# On Data Scaling in Masked Image Modeling

arXiv: https://arxiv.org/abs/2206.04664 · HTML: https://mlsanity.com/paper/2206.04664/

## Key facts

- Cited by 46 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 51 references that are in the map.
- First posted on arXiv 9 Jun 2022.

## Builds on (most cited first, 30 of 40)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Context Encoders: Feature Learning by Inpainting](https://mlsanity.com/paper/1604.07379/) (2016)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [Big Self-Supervised Models are Strong Semi-Supervised Learners](https://mlsanity.com/paper/2006.10029/) (2020)
- [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://mlsanity.com/paper/2203.12602/) (2022)
- [Unified Perceptual Parsing for Scene Understanding](https://mlsanity.com/paper/1807.10221/) (2018)
- [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017)
- [Swin Transformer V2: Scaling Up Capacity and Resolution](https://mlsanity.com/paper/2111.09883/) (2021)
- [SimMIM: A Simple Framework for Masked Image Modeling](https://mlsanity.com/paper/2111.09886/) (2021)
- [Video Swin Transformer](https://mlsanity.com/paper/2106.13230/) (2021)
- [Semantic Understanding of Scenes through the ADE20K Dataset](https://mlsanity.com/paper/1608.05442/) (2016)
- [Scaling Vision Transformers](https://mlsanity.com/paper/2106.04560/) (2021)
- [Big Transfer (BiT): General Visual Representation Learning](https://mlsanity.com/paper/1912.11370/) (2019)

## Built on by (most cited first, 30 of 46)

- [EVA: Exploring the Limits of Masked Visual Representation Learning at Scale](https://mlsanity.com/paper/2211.07636/) (2022)
- [VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking](https://mlsanity.com/paper/2303.16727/) (2023)
- [EVA-02: A Visual Representation for Neon Genesis](https://mlsanity.com/paper/2303.11331/) (2023)
- [A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trends](https://mlsanity.com/paper/2301.05712/) (2023)
- [Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining](https://mlsanity.com/paper/2302.02318/) (2023)
- [Contrastive Masked Autoencoders are Stronger Vision Learners](https://mlsanity.com/paper/2207.13532/) (2022)
- [Exploring scalable medical image encoders beyond text supervision](https://mlsanity.com/paper/2401.10815/) (2024)
- [SVFormer: Semi-supervised Video Transformer for Action Recognition](https://mlsanity.com/paper/2211.13222/) (2022)
- [Scaling Wearable Foundation Models](https://mlsanity.com/paper/2410.13638/) (2024)
- [A Survey on Masked Autoencoder for Self-supervised Learning in Vision and Beyond](https://mlsanity.com/paper/2208.00173/) (2022)
- [Predicting Gradient is Better: Exploring Self-Supervised Learning for SAR ATR with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2311.15153/) (2023)
- [Equivariant Adaptation of Large Pretrained Models](https://mlsanity.com/paper/2310.01647/) (2023)
- [ResFormer: Scaling ViTs with Multi-Resolution Training](https://mlsanity.com/paper/2212.00776/) (2022)
- [Masked Image Modeling: A Survey](https://mlsanity.com/paper/2408.06687/) (2024)
- [MAPSeg: Unified Unsupervised Domain Adaptation for Heterogeneous Medical Image Segmentation Based on 3D Masked Autoencoding and Pseudo-Labeling](https://mlsanity.com/paper/2303.09373/) (2023)
- [SARATR-X: Toward Building A Foundation Model for SAR Target Recognition](https://mlsanity.com/paper/2405.09365/) (2024)
- [TerraFM: A Scalable Foundation Model for Unified Multisensor Earth Observation](https://mlsanity.com/paper/2506.06281/) (2025)
- [TinyMIM: An Empirical Study of Distilling MIM Pre-trained Models](https://mlsanity.com/paper/2301.01296/) (2023)
- [MIM-Refiner: A Contrastive Learning Boost from Intermediate Pre-Trained Representations](https://mlsanity.com/paper/2402.10093/) (2024)
- [DeepMIM: Deep Supervision for Masked Image Modeling](https://mlsanity.com/paper/2303.08817/) (2023)
- [Bringing Masked Autoencoders Explicit Contrastive Properties for Point Cloud Self-Supervised Learning](https://mlsanity.com/paper/2407.05862/) (2024)
- [Fewer Tokens, Greater Scaling: Self-Adaptive Visual Bases for Efficient and Expansive Representation Learning](https://mlsanity.com/paper/2511.19515/) (2025)
- [Contrastive Tuning: A Little Help to Make Masked Autoencoders Forget](https://mlsanity.com/paper/2304.10520/) (2023)
- [Towards a general-purpose foundation model for fMRI analysis](https://mlsanity.com/paper/2506.11167/) (2025)
- [Masked Modeling for Self-supervised Representation Learning on Vision and Beyond](https://mlsanity.com/paper/2401.00897/) (2023)
- [Representing Part-Whole Hierarchies in Foundation Models by Learning Localizability, Composability, and Decomposability from Anatomy via Self-Supervision](https://mlsanity.com/paper/2404.15672/) (2024)
- [OReole-FM: successes and challenges toward billion-parameter foundation models for high-resolution satellite imagery](https://mlsanity.com/paper/2410.19965/) (2024)
- [AnatoMask: Enhancing Medical Image Segmentation with Reconstruction-guided Self-masking](https://mlsanity.com/paper/2407.06468/) (2024)
- [Towards Unifying Understanding and Generation in the Era of Vision Foundation Models: A Survey from the Autoregression Perspective](https://mlsanity.com/paper/2410.22217/) (2024)
- [Where Should I Spend My FLOPS? Efficiency Evaluations of Visual Pre-training Methods](https://mlsanity.com/paper/2209.15589/) (2022)

## Abstract (arXiv)

An important goal of self-supervised learning is to enable model pre-training to benefit from almost unlimited data. However, one method that has recently become popular, namely masked image modeling (MIM), is suspected to be unable to benefit from larger data. In this work, we break this misconception through extensive experiments, with data scales ranging from 10% of ImageNet-1K to full ImageNet-22K, model sizes ranging from 49 million to 1 billion, and training lengths ranging from 125K iterations to 500K iterations. Our study reveals that: (i) Masked image modeling is also demanding on larger data. We observed that very large models got over-fitted with relatively small data; (ii) The length of training matters. Large models trained with masked image modeling can benefit from more data with longer training; (iii) The validation loss in pre-training is a good indicator to measure how well the model performs for fine-tuning on multiple tasks. This observation allows us to pre-evaluate pre-trained models in advance without having to make costly trial-and-error assessments of downstream tasks. We hope that our findings will advance the understanding of masked image modeling in terms of scaling ability.