# Towards Effective Data-Free Knowledge Distillation via Diverse Diffusion Augmentation

arXiv: https://arxiv.org/abs/2410.17606 · HTML: https://mlsanity.com/paper/2410.17606/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 51 references that are in the map.
- First posted on arXiv 23 Oct 2024.

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

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [Diffusion Models in Vision: A Survey](https://mlsanity.com/paper/2209.04747/) (2022)
- [Dreaming to Distill: Data-free Knowledge Transfer via DeepInversion](https://mlsanity.com/paper/1912.08795/) (2019)
- [Effective Data Augmentation With Diffusion Models](https://mlsanity.com/paper/2302.07944/) (2023)
- [Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixup](https://mlsanity.com/paper/2009.06962/) (2020)
- [GAN-based Synthetic Medical Image Augmentation for increased CNN Performance in Liver Lesion Classification](https://mlsanity.com/paper/1803.01229/) (2018)
- [Data-Free Learning of Student Networks](https://mlsanity.com/paper/1904.01186/) (2019)
- [Generate To Adapt: Aligning Domains using Generative Adversarial Networks](https://mlsanity.com/paper/1704.01705/) (2017)
- [Diverse Data Augmentation with Diffusions for Effective Test-time Prompt Tuning](https://mlsanity.com/paper/2308.06038/) (2023)
- [Data-Free Knowledge Distillation for Deep Neural Networks](https://mlsanity.com/paper/1710.07535/) (2017)
- [Zero-shot Knowledge Transfer via Adversarial Belief Matching](https://mlsanity.com/paper/1905.09768/) (2019)
- [Zero-Shot Knowledge Distillation in Deep Networks](https://mlsanity.com/paper/1905.08114/) (2019)
- [D2C: Diffusion-Denoising Models for Few-shot Conditional Generation](https://mlsanity.com/paper/2106.06819/) (2021)
- [Leaving Reality to Imagination: Robust Classification via Generated Datasets](https://mlsanity.com/paper/2302.02503/) (2023)
- [AutoMix: Unveiling the Power of Mixup for Stronger Classifiers](https://mlsanity.com/paper/2103.13027/) (2021)
- [Conditional Text Image Generation with Diffusion Models](https://mlsanity.com/paper/2306.10804/) (2023)
- [Robust and Resource-Efficient Data-Free Knowledge Distillation by Generative Pseudo Replay](https://mlsanity.com/paper/2201.03019/) (2022)
- [Data-Free Knowledge Transfer: A Survey](https://mlsanity.com/paper/2112.15278/) (2021)
- [Learning to Retain while Acquiring: Combating Distribution-Shift in Adversarial Data-Free Knowledge Distillation](https://mlsanity.com/paper/2302.14290/) (2023)
- [CDFKD-MFS: Collaborative Data-free Knowledge Distillation via Multi-level Feature Sharing](https://mlsanity.com/paper/2205.11845/) (2022)
- [Customizing Synthetic Data for Data-Free Student Learning](https://mlsanity.com/paper/2307.04542/) (2023)

## Built on by (most cited first, 13 of 13)

- [TWLA: Achieving Ternary Weights and Low-Bit Activations for LLMs via Post-Training Quantization](https://mlsanity.com/paper/2606.13054/) (2026)
- [One Refiner to Unlock Them All: Inference-Time Reasoning Elicitation via Reinforcement Query Refinement](https://mlsanity.com/paper/2604.25444/) (2026)
- [Beyond Random: Automatic Inner-loop Optimization in Dataset Distillation](https://mlsanity.com/paper/2510.04838/) (2025)
- [DSAS: A Universal Plug-and-Play Framework for Attention Optimization in Multi-Document Question Answering](https://mlsanity.com/paper/2510.12251/) (2025)
- [CAE-DFKD: Bridging the Transferability Gap in Data-Free Knowledge Distillation](https://mlsanity.com/paper/2504.21478/) (2025)
- [All for 1-Bit: Towards Genuine 1-Bit Post-Training Quantization for LLMs](https://mlsanity.com/paper/2609.06161/) (2026)
- [PRISM: Precision-Recall Informed Data-Free Knowledge Distillation via Generative Diffusion](https://mlsanity.com/paper/2509.16897/) (2025)
- [UBATrack: Spatio-Temporal State Space Model for General Multi-Modal Tracking](https://mlsanity.com/paper/2601.14799/) (2026)
- [Breaking the Scale Barrier: One-Shot Knowledge Transfer via Frequency Transform](https://mlsanity.com/paper/2603.07523/) (2026)
- [CAGE-SGG: Counterfactual Active Graph Evidence for Open-Vocabulary Scene Graph Generation](https://mlsanity.com/paper/2604.22274/) (2026)
- [ReLIC-SGG: Relation Lattice Completion for Open-Vocabulary Scene Graph Generation](https://mlsanity.com/paper/2604.22546/) (2026)
- [UniDFKD: A Unified Semantic Prior Framework for Architecture-Agnostic Data-Free Knowledge Distillation](https://mlsanity.com/paper/2608.09287/) (2026)
- [GHOST: Geometry-Constrained Hybrid Diffusion for Open-Vocabulary 3D Scene Graph Generation](https://mlsanity.com/paper/2610.16455/) (2026)

## Abstract (arXiv)

Data-free knowledge distillation (DFKD) has emerged as a pivotal technique in the domain of model compression, substantially reducing the dependency on the original training data. Nonetheless, conventional DFKD methods that employ synthesized training data are prone to the limitations of inadequate diversity and discrepancies in distribution between the synthesized and original datasets. To address these challenges, this paper introduces an innovative approach to DFKD through diverse diffusion augmentation (DDA). Specifically, we revise the paradigm of common data synthesis in DFKD to a composite process through leveraging diffusion models subsequent to data synthesis for self-supervised augmentation, which generates a spectrum of data samples with similar distributions while retaining controlled variations. Furthermore, to mitigate excessive deviation in the embedding space, we introduce an image filtering technique grounded in cosine similarity to maintain fidelity during the knowledge distillation process. Comprehensive experiments conducted on CIFAR-10, CIFAR-100, and Tiny-ImageNet datasets showcase the superior performance of our method across various teacher-student network configurations, outperforming the contemporary state-of-the-art DFKD methods. Code will be available at:https://github.com/SLGSP/DDA.