answeringcited by 1
  35. 2025GViT: Representing Images as Gaussians for Visual Recognitioncited by 1
  36. 2025Calibrated Self-supervised Vision Transformers Improve Intracranial Arterial Calcification Segmentation from Clinical CT Head Scanscited by 1
  37. 2025MM-SeR: Multimodal Self-Refinement for Lightweight Image Captioningcited by 1
  38. 2023Enhancing Robot Learning through Learned Human-Attention Feature Mapscited by 0

50 most cited of 58 All 58 (JSON)