English
Related papers

Related papers: Fast Training of Diffusion Models with Masked Tran…

200 papers

Diffusion models have demonstrated remarkable performance in image and video synthesis. However, scaling them to high-resolution inputs is challenging and requires restructuring the diffusion pipeline into multiple independent components,…

Computer Vision and Pattern Recognition · Computer Science 2024-06-13 Ivan Skorokhodov , Willi Menapace , Aliaksandr Siarohin , Sergey Tulyakov

Panoptic and instance segmentation networks are often trained with specialized object detection modules, complex loss functions, and ad-hoc post-processing steps to manage the permutation-invariance of the instance masks. This work builds…

Computer Vision and Pattern Recognition · Computer Science 2024-07-17 Wouter Van Gansbeke , Bert De Brabandere

Masked diffusion models have shown promising performance in generating high-quality samples in a wide range of domains, but accelerating their sampling process remains relatively underexplored. To investigate efficient samplers for masked…

Machine Learning · Computer Science 2026-04-23 Satoshi Hayakawa , Yuhta Takida , Masaaki Imaizumi , Hiromi Wakaki , Yuki Mitsufuji

Despite the success of transformers on various computer vision tasks, they suffer from excessive memory and computational cost. Some works present dynamic vision transformers to accelerate inference by pruning redundant tokens. A key to…

Computer Vision and Pattern Recognition · Computer Science 2023-10-27 Fengyuan Shi , Limin Wang

Tokenizing images into compact visual representations is a key step in learning efficient and high-quality image generative models. We present a simple diffusion tokenizer (DiTo) that learns compact visual representations for image…

Computer Vision and Pattern Recognition · Computer Science 2025-01-31 Yinbo Chen , Rohit Girdhar , Xiaolong Wang , Sai Saketh Rambhatla , Ishan Misra

Machine learning is typically framed from a perspective of i.i.d., and more importantly, isolated data. In parts, federated learning lifts this assumption, as it sets out to solve the real-world challenge of collaboratively learning a…

Machine Learning · Computer Science 2024-07-19 Subarnaduti Paul , Lars-Joel Frey , Roshni Kamath , Kristian Kersting , Martin Mundt

In this work, we investigate the capability of generating images from pre-trained diffusion models at much higher resolutions than the training image sizes. In addition, the generated images should have arbitrary image aspect ratios. When…

Computer Vision and Pattern Recognition · Computer Science 2023-10-12 Yingqing He , Shaoshu Yang , Haoxin Chen , Xiaodong Cun , Menghan Xia , Yong Zhang , Xintao Wang , Ran He , Qifeng Chen , Ying Shan

Masked diffusion models (MDMs) have emerged as a promising alternative to autoregressive models (ARMs) for language modeling. However, MDMs are known to learn substantially more slowly than ARMs, which may become problematic when scaling…

Machine Learning · Computer Science 2026-05-14 Chunsan Hong , Sanghyun Lee , Chieh-Hsin Lai , Satoshi Hayakawa , Yuhta Takida , Yuki Mitsufuji , Seungryong Kim , Jong Chul Ye

Latent diffusion models (LDMs) dominate high-quality image generation, yet integrating representation learning with generative modeling remains a challenge. We introduce a novel generative image modeling framework that seamlessly bridges…

Computer Vision and Pattern Recognition · Computer Science 2026-01-23 Theodoros Kouzelis , Efstathios Karypidis , Ioannis Kakogeorgiou , Spyros Gidaris , Nikos Komodakis

Diffusion models have shown remarkable performance on many generative tasks. Despite recent success, most diffusion models are restricted in that they only allow linear transformation of the data distribution. In contrast, broader family of…

Machine Learning · Computer Science 2024-06-04 Grigory Bartosh , Dmitry Vetrov , Christian A. Naesseth

Discrete diffusion models enable parallel token sampling for faster inference than autoregressive approaches. However, prior diffusion models use a decoder-only architecture, which requires sampling algorithms that invoke the full network…

Machine Learning · Computer Science 2025-10-28 Marianne Arriola , Yair Schiff , Hao Phung , Aaron Gokaslan , Volodymyr Kuleshov

Augmentation for dense prediction typically relies on either sample mixing or generative synthesis. Mixing improves robustness but misaligned masks yield soft label ambiguity. Diffusion synthesis increases apparent diversity but, when…

Computer Vision and Pattern Recognition · Computer Science 2025-11-06 Pengyu Jie , Wanquan Liu , Rui He , Yihui Wen , Deyu Meng , Chenqiang Gao

Diffusion models offer stable training and state-of-the-art performance for deep generative modeling tasks. Here, we consider their use in the context of multivariate subsurface modeling and probabilistic inversion. We first demonstrate…

Computer Vision and Pattern Recognition · Computer Science 2026-01-28 Roberto Miele , Niklas Linde

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. This paper shows that…

Computer Vision and Pattern Recognition · Computer Science 2023-08-22 Weilai Xiang , Hongyu Yang , Di Huang , Yunhong Wang

As the deep learning revolution marches on, self-supervised learning has garnered increasing attention in recent years thanks to its remarkable representation learning ability and the low dependence on labeled data. Among these varied…

Computer Vision and Pattern Recognition · Computer Science 2024-01-10 Siyuan Li , Luyuan Zhang , Zedong Wang , Di Wu , Lirong Wu , Zicheng Liu , Jun Xia , Cheng Tan , Yang Liu , Baigui Sun , Stan Z. Li

Deep generative models have garnered significant attention in low-level vision tasks due to their generative capabilities. Among them, diffusion model-based solutions, characterized by a forward diffusion process and a reverse denoising…

Computer Vision and Pattern Recognition · Computer Science 2025-02-26 Chunming He , Yuqi Shen , Chengyu Fang , Fengyang Xiao , Longxiang Tang , Yulun Zhang , Wangmeng Zuo , Zhenhua Guo , Xiu Li

As the deep learning revolution marches on, masked modeling has emerged as a distinctive approach that involves predicting parts of the original data that are proportionally masked during training, and has demonstrated exceptional…

Image and Video Processing · Electrical Eng. & Systems 2025-06-25 Qinrong Cai , Yu Guan , Zhibo Chen , Dong Liang , Qiuyun Fan , Qiegen Liu

The latent space of diffusion model mostly still remains unexplored, despite its great success and potential in the field of generative modeling. In fact, the latent space of existing diffusion models are entangled, with a distorted mapping…

Machine Learning · Computer Science 2024-07-17 Jaehoon Hahm , Junho Lee , Sunghyun Kim , Joonseok Lee

This paper shows that masked autoencoders (MAE) are scalable self-supervised learners for computer vision. Our MAE approach is simple: we mask random patches of the input image and reconstruct the missing pixels. It is based on two core…

Computer Vision and Pattern Recognition · Computer Science 2021-12-21 Kaiming He , Xinlei Chen , Saining Xie , Yanghao Li , Piotr Dollár , Ross Girshick

Transformer-based Diffusion Probabilistic Models (DPMs) have shown more potential than CNN-based DPMs, yet their extensive computational requirements hinder widespread practical applications. To reduce the computation budget of…

Computer Vision and Pattern Recognition · Computer Science 2024-11-01 Xinwang Chen , Ning Liu , Yichen Zhu , Feifei Feng , Jian Tang