# Understanding Masked Autoencoders From a Local Contrastive Perspective

arXiv: https://arxiv.org/abs/2310.01994 · HTML: https://mlsanity.com/paper/2310.01994/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 42 references that are in the map.
- First posted on arXiv 3 Oct 2023.

## Builds on (most cited first, 30 of 39)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [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)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [An Empirical Study of Training Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.02057/) (2021)
- [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017)
- [SimMIM: A Simple Framework for Masked Image Modeling](https://mlsanity.com/paper/2111.09886/) (2021)
- [CvT: Introducing Convolutions to Vision Transformers](https://mlsanity.com/paper/2103.15808/) (2021)
- [iBOT: Image BERT Pre-Training with Online Tokenizer](https://mlsanity.com/paper/2111.07832/) (2021)
- [Dense Contrastive Learning for Self-Supervised Visual Pre-Training](https://mlsanity.com/paper/2011.09157/) (2020)
- [XCiT: Cross-Covariance Image Transformers](https://mlsanity.com/paper/2106.09681/) (2021)
- [With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2104.14548/) (2021)
- [Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/2011.10043/) (2020)
- [Context Autoencoder for Self-Supervised Representation Learning](https://mlsanity.com/paper/2202.03026/) (2022)
- [Incorporating Convolution Designs into Visual Transformers](https://mlsanity.com/paper/2103.11816/) (2021)
- [Localizing Objects with Self-Supervised Transformers and no Labels](https://mlsanity.com/paper/2109.14279/) (2021)
- [Cut and Learn for Unsupervised Object Detection and Instance Segmentation](https://mlsanity.com/paper/2301.11320/) (2023)
- [Contrastive Masked Autoencoders are Stronger Vision Learners](https://mlsanity.com/paper/2207.13532/) (2022)
- [SemMAE: Semantic-Guided Masking for Learning Masked Autoencoders](https://mlsanity.com/paper/2206.10207/) (2022)
- [TokenCut: Segmenting Objects in Images and Videos with Self-supervised Transformer and Normalized Cut](https://mlsanity.com/paper/2209.00383/) (2022)

## Built on by (most cited first, 10 of 10)

- [Projection Head is Secretly an Information Bottleneck](https://mlsanity.com/paper/2503.00507/) (2025)
- [Understand Before You Generate: Self-Guided Training for Autoregressive Image Generation](https://mlsanity.com/paper/2509.15185/) (2025)
- [An Experimental Study on Exploring Strong Lightweight Vision Transformers via Masked Image Modeling Pre-Training](https://mlsanity.com/paper/2404.12210/) (2024)
- [DenoMAE2.0: Improving Denoising Masked Autoencoders by Classifying Local Patches](https://mlsanity.com/paper/2502.18202/) (2025)
- [Learning Mask Invariant Mutual Information for Masked Image Modeling](https://mlsanity.com/paper/2502.19718/) (2025)
- [Understanding and Enhancing Mask-Based Pretraining towards Universal Representations](https://mlsanity.com/paper/2509.21650/) (2025)
- [From Pixels to Components: Eigenvector Masking for Visual Representation Learning](https://mlsanity.com/paper/2502.06314/) (2025)
- [A computationally frugal open-source foundation model for thoracic disease detection in lung cancer screening programs](https://mlsanity.com/paper/2507.01881/) (2025)
- [Which Direction to Choose? An Analysis on the Representation Power of Self-Supervised ViTs in Downstream Tasks](https://mlsanity.com/paper/2509.15272/) (2025)
- [CUPID: Reconstructing UV Texture Maps for Interpretable Person-of-Interest Deepfake Detection](https://mlsanity.com/paper/2606.20302/) (2026)

## Abstract (arXiv)

Masked AutoEncoder (MAE) has revolutionized the field of self-supervised learning with its simple yet effective masking and reconstruction strategies. However, despite achieving state-of-the-art performance across various downstream vision tasks, the underlying mechanisms that drive MAE's efficacy are less well-explored compared to the canonical contrastive learning paradigm. In this paper, we first propose a local perspective to explicitly extract a local contrastive form from MAE's reconstructive objective at the patch level. And then we introduce a new empirical framework, called Local Contrastive MAE (LC-MAE), to analyze both reconstructive and contrastive aspects of MAE. LC-MAE reveals that MAE learns invariance to random masking and ensures distribution consistency between the learned token embeddings and the original images. Furthermore, we dissect the contribution of the decoder and random masking to MAE's success, revealing both the decoder's learning mechanism and the dual role of random masking as data augmentation and effective receptive field restriction. Our experimental analysis sheds light on the intricacies of MAE and summarizes some useful design methodologies, which can inspire more powerful visual self-supervised methods.