search
HomeTechnology peripheralsAIHe Kaiming cooperates with MIT: A simple framework achieves the latest breakthrough in unconditional image generation

He Kaiming, the boss, has not officially joined MIT, but the first collaborative research with MIT has come out:

He developed it together with MIT teachers and students A self-conditional image generation framework was developed, named RCG (the code has been open source).

This framework structure is very simple but the effect is outstanding. It directly implements the new SOTA of unconditional image generation on the ImageNet-1K data set.

He Kaiming cooperates with MIT: A simple framework achieves the latest breakthrough in unconditional image generation

The images it generates do not require any human annotations (that is, prompt words, class labels, etc.) , and can achieve both fidelity and Have diversity.

He Kaiming cooperates with MIT: A simple framework achieves the latest breakthrough in unconditional image generation

In this way, it not only significantly improves the level of unconditional image generation, but also competes with the best current conditional generation methods.

In the words of He Kaiming’s team:

The long-standing performance gap between conditional and unconditional generation tasks was finally closed at this moment.

So, how exactly is it done?

Self-conditional generation similar to self-supervised learning

First of all, the so-called unconditional generation means that the model directly captures the data distribution generation content without the help of input signals.

This method of training is difficult, so there has always been a large performance gap with conditional generation - just like unsupervised learning cannot be compared with supervised learning

Just like the emergence of self-supervised learning , it also changes this situation

In the field of unconditional image generation, there is also a self-conditional generation method similar to the concept of self-supervised learning.

Compared with traditional unconditional generation that simply maps the noise distribution to the image distribution, this method mainly sets the pixel generation process on the representation distribution derived from the data distribution itself.

It is expected to go beyond conditional image generation and promote the development of applications such as

molecular design or drug discoverythat do not require human annotations (This is why conditional image generation is developed So good, we also need to pay attention to unconditional generation).

Now, based on this concept of self-conditional generation, He Kaiming's team first developed a

representation diffusion model RDM.

Intercepted from the image through the self-supervised image encoder, mainly used to generate low-dimensional self-supervised image representation

He Kaiming cooperates with MIT: A simple framework achieves the latest breakthrough in unconditional image generation

Its core architecture is as follows:

The first is the input layer, which is responsible for projecting the representation to the hidden dimension C, followed by N fully connected blocks, and finally an output layer, which is responsible for reprojecting the latent features of the hidden layer

(Conversion)To the original representation dimension.

Each layer includes a LayerNorm layer, a SiLU layer and a linear layer.

He Kaiming cooperates with MIT: A simple framework achieves the latest breakthrough in unconditional image generation

Such an RDM has two advantages:

One of its characteristics is that it has strong diversity, and the other is that it has very little computational overhead.

After that, the team proposed today's protagonist with the help of RDM: Representation Conditional Image Generation Architecture RCG

It is a simple self-conditional generation framework, consisting of three

Component consists of:

One is the SSL image encoder , which is used to convert the image distribution into a compact representation distribution.

One is RDM, which is used to model and sample the distribution.

Finally, there is a pixel generator MAGE, which is used to process the image according to the representation.

MAGE works by adding a random mask to the tokenized image and asking the network to reconstruct the missing token conditioned on a representation extracted from the same image

He Kaiming cooperates with MIT: A simple framework achieves the latest breakthrough in unconditional image generation

After testing, it was found that the final results showed that although the structure of this self-conditional generation framework is simple, its effect is very good

On ImageNet 256×256, RCG achieved

FID of 3.56 and IS(Inception Score) score of 186.9.

In comparison, the most powerful unconditional generation method before it has an FID score of 7.04 and an IS score of 123.5.

He Kaiming cooperates with MIT: A simple framework achieves the latest breakthrough in unconditional image generation

For RCG, it not only performs well in conditional generation, but also performs at the same level or even exceeds it when compared with baseline models in the field

Finally, without classifier guidance , RCG's results can be further improved to 3.31(FID) and 253.4(IS).

The team expressed:

These results show that conditional image generation models have great potential and may herald a new era in this field to come

Team introduction

There are three authors in this article:

He Kaiming cooperates with MIT: A simple framework achieves the latest breakthrough in unconditional image generation

##The first author is Li Tianhong, a doctoral student at MIT, who graduated from the Yao Class of Tsinghua University with his undergraduate degree

, whose research direction is cross-modal integrated sensing technology.

His personal homepage is very interesting, and he also has a collection of recipes - research and cooking are the two things he is most passionate about

He Kaiming cooperates with MIT: A simple framework achieves the latest breakthrough in unconditional image generation

Another The author is Dina Katabi, professor in the Department of Electrical Engineering and Computer Science (EECS) at MIT and director of the MIT Wireless Networks and Mobile Computing Center. She is the winner of this year's Sloan Award and has been elected as an academician of the National Academy of Sciences.

Finally, the corresponding author He Yuming will officially return to academia next year and leave Meta to join the Department of Electrical Engineering and Computer Science at MIT, where he will become colleagues with Dina Katabi. He Kaiming cooperates with MIT: A simple framework achieves the latest breakthrough in unconditional image generation

He Kaiming cooperates with MIT: A simple framework achieves the latest breakthrough in unconditional image generation Please click the following link to view the paper: https://arxiv.org/abs/2312.03701

The above is the detailed content of He Kaiming cooperates with MIT: A simple framework achieves the latest breakthrough in unconditional image generation. For more information, please follow other related articles on the PHP Chinese website!

Statement
This article is reproduced at:51CTO.COM. If there is any infringement, please contact admin@php.cn delete
AI For Runners And Athletes: We're Making Excellent ProgressAI For Runners And Athletes: We're Making Excellent ProgressApr 22, 2025 am 11:12 AM

There were some very insightful perspectives in this speech—background information about engineering that showed us why artificial intelligence is so good at supporting people’s physical exercise. I will outline a core idea from each contributor’s perspective to demonstrate three design aspects that are an important part of our exploration of the application of artificial intelligence in sports. Edge devices and raw personal data This idea about artificial intelligence actually contains two components—one related to where we place large language models and the other is related to the differences between our human language and the language that our vital signs “express” when measured in real time. Alexander Amini knows a lot about running and tennis, but he still

Jamie Engstrom On Technology, Talent And Transformation At CaterpillarJamie Engstrom On Technology, Talent And Transformation At CaterpillarApr 22, 2025 am 11:10 AM

Caterpillar's Chief Information Officer and Senior Vice President of IT, Jamie Engstrom, leads a global team of over 2,200 IT professionals across 28 countries. With 26 years at Caterpillar, including four and a half years in her current role, Engst

New Google Photos Update Makes Any Photo Pop With Ultra HDR QualityNew Google Photos Update Makes Any Photo Pop With Ultra HDR QualityApr 22, 2025 am 11:09 AM

Google Photos' New Ultra HDR Tool: A Quick Guide Enhance your photos with Google Photos' new Ultra HDR tool, transforming standard images into vibrant, high-dynamic-range masterpieces. Ideal for social media, this tool boosts the impact of any photo,

What are the TCL Commands in SQL? - Analytics VidhyaWhat are the TCL Commands in SQL? - Analytics VidhyaApr 22, 2025 am 11:07 AM

Introduction Transaction Control Language (TCL) commands are essential in SQL for managing changes made by Data Manipulation Language (DML) statements. These commands allow database administrators and users to control transaction processes, thereby

How to Make Custom ChatGPT? - Analytics VidhyaHow to Make Custom ChatGPT? - Analytics VidhyaApr 22, 2025 am 11:06 AM

Harness the power of ChatGPT to create personalized AI assistants! This tutorial shows you how to build your own custom GPTs in five simple steps, even without coding skills. Key Features of Custom GPTs: Create personalized AI models for specific t

Difference Between Method Overloading and OverridingDifference Between Method Overloading and OverridingApr 22, 2025 am 10:55 AM

Introduction Method overloading and overriding are core object-oriented programming (OOP) concepts crucial for writing flexible and efficient code, particularly in data-intensive fields like data science and AI. While similar in name, their mechanis

Difference Between SQL Commit and SQL RollbackDifference Between SQL Commit and SQL RollbackApr 22, 2025 am 10:49 AM

Introduction Efficient database management hinges on skillful transaction handling. Structured Query Language (SQL) provides powerful tools for this, offering commands to maintain data integrity and consistency. COMMIT and ROLLBACK are central to t

PySimpleGUI: Simplifying GUI Development in Python - Analytics VidhyaPySimpleGUI: Simplifying GUI Development in Python - Analytics VidhyaApr 22, 2025 am 10:46 AM

Python GUI Development Simplified with PySimpleGUI Developing user-friendly graphical interfaces (GUIs) in Python can be challenging. However, PySimpleGUI offers a streamlined and accessible solution. This article explores PySimpleGUI's core functio

See all articles

Hot AI Tools

Undresser.AI Undress

Undresser.AI Undress

AI-powered app for creating realistic nude photos

AI Clothes Remover

AI Clothes Remover

Online AI tool for removing clothes from photos.

Undress AI Tool

Undress AI Tool

Undress images for free

Clothoff.io

Clothoff.io

AI clothes remover

Video Face Swap

Video Face Swap

Swap faces in any video effortlessly with our completely free AI face swap tool!

Hot Tools

SublimeText3 English version

SublimeText3 English version

Recommended: Win version, supports code prompts!

mPDF

mPDF

mPDF is a PHP library that can generate PDF files from UTF-8 encoded HTML. The original author, Ian Back, wrote mPDF to output PDF files "on the fly" from his website and handle different languages. It is slower than original scripts like HTML2FPDF and produces larger files when using Unicode fonts, but supports CSS styles etc. and has a lot of enhancements. Supports almost all languages, including RTL (Arabic and Hebrew) and CJK (Chinese, Japanese and Korean). Supports nested block-level elements (such as P, DIV),

SublimeText3 Mac version

SublimeText3 Mac version

God-level code editing software (SublimeText3)

MinGW - Minimalist GNU for Windows

MinGW - Minimalist GNU for Windows

This project is in the process of being migrated to osdn.net/projects/mingw, you can continue to follow us there. MinGW: A native Windows port of the GNU Compiler Collection (GCC), freely distributable import libraries and header files for building native Windows applications; includes extensions to the MSVC runtime to support C99 functionality. All MinGW software can run on 64-bit Windows platforms.

Atom editor mac version download

Atom editor mac version download

The most popular open source editor