Exploring diffusion time-steps for unsupervised representation learning
Representation learning is all about discovering the hidden modular attributes that generate the data faithfully. We explore the potential of Denoising Diffusion Probabilistic Model (DM) in unsupervised learning of the modular attributes. We build a theoretical framework that connects the diffusion...
Saved in:
Main Authors: | YUE, Zhongqi, WANG, Jiankun, SUN, Qianru, JI, Lei, CHANG, Eric I-Chao, ZHANG, Hanwang |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2024
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/9215 https://ink.library.smu.edu.sg/context/sis_research/article/10221/viewcontent/3386_exploring_diffusion_time_steps__1_.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
Similar Items
-
Few-shot learner parameterization by diffusion time-steps
by: YUE, Zhongqi, et al.
Published: (2024) -
Transporting causal mechanisms for unsupervised domain adaptation
by: YUE, Zhongqi, et al.
Published: (2021) -
Self-supervised learning disentangled group representation as feature
by: WANG, Tan, et al.
Published: (2021) -
Diffusion time-step curriculum for one image to 3D generation
by: YI, Xuanyu, et al.
Published: (2024) -
Prototypical contrastive learning of unsupervised representations
by: LI, Junnan, et al.
Published: (2021)