Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
[Survey] Masked Modeling for Self-supervised Representation Learning on Vision and Beyond (https://arxiv.org/abs/2401.00897)
| Date | Stars |
|---|---|
| 2026-07-24 | 354 |
| 2026-07-25 | 354 |
| 2026-07-28 | 354 |
| 2026-07-30 | 354 |
| 2026-08-06 | 354 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Awesome Masked Modeling for Self-supervised Vision Represention and Beyond
[](https://awesome.re)  [](https://github.com/Lupin1998/Awesome-MIM/graphs/commit-activity)  
## Introduction
**We summarize awesome Masked Image Modeling (MIM) and relevent Masked Modeling methods proposed for self-supervised representation learning.** *Welcome to add relevant masked modeling paper to our project!*
This project is a part of our **survey on masked modeling methods** ([arXiv](https://arxiv.org/abs/2401.00897)). The list of awesome MIM methods is summarized in chronological order and is on updating. If you find any typos or any missed paper, please feel free to open an issue or send a pull request. Currently, our survey is on updating and here is the [latest version](https://github.com/Lupin1998/Awesome-MIM/blob/master/files/Survey_on_Masked_Modeling_Latest_Version.pdf).
* To find related papers and their relationships, check out [Connected Papers](https://www.connectedpapers.com/), which visualizes the academic field in a graph representation.
* To export BibTeX citations of papers, check out [arXiv](https://arxiv.org/) or [Semantic Scholar](https://www.semanticscholar.org/) of the paper for professional reference formats.
<p align="center" width="100%">
<img src='https://github.com/Lupin1998/Awesome-MIM/assets/44519745/226171ad-0d9d-4492-9abf-7c8af0379af6' width="100%">
</p>
Research in self-supervised learning can be broadly categorized into Generative and Discriminative paradigms. We reviewed major SSL research since 2008 and found that SSL has followed distinct developmental trajectories and stages across time periods and modalities. Since 2018, SSL in NLP has been dominated by generative masked language modeling, which remains mainstream. In computer vision, discriminative contrastive learning dominated from 2018 to 2021 before masked image modeling gained prominence after 2022.
## Table of Contents
- [Awesome Masked Modeling for Self-supervised Vision Represention and Beyond](#awesome-masked-modeling-for-self-supervised-vision-represention-and-beyond)
- [Introduction](#introduction)
- [Table of Contents](#table-of-contents)
- [Fundamental MIM Methods](#fundamental-mim-methods)
- [MIM for Transformers](#mim-for-transformers)
- [MIM with Constrastive Learning](#mim-with-constrastive-learning)
- [MIM for Transformers and CNNs](#mim-for-transformers-and-cnns)
- [MIM with Advanced Masking](#mim-with-advanced-masking)
- [MIM for Multi-Modality](#mim-for-multi-modality)
- [MIM for Vision Generalist Model](#mim-for-vision-generalist-model)
- [Unified Representation and Image Generation](#unified-representation-and-image-generation)
- [Image Generation](#image-generation)
- [MIM for CV Downstream Tasks](#mim-for-cv-downstream-tasks)
- [Object Detection](#object-detection)
- [Video Rrepresentation](#video-rrepresentation)
- [Knowledge Distillation and Few-shot Classification](#knowledge-distillation-and-few-shot-classification)
- [Efficient Fine-tuning](#efficient-fine-tuning)
- [Medical Image](#medical-image)
- [Face Recognition](#face-recognition)
- [Scene Text Recognition (OCR)](#scene-text-recognition-ocr)
- [Remote Sensing Image](#remote-sensing-image)
- [3D Representation Learning](#3d-representation-learning)
- [Depth Estimation](#depth-estimation)
- [Audio and Speech](#audio-and-speech)
- [AI for Science](#ai-for-science)
- [Protein](#protein)
- [Chemistry](#chemistry)
- [Physics](#physics)
- [Neuroscience Learning](#time-series-and-neuroscience-learning)
- [ReinforceExcerpt of 131,824 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:6bea1b581b99e423, topic:representation-learning, desc:representation learning, readme:representation learning
matched fp:6bea1b581b99e423, topic:deep-learning
matched fp:6bea1b581b99e423, topic:gpt
matched fp:6bea1b581b99e423, topic:computer-vision, readme:computer vision, readme:object detection