paper-with-me

Papers

Diffusion Models as Masked Autoencoders

2023-04-06 · ICCV 2023 1 · Chen Wei, Karttikeya Mangalam, Po-Yao Huang, Yanghao Li, Haoqi Fan, Hu Xu, Huiyu Wang, Cihang Xie, Alan Yuille, Christoph Feichtenhofer

There has been a longstanding belief that generation can facilitate a true understanding of visual data. In line with this, we revisit generatively pre-training visual representations in light of recent interest in denoising diffusion models. While directly pre-training with diffusion models does not produce strong representations, we condition diffusion models on masked input and formulate diffusion models as masked autoencoders (DiffMAE). Our approach is capable of (i) serving as a strong initialization for downstream recognition tasks, (ii) conducting high-quality image inpainting, and (iii) being effortlessly extended to video where it produces state-of-the-art classification accuracy. We further perform a comprehensive study on the pros and cons of design choices and build connections between diffusion models and masked autoencoders.

📄 PDF Abstract BibTeX arXiv:2304.03283

Code (1)

kimdanni/DiffMAE pytorch

Tasks

DenoisingImage Inpainting

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Latent Diffusion Models with Masked AutoEncoders

2025-07-14 · Junho Lee, Jeongwoo Shin, Hyungwook Choi, Joonseok Lee arxiv

In spite of the remarkable potential of Latent Diffusion Models (LDMs) in image generation, the desired properties and optimal design of the autoencoders have been underexplored. In this work, we analyze the role of auto…

Image Generation

Denoising Diffusion Autoencoders are Unified Self-supervised Learners

2023-03-17 · ICCV 2023 1 · Weilai Xiang, Hongyu Yang, Di Huang, Yunhong Wang

Inspired by recent advances in diffusion models, which are reminiscent of denoising autoencoders, we investigate whether they can acquire discriminative representations for classification via generative pre-training. Thi…

Contrastive LearningDenoisingImage GenerationLinear evaluation+2

Quantum Masked Autoencoders for Vision Learning

2025-11-21 · Emma Andrews, Prabhat Mishra arxiv

Classical autoencoders are widely used to learn features of input data. To improve the feature learning, classical masked autoencoders extend classical autoencoders to learn the features of the original input sample in t…

Multi-modal Latent Diffusion

2023-06-07 · Mustapha Bounoua, Giulio Franzese, Pietro Michiardi

Multi-modal data-sets are ubiquitous in modern applications, and multi-modal Variational Autoencoders are a popular family of models that aim to learn a joint representation of the different modalities. However, existing…

multimodal generation

Fast Training of Diffusion Transformer with Extreme Masking for 3D Point Clouds Generation

2023-12-12 · Shentong Mo, Enze Xie, Yue Wu, Junsong Chen 외

Diffusion Transformers have recently shown remarkable effectiveness in generating high-quality 3D point clouds. However, training voxel-based diffusion models for high-resolution 3D voxels remains prohibitively expensive…

3D GenerationDenoisingPoint Cloud Generation