Scaling Diffusion Models for Downstream Prediction
Keywords: Generative Models, Diffusion
TL;DR: Applying diffusion for prediction tasks by efficiently scaling training / test-time compute.
Abstract: In this paper, we argue that iterative computation, as exemplified by diffusion models, offers a powerful paradigm for not only image generation but also for visual perception tasks. First, we unify few of the mid-level vision tasks as image to image translations tasks ranging from depth estimation to optical flow to segmentation. Then, through extensive experiments across these tasks, we demonstrate how diffusion models scale with increased compute during both training and inference. Notably, we train various dense and Mixture of Expert models up to 2.8 billion parameters, and we utilize increased sampling steps, use various ensembling methods to increase compute at test time. Our work provides compelling evidence for the benefits of scaling compute at train and test time for diffusion models for visual perception, and by studying the scaling properties carefully, we were able to archive same performance of the state-of-the-art models with less compute.
Primary Area: generative models
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 1728
Loading