Masked Autoencoders

Ask about this topic

Overview

Masked autoencoders study how models can learn useful representations from unlabeled data by predicting hidden patches, tokens, or time segments. Common approaches encode only the visible input and use a decoder for reconstruction, while newer variants guide masking with domain structure, predict latent features, or combine reconstruction with contrastive and cross-modal learning. These methods are used across images, video, medical scans, audio, biosignals, and remote sensing, with evaluations spanning tasks such as ImageNet classification, NTU action recognition, and medical image segmentation. A central open question is when reconstruction pretraining transfers better than alternatives: results depend on the masking strategy, data scale, and downstream task, and faithful reconstruction does not always produce the most useful features.

Latest papers

CardsList

103 papers12 papers in the last four weeks, down 8% on the four weeks before. 0.1% of all new papers.

  1. Observability-Aligned Evidential Masked Pretraining for Reliable VRU Motion Prediction

    Oct 29, 2026Shang Gao, Franz Götz-Hahn, Konrad Doll +1Uncertainty QuantificationMasked Autoencoders

    Intelligent Embedded Systems, University of Kassel, Germany · Aschaffenburg University of Applied Sciences, Germany

  2. SpectralTF-MAE: A Pre-trained Spectral Foundation Model for Tokamak Fusion Plasma Diagnostics

    Oct 28, 2026Xiao Wang, Zhijie Lu, Duoqing Yang +7Representation LearningSelf-Supervised Pre-Training

    School of Computer Science and Technology, Anhui University, Hefei 230601, China · Institute of Plasma Physics, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230031, China · New Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China

  3. WildMAE: Structure-Aware Masked Autoencoding for Wildlife Image Reconstruction

    Oct 20, 2026Yicheng Zhang, Yujie Jin, Ke Zhang +1Masked Image ModelingMasked Autoencoders

    The Chinese University of Hong Kong, Shenzhen

  4. Data-Efficient ConvNeXt Pretraining for High-Resolution Sentinel-1 GRD SAR Representation Learning

    Oct 15, 2026Yuki Natsume, Sang-Ho Yun, Chai Kiat YeoSelf-Supervised Pre-TrainingMasked Autoencoders

    College of Computing and Data Science, Nanyang Technological University, Singapore · Earth Observatory of Singapore, Nanyang Technological University, Singapore · Asian School of the Environment, Nanyang Technological University, Singapore +1

  5. Variable Input Masked Autoencoders for Wrist-Worn Accelerometry

    Oct 12, 2026Harish Haresamudram, Wanting Mao, Aditya Radhakrishnan +2Self-Supervised Time Series Representation LearningTime-Series Foundation Models

    University of Illinois Urbana-Champaign · Google

  6. DIME: Scaling Facial Representation Learning via Differential Masked Autoencoding

    Oct 12, 2026Hao Yu, Haoyu Chen, Hui Wei +3Visual Representation LearningSelf-Supervised Visual Representation Learning

    ELLIS Institute Finland and CMVS, University of Oulu, Finland · DISI, University of Trento, Italy

  7. Growing to See: Efficient Pretraining of Self-Supervised Vision Transformers

    Oct 12, 2026Amir Mohammad Karimi Mamaghan, Ferdinand Kapl, Andrea Dittadi +4Self-Supervised Visual Representation LearningSelf-Supervised Pre-Training

    KTH Royal Institute of Technology · Helmholtz AI, Munich · Technical University of Munich +3

  8. Event-based Action Recognition by Pre-Training on Multi-Frame Representations

    Oct 9, 2026Emma Norrby, Tomas Wilkinson, Per Nyblom +1Event-Based VisionMasked Autoencoders

    Swedish Defence Research Agency (FOI), Linköping, Sweden

  9. HuC-VideoMAE: Human-Centric Video Masked Autoencoding from synthetic data

    Oct 6, 2026Ricardo Pizarro, Roberto Valle, José M. Buenaposada +2Synthetic Data PretrainingMasked Autoencoders

    Universidad de Alcal´a, Alcal´a de Henares, Spain · Universidad Polit´ecnica de Madrid, Madrid, Spain · Universidad Rey Juan Carlos, M´ostoles, Spain

  10. LEON: Location Embeddings from OSM Neighborhoods via Hexagonal Graph Masked Autoencoders

    Oct 4, 2026Szymon Soltysiak, Radoslaw Malek, Jedrzej Kusnierz +3Masked AutoencodersGeospatial Representation Learning

    Department of Artificial Intelligence, Wroclaw University of Science and Technology, Wroclaw, Poland

  11. The hidden advantage of mask resampling: a theory of masked autoencoders

    Oct 1, 2026Jorge Medina Moreira, Lorenzo Bardone, Lenka ZdeborováMasked AutoencodersMasked Language Modeling

    Statistical Physics of Computation Laboratory, École Polytechnique Fédérale de Lausanne (EPFL), CH-1015 Lausanne, Switzerland

  12. I Have a Stream: Making Self-Supervised Learning Work on Continuous Video

    Sep 30, 2026Ivan Martinović, Lukas Knobel, Yuki M. AsanoMasked AutoencodersSelf-Supervised Learning

    Faculty of Electrical Engineering and Computing, University of Zagreb · Fundamental AI Lab, University of Technology Nuremberg

  13. Masked Swingers: Harnessing Data Augmentation to Advance Autoencoders for Self-Supervised Learning

    Sep 29, 2026Anthony Fuller, Scott C. Lowe, Daniel G. Kyrollos +3Masked AutoencodersInvariant Representation Learning

    Vector Institute · Carleton University · University of Guelph +1

  14. Physical Cross-Modal Masked Autoencoding for Seismic-to-Well Representation Learning

    Sep 28, 2026Meher Gajula, Keyla Gonzalez, Ben Lasscock +1Cross-Modal Representation LearningRepresentation Learning

  15. What masking geometry works best for EEG foundation models?

    Sep 27, 2026Pierre Guetschel, Bruno Aristimunha, Yassine El Ouahidi +3Masked AutoencodersEEG Decoding

    Donders Institute for Brain, Cognition and Behaviour Radboud University Nijmegen, The Netherlands · Yneuro, University of California San Diego, Paris, France · Lab-STICC, IMT Atlantique Brest, France +2

  16. BarcodeMAE+: Rethinking Masked Pretraining and Global Representations for DNA Barcode Foundation Models

    Sep 26, 2026Monireh Safari, Pablo Millan Arias, Scott C. Lowe +3Molecular Representation LearningMasked Autoencoders

    Cheriton School of Computer Science, University of Waterloo, Ontario, Canada · Vector Institute, Ontario, Canada · School of Computing Science, Simon Fraser University, British Columbia, Canada +2

  17. Structure-Guided Masked Autoencoders for Ultra-High Resolution Scientific Image Understanding

    Sep 25, 2026Enzhi Zhang, Du Wu, Rui Zhong +18Masked AutoencodersMasked Image Modeling

    Hokkaido University, Japan · RIKEN Center for Computational Science (R-CCS), Japan · Oak Ridge National Laboratory, USA +4

  18. Fed-ReMasker: Federated Tabular Imputation under Feature-Level Missingness

    Sep 23, 2026Ioannis Papathanail, Rooholla Poursoleymani, Lubnaa Abdur Rahman +1Incomplete Data ImputationMasked Autoencoders

    ARTORG Center for Biomedical Engineering Research University of Bern, Bern, Switzerland · Graduate School for Cellular and Biomedical Sciences University of Bern, Bern, Switzerland

  19. MiTHras: Task-specific Hierarchical Semi-supervised Contrastive Masked Autoencoder for Mitotic Figure Analysis

    Sep 21, 2026Trinh T. L. Vuong, Simon Graham, Quoc Dang Vu +5Contrastive LearningMasked Autoencoders

    Department of Pathology, Brigham and Women’s Hospital, Harvard Medical School, Boston, USA · Histofy Ltd, Coventry, United Kingdom · Department of Pathology, University Medical Center Ho Chi Minh City, Ho Chi Minh City, Vietnam +1

  20. Mask 2D-3D: Adaptive Dual-Masked Autoencoder Network for Image-to-Point Cloud Registration

    Sep 16, 2026Zhixin Cheng, Jiacheng Deng, Xiaotian Yin +3Masked AutoencodersPoint Cloud Registration

    School of Computer Science and Technology, Hefei University of Technology, Hefei 230601, China · School of Information Science and Technology, University of Science and Technology of China, Hefei 230027, China · Institute of Advanced Technology, University of Science and Technology of China, Hefei 230027, China

  21. MAETrack: Unleashing the Potential of Pretrained Geometric Priors for 3D Single Object Tracking

    Sep 15, 2026Sifan Zhou, Qiwei Wang, Linyue Tan +3Masked AutoencodersSelf-Supervised Pre-Training

    School of Automation, Southeast University, Nanjing, 210096, China · Key Laboratory of Measurement and Control of Complex Systems of Engineering, Ministry of Education, Nanjing, 210096, China · Harbin Institute of Technology Shenzhen, Shenzhen, 518000, China +1

  22. Which Pretext Task Transfers? Self-Supervised Pretraining Objectives for Lung Ultrasound

    Sep 15, 2026Moein Heidari, Junbo Rao, Jai Choraria +3Contrastive LearningMasked Autoencoders

    University of British Columbia, Vancouver, BC, Canada · Rutgers Cancer Institute of New Jersey, New Brunswick, NJ, USA

  23. Rethinking Procedural Audio Pre-training: Source Scaling and Objective Adaptation

    Sep 14, 2026Jiajun Peng, Fengrui Liu, Xinyu Liu +1Synthetic Data PretrainingAudio Representation Learning

    School of Data Science, University of Science and Technology of China, Hefei 230026, China · School of Computer Science and Technology, East China Normal University, Shanghai 200062, China · School of Psychology, Shanghai Jiao Tong University, Shanghai 200030, China

  24. MANAS-2: Constrained Reconstruction for EEG Foundation Models

    Sep 12, 2026Arvasu Kulkarni, Aditya Ray Mishra, Jeet Bandhu Lahiri +5ElectroencephalographyMasked Autoencoders

    Mannas AI · Indian Institute of Technology, Mandi

  25. Pretraining for Sample-Efficient Neural Interfaces

    Sep 11, 2026Ben Tang, Zachary Spalding, Gregory B. CoganBrain-Computer InterfacesSelf-Supervised Pre-Training

    Duke University, Durham, NC

  26. Reading the Whole Heart: Latent-Attention Masked Autoencoders for Multimodal Cardiac Representation Learning

    Sep 10, 2026Andrea Agostini, Simon Böhi, Moritz Vandenhirtz +7Masked AutoencodersHealthcare

    Department of Computer Science, ETH Zurich, Switzerland · Department of Biomedical Engineering, University of Basel, Switzerland

  27. MEOX: Compact Multimodal Mixture-of-Experts for Earth Observation

    Sep 4, 2026Mohanad AlbughdadiMasked AutoencodersGeospatial Representation Learning

    European Centre for Medium-Range Weather Forecasts Bonn, Germany

  28. AgriField-40K: Adapting Vision Models to Agriculture With Efficient Continual Pretraining

    Aug 8, 2026Vasileios Tzouras, Paraskevas Pegios, Lazaros NalpantidisAgricultural Image AnalysisMasked Autoencoders

    Technical University of Denmark (DTU), Kongens Lyngby, Denmark · Pioneer Centre for Artificial Intelligence, Copenhagen, Denmark

  29. Curia-MAE: Multi-Modal Multi-Anatomy MAE Pre-Training for 3D Medical Image Segmentation

    Aug 6, 2026Théo Danielou, Antoine Saporta, Léo Alberge +1Medical Imaging Foundation ModelsMasked Autoencoders

    Raidium

  30. ReMiX-MAE: Learning Missing-Channel Cross-Modal Representations from RGB-Only Clinical Facial Videos for Sympathetic-Mediated Pain Assessment

    Aug 3, 2026Nan Bi, Taoyue Wang, Lijun Yin +1Missing-Modality LearningMasked Autoencoders

    School of Computing, Binghamton University, Binghamton, NY, USA · Department of Anesthesiology, SUNY Upstate Medical University, Syracuse, NY, USA