# Diffusion Model as Representation Learner

arXiv: https://arxiv.org/abs/2308.10916 · HTML: https://mlsanity.com/paper/2308.10916/

## Key facts

- Cited by 95 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models.
- Builds on 64 of its 90 references that are in the map.
- First posted on arXiv 21 Aug 2023.

## Placed in

- Diffusion models / [Diffusion foundations and sampling](https://mlsanity.com/diffusion/diffusion-foundations-and-sampling/)

## Builds on (most cited first, 30 of 64)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [Video Diffusion Models](https://mlsanity.com/paper/2204.03458/) (2022)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [Asynchronous Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1602.01783/) (2016)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [Spectral Normalization for Generative Adversarial Networks](https://mlsanity.com/paper/1802.05957/) (2018)
- [Deep High-Resolution Representation Learning for Visual Recognition](https://mlsanity.com/paper/1908.07919/) (2019)
- [Learning deep representations by mutual information estimation and maximization](https://mlsanity.com/paper/1808.06670/) (2018)
- [Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer](https://mlsanity.com/paper/1612.03928/) (2016)
- [Relational Knowledge Distillation](https://mlsanity.com/paper/1904.05068/) (2019)
- [Contrastive Representation Distillation](https://mlsanity.com/paper/1910.10699/) (2019)
- [On Distillation of Guided Diffusion Models](https://mlsanity.com/paper/2210.03142/) (2022)
- [LLM-Pruner: On the Structural Pruning of Large Language Models](https://mlsanity.com/paper/2305.11627/) (2023)

## Built on by (most cited first, 30 of 95)

- [Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think](https://mlsanity.com/paper/2410.06940/) (2024)
- [Representation Entanglement for Generation: Training Diffusion Transformers Is Much Easier Than You Think](https://mlsanity.com/paper/2507.01467/) (2025)
- [AA-CLIP: Enhancing Zero-shot Anomaly Detection via Anomaly-Aware CLIP](https://mlsanity.com/paper/2503.06661/) (2025)
- [Adapting Visual-Language Models for Generalizable Anomaly Detection in Medical Images](https://mlsanity.com/paper/2403.12570/) (2024)
- [Priority-Centric Human Motion Generation in Discrete Latent Space](https://mlsanity.com/paper/2308.14480/) (2023)
- [MindBridge: A Cross-Subject Brain Decoding Framework](https://mlsanity.com/paper/2404.07850/) (2024)
- [No Other Representation Component Is Needed: Diffusion Transformers Can Provide Representation Guidance by Themselves](https://mlsanity.com/paper/2505.02831/) (2025)
- [Diffusion Models and Representation Learning: A Survey](https://mlsanity.com/paper/2407.00783/) (2024)
- [Boosting Generative Image Modeling via Joint Image-Feature Synthesis](https://mlsanity.com/paper/2504.16064/) (2025)
- [Track4Gen: Teaching Video Diffusion Models to Track Points Improves Video Generation](https://mlsanity.com/paper/2412.06016/) (2024)
- [Image Generators are Generalist Vision Learners](https://mlsanity.com/paper/2604.20329/) (2026)
- [Video Diffusion Models: A Survey](https://mlsanity.com/paper/2405.03150/) (2024)
- [textitRevelio: Interpreting and leveraging semantic information in diffusion models](https://mlsanity.com/paper/2411.16725/) (2024)
- [Not All Diffusion Model Activations Have Been Evaluated as Discriminative Features](https://mlsanity.com/paper/2410.03558/) (2024)
- [USP: Unified Self-Supervised Pretraining for Image Generation and Understanding](https://mlsanity.com/paper/2503.06132/) (2025)
- [AV-Link: Temporally-Aligned Diffusion Features for Cross-Modal Audio-Video Generation](https://mlsanity.com/paper/2412.15191/) (2024)
- [MeLFusion: Synthesizing Music from Image and Language Cues using Diffusion Models](https://mlsanity.com/paper/2406.04673/) (2024)
- [PartSTAD: 2D-to-3D Part Segmentation Task Adaptation](https://mlsanity.com/paper/2401.05906/) (2024)
- [Understanding Representation Dynamics of Diffusion Models via Low-Dimensional Modeling](https://mlsanity.com/paper/2502.05743/) (2025)
- [Human-Object Interaction Detection Collaborated with Large Relation-driven Diffusion Models](https://mlsanity.com/paper/2410.20155/) (2024)
- [From Image to Video: An Empirical Study of Diffusion Representations](https://mlsanity.com/paper/2502.07001/) (2025)
- [On Denoising Walking Videos for Gait Recognition](https://mlsanity.com/paper/2505.18582/) (2025)
- [Learning Diffusion Models with Flexible Representation Guidance](https://mlsanity.com/paper/2507.08980/) (2025)
- [Open-Vocabulary 3D Semantic Segmentation with Text-to-Image Diffusion Models](https://mlsanity.com/paper/2407.13642/) (2024)
- [Visual Lexicon: Rich Image Features in Language Space](https://mlsanity.com/paper/2412.06774/) (2024)
- [VDT-Auto: End-to-end Autonomous Driving with VLM-Guided Diffusion Transformers](https://mlsanity.com/paper/2502.20108/) (2025)
- [Discriminative Probing and Tuning for Text-to-Image Generation](https://mlsanity.com/paper/2403.04321/) (2024)
- [Residual Connections Harm Generative Representation Learning](https://mlsanity.com/paper/2404.10947/) (2024)
- [Pre-trained Text-to-Image Diffusion Models Are Versatile Representation Learners for Control](https://mlsanity.com/paper/2405.05852/) (2024)
- [SARA: Structural and Adversarial Representation Alignment for Training-efficient Diffusion Models](https://mlsanity.com/paper/2503.08253/) (2025)

## Abstract (arXiv)

Diffusion Probabilistic Models (DPMs) have recently demonstrated impressive results on various generative tasks.Despite its promises, the learned representations of pre-trained DPMs, however, have not been fully understood. In this paper, we conduct an in-depth investigation of the representation power of DPMs, and propose a novel knowledge transfer method that leverages the knowledge acquired by generative DPMs for recognition tasks. Our study begins by examining the feature space of DPMs, revealing that DPMs are inherently denoising autoencoders that balance the representation learning with regularizing model capacity. To this end, we introduce a novel knowledge transfer paradigm named RepFusion. Our paradigm extracts representations at different time steps from off-the-shelf DPMs and dynamically employs them as supervision for student networks, in which the optimal time is determined through reinforcement learning. We evaluate our approach on several image classification, semantic segmentation, and landmark detection benchmarks, and demonstrate that it outperforms state-of-the-art methods. Our results uncover the potential of DPMs as a powerful tool for representation learning and provide insights into the usefulness of generative models beyond sample generation. The code is available at urlhttps://github.com/Adamdad/Repfusion.