# Knowledge Diffusion for Distillation

arXiv: https://arxiv.org/abs/2305.15712 · HTML: https://mlsanity.com/paper/2305.15712/

## Key facts

- Cited by 53 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models.
- Builds on 43 of its 56 references that are in the map.
- First posted on arXiv 25 May 2023.

## Placed in

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

## Builds on (most cited first, 30 of 43)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps](https://mlsanity.com/paper/2206.00927/) (2022)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [Cascade R-CNN: Delving into High Quality Object Detection](https://mlsanity.com/paper/1712.00726/) (2017)
- [Relational Knowledge Distillation](https://mlsanity.com/paper/1904.05068/) (2019)
- [Contrastive Representation Distillation](https://mlsanity.com/paper/1910.10699/) (2019)
- [Improved Knowledge Distillation via Teacher Assistant](https://mlsanity.com/paper/1902.03393/) (2019)
- [Decoupled Knowledge Distillation](https://mlsanity.com/paper/2203.08679/) (2022)
- [ResNet strikes back: An improved training procedure in timm](https://mlsanity.com/paper/2110.00476/) (2021)
- [A Comprehensive Overhaul of Feature Distillation](https://mlsanity.com/paper/1904.01866/) (2019)
- [Variational Information Distillation for Knowledge Transfer](https://mlsanity.com/paper/1904.05835/) (2019)
- [Distilling Knowledge via Knowledge Review](https://mlsanity.com/paper/2104.09044/) (2021)
- [Structured Knowledge Distillation for Dense Prediction](https://mlsanity.com/paper/1903.04197/) (2019)

## Built on by (most cited first, 30 of 53)

- [On the Design Fundamentals of Diffusion Models: A Survey](https://mlsanity.com/paper/2306.04542/) (2023)
- [Foundation Models for Music: A Survey](https://mlsanity.com/paper/2408.14340/) (2024)
- [Stable Diffusion is Unstable](https://mlsanity.com/paper/2306.02583/) (2023)
- [FreeKD: Knowledge Distillation via Semantic Frequency Prompt](https://mlsanity.com/paper/2311.12079/) (2023)
- [Wasserstein Distance Rivals Kullback-Leibler Divergence for Knowledge Distillation](https://mlsanity.com/paper/2412.08139/) (2024)
- [ACAM-KD: Adaptive and Cooperative Attention Masking for Knowledge Distillation](https://mlsanity.com/paper/2503.06307/) (2025)
- [Cached Adaptive Token Merging: Dynamic Token Reduction and Redundant Computation Elimination in Diffusion Model](https://mlsanity.com/paper/2501.00946/) (2025)
- [Cloud-Device Collaborative Learning for Multimodal Large Language Models](https://mlsanity.com/paper/2312.16279/) (2023)
- [ScaleKD: Strong Vision Transformers Could Be Excellent Teachers](https://mlsanity.com/paper/2411.06786/) (2024)
- [Scale-wise Distillation of Diffusion Models](https://mlsanity.com/paper/2503.16397/) (2025)
- [Learnable Sparsity for Vision Generative Models](https://mlsanity.com/paper/2412.02852/) (2024)
- [LIX: Implicitly Infusing Spatial Geometric Prior Knowledge into Visual Semantic Segmentation for Autonomous Driving](https://mlsanity.com/paper/2403.08215/) (2024)
- [Model Compression Method for S4 with Diagonal State Space Layers using Balanced Truncation](https://mlsanity.com/paper/2402.15993/) (2024)
- [Pluggable Pruning with Contiguous Layer Distillation for Diffusion Transformers](https://mlsanity.com/paper/2511.16156/) (2025)
- [Feature Denoising Diffusion Model for Blind Image Quality Assessment](https://mlsanity.com/paper/2401.11949/) (2024)
- [DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer](https://mlsanity.com/paper/2505.15133/) (2025)
- [Local Dense Logit Relations for Enhanced Knowledge Distillation](https://mlsanity.com/paper/2507.15911/) (2025)
- [LumiNet: Perception-Driven Knowledge Distillation via Statistical Logit Calibration](https://mlsanity.com/paper/2310.03669/) (2023)
- [Attention-guided Feature Distillation for Semantic Segmentation](https://mlsanity.com/paper/2403.05451/) (2024)
- [CA-BERT: Leveraging Context Awareness for Enhanced Multi-Turn Chat Interaction](https://mlsanity.com/paper/2409.13701/) (2024)
- [PTQ4ADM: Post-Training Quantization for Efficient Text Conditional Audio Diffusion Models](https://mlsanity.com/paper/2409.13894/) (2024)
- [Q-Sched: Pushing the Boundaries of Few-Step Diffusion Models with Quantization-Aware Scheduling](https://mlsanity.com/paper/2509.01624/) (2025)
- [Model Mimic Attack: Knowledge Distillation for Provably Transferable Adversarial Examples](https://mlsanity.com/paper/2410.15889/) (2024)
- [Precise Knowledge Transfer via Flow Matching](https://mlsanity.com/paper/2402.02012/) (2024)
- [Teaching with Uncertainty: Unleashing the Potential of Knowledge Distillation in Object Detection](https://mlsanity.com/paper/2406.06999/) (2024)
- [Computer Vision Model Compression Techniques for Embedded Systems: A Survey](https://mlsanity.com/paper/2408.08250/) (2024)
- [Asymmetric Decision-Making in Online Knowledge Distillation:Unifying Consensus and Divergence](https://mlsanity.com/paper/2503.06685/) (2025)
- [FedPhD: Federated Pruning with Hierarchical Learning of Diffusion Models](https://mlsanity.com/paper/2507.06449/) (2025)
- [Generative Distribution Distillation](https://mlsanity.com/paper/2507.14503/) (2025)
- [3M-TI: High-Quality Mobile Thermal Imaging via Calibration-free Multi-Camera Cross-Modal Diffusion](https://mlsanity.com/paper/2511.19117/) (2025)

## Abstract (arXiv)

The representation gap between teacher and student is an emerging topic in knowledge distillation (KD). To reduce the gap and improve the performance, current methods often resort to complicated training schemes, loss functions, and feature alignments, which are task-specific and feature-specific. In this paper, we state that the essence of these methods is to discard the noisy information and distill the valuable information in the feature, and propose a novel KD method dubbed DiffKD, to explicitly denoise and match features using diffusion models. Our approach is based on the observation that student features typically contain more noises than teacher features due to the smaller capacity of student model. To address this, we propose to denoise student features using a diffusion model trained by teacher features. This allows us to perform better distillation between the refined clean feature and teacher feature. Additionally, we introduce a light-weight diffusion model with a linear autoencoder to reduce the computation cost and an adaptive noise matching module to improve the denoising performance. Extensive experiments demonstrate that DiffKD is effective across various types of features and achieves state-of-the-art performance consistently on image classification, object detection, and semantic segmentation tasks. Code is available at https://github.com/hunto/DiffKD.