Towards Effective Data-Free Knowledge Distillation via Diverse Diffusion Augmentation

• URL: http://arxiv.org/abs/2410.17606v1
• Date: Wed, 23 Oct 2024 07:01:16 GMT
• Title: Towards Effective Data-Free Knowledge Distillation via Diverse Diffusion Augmentation
• Authors: Muquan Li, Dongyang Zhang, Tao He, Xiurui Xie, Yuan-Fang Li, Ke Qin,
• Abstract summary: Data-free knowledge distillation (DFKD) has emerged as a pivotal technique in the domain of model compression. This paper introduces an innovative approach to DFKD through diverse diffusion augmentation (DDA) Comprehensive experiments conducted on CIFAR-10, CIFAR-100, and Tiny-ImageNet datasets showcase the superior performance of our method.
• Score: 20.556083321381514
• License:
• Abstract: 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.

Related papers

• Mitigating Embedding Collapse in Diffusion Models for Categorical Data [52.90687881724333]
  We introduce CATDM, a continuous diffusion framework within the embedding space that stabilizes training. Experiments on benchmarks show that CATDM mitigates embedding collapse, yielding superior results on FFHQ, LSUN Churches, and LSUN Bedrooms.
  arXiv  Detail & Related papers  (2024-10-18T09:12:33Z)
• One Step Diffusion-based Super-Resolution with Time-Aware Distillation [60.262651082672235]
  Diffusion-based image super-resolution (SR) methods have shown promise in reconstructing high-resolution images with fine details from low-resolution counterparts. Recent techniques have been devised to enhance the sampling efficiency of diffusion-based SR models via knowledge distillation. We propose a time-aware diffusion distillation method, named TAD-SR, to accomplish effective and efficient image super-resolution.
  arXiv  Detail & Related papers  (2024-08-14T11:47:22Z)
• Data-Free Federated Class Incremental Learning with Diffusion-Based Generative Memory [27.651921957220004]
  We introduce a novel data-free federated class incremental learning framework with diffusion-based generative memory (DFedDGM) We design a new balanced sampler to help train the diffusion models to alleviate the common non-IID problem in FL. We also introduce an entropy-based sample filtering technique from an information theory perspective to enhance the quality of generative samples.
  arXiv  Detail & Related papers  (2024-05-22T20:59:18Z)
• De-confounded Data-free Knowledge Distillation for Handling Distribution Shifts [32.1016787150064]
  Data-Free Knowledge Distillation (DFKD) is a promising task to train high-performance small models to enhance actual deployment without relying on the original training data. Existing methods commonly avoid relying on private data by utilizing synthetic or sampled data. This paper proposes a novel perspective with causal inference to disentangle the student models from the impact of such shifts.
  arXiv  Detail & Related papers  (2024-03-28T16:13:22Z)
• Distribution-Aware Data Expansion with Diffusion Models [55.979857976023695]
  We propose DistDiff, a training-free data expansion framework based on the distribution-aware diffusion model. DistDiff consistently enhances accuracy across a diverse range of datasets compared to models trained solely on original data.
  arXiv  Detail & Related papers  (2024-03-11T14:07:53Z)
• Cross-feature Contrastive Loss for Decentralized Deep Learning on Heterogeneous Data [8.946847190099206]
  We present a novel approach for decentralized learning on heterogeneous data. Cross-features for a pair of neighboring agents are the features obtained from the data of an agent with respect to the model parameters of the other agent. Our experiments show that the proposed method achieves superior performance (0.2-4% improvement in test accuracy) compared to other existing techniques for decentralized learning on heterogeneous data.
  arXiv  Detail & Related papers  (2023-10-24T14:48:23Z)
• Towards Efficient Deep Hashing Retrieval: Condensing Your Data via Feature-Embedding Matching [7.908244841289913]
  The expenses involved in training state-of-the-art deep hashing retrieval models have witnessed an increase. The state-of-the-art dataset distillation methods can not expand to all deep hashing retrieval methods. We propose an efficient condensation framework that addresses these limitations by matching the feature-embedding between synthetic set and real set.
  arXiv  Detail & Related papers  (2023-05-29T13:23:55Z)
• Prompting to Distill: Boosting Data-Free Knowledge Distillation via Reinforced Prompt [52.6946016535059]
  Data-free knowledge distillation (DFKD) conducts knowledge distillation via eliminating the dependence of original training data. We propose a prompt-based method, termed as PromptDFD, that allows us to take advantage of learned language priors. As shown in our experiments, the proposed method substantially improves the synthesis quality and achieves considerable improvements on distillation performance.
  arXiv  Detail & Related papers  (2022-05-16T08:56:53Z)
• CAFE: Learning to Condense Dataset by Aligning Features [72.99394941348757]
  We propose a novel scheme to Condense dataset by Aligning FEatures (CAFE) At the heart of our approach is an effective strategy to align features from the real and synthetic data across various scales. We validate the proposed CAFE across various datasets, and demonstrate that it generally outperforms the state of the art.
  arXiv  Detail & Related papers  (2022-03-03T05:58:49Z)
• Up to 100x Faster Data-free Knowledge Distillation [52.666615987503995]
  We introduce FastDFKD, which allows us to accelerate DFKD by a factor of orders of magnitude. Unlike prior methods that optimize a set of data independently, we propose to learn a meta-synthesizer that seeks common features. FastDFKD achieves data synthesis within only a few steps, significantly enhancing the efficiency of data-free training.
  arXiv  Detail & Related papers  (2021-12-12T14:56:58Z)
• Preventing Catastrophic Forgetting and Distribution Mismatch in Knowledge Distillation via Synthetic Data [5.064036314529226]
  We propose a data-free KD framework that maintains a dynamic collection of generated samples over time. Our experiments demonstrate that we can improve the accuracy of the student models obtained via KD when compared with state-of-the-art approaches.
  arXiv  Detail & Related papers  (2021-08-11T08:11:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.