Diffusion-Based Representation Learning
Diffusion-based methods represented as stochastic differential equations on a continuous-time domain have recently proven successful as a non-adversarial generative model. Training such models relies on denoising score matching, which can be seen as multi-scale denoising autoencoders. Here, we augment the denoising score matching framework to enable representation learning without any supervised signal. GANs and VAEs learn representations by directly transforming latent codes to data samples. In contrast, the introduced diffusion-based representation learning relies on a new formulation of the denoising score matching objective and thus encodes the information needed for denoising. We illustrate how this difference allows for manual control of the level of details encoded in the representation. Using the same approach, we propose to learn an infinite-dimensional latent code that achieves improvements of state-of-the-art models on semi-supervised image classification. We also compare the quality of learned representations of diffusion score matching with other methods like autoencoder and contrastively trained systems through their performances on downstream tasks.
Code (0)
등록된 구현이 없습니다.
Tasks
Denoisingimage-classificationImage ClassificationRepresentation LearningSemi-Supervised Image ClassificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Diffusion Models and Representation Learning: A Survey
Diffusion Models are popular generative modeling methods in various vision tasks, attracting significant attention. They can be considered a unique instance of self-supervised learning methods due to their independence f…
DenoisingRepresentation LearningSelf-Supervised LearningSurveyExpanding the Role of Diffusion Models for Robust Classifier Training
Incorporating diffusion-generated synthetic data into adversarial training (AT) has been shown to substantially improve the training of robust image classifiers. In this work, we extend the role of diffusion models beyon…
Graph Representation Learning with Diffusion Generative Models
Diffusion models have established themselves as state-of-the-art generative models across various data modalities, including images and videos, due to their ability to accurately approximate complex data distributions. U…
DenoisingGraph Representation LearningRepresentation LearningCoevolving Representations in Joint Image-Feature Diffusion
Joint image-feature generative modeling has recently emerged as an effective strategy for improving diffusion training by coupling low-level VAE latents with high-level semantic features extracted from pre-trained visual…
Segment-Level Diffusion: A Framework for Controllable Long-Form Generation with Diffusion Language Models
Diffusion models have shown promise in text generation but often struggle with generating long, coherent, and contextually accurate text. Token-level diffusion overlooks word-order dependencies and enforces short output …
Contrastive LearningDecoderFormRepresentation Learning+2