Hierarchical Features Matter: A Deep Exploration of GAN Priors for Improved Dataset Distillation

• URL: http://arxiv.org/abs/2406.05704v2
• Date: Wed, 12 Jun 2024 11:11:07 GMT
• Title: Hierarchical Features Matter: A Deep Exploration of GAN Priors for Improved Dataset Distillation
• Authors: Xinhao Zhong, Hao Fang, Bin Chen, Xulin Gu, Tao Dai, Meikang Qiu, Shu-Tao Xia,
• Abstract summary: We propose a novel parameterization method dubbed Hierarchical Generative Latent Distillation (H-GLaD) This method systematically explores hierarchical layers within the generative adversarial networks (GANs) In addition, we introduce a novel class-relevant feature distance metric to alleviate the computational burden associated with synthetic dataset evaluation.
• Score: 51.44054828384487
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Dataset distillation is an emerging dataset reduction method, which condenses large-scale datasets while maintaining task accuracy. Current methods have integrated parameterization techniques to boost synthetic dataset performance by shifting the optimization space from pixel to another informative feature domain. However, they limit themselves to a fixed optimization space for distillation, neglecting the diverse guidance across different informative latent spaces. To overcome this limitation, we propose a novel parameterization method dubbed Hierarchical Generative Latent Distillation (H-GLaD), to systematically explore hierarchical layers within the generative adversarial networks (GANs). This allows us to progressively span from the initial latent space to the final pixel space. In addition, we introduce a novel class-relevant feature distance metric to alleviate the computational burden associated with synthetic dataset evaluation, bridging the gap between synthetic and original datasets. Experimental results demonstrate that the proposed H-GLaD achieves a significant improvement in both same-architecture and cross-architecture performance with equivalent time consumption.

Related papers

• D$^4$M: Dataset Distillation via Disentangled Diffusion Model [4.568710926635445]
  We propose an efficient framework for dataset distillation via Disentangled Diffusion Model (D$4$M) Compared to architecture-dependent methods, D$4$M employs latent diffusion model to guarantee consistency and incorporates label information into category prototypes. D$4$M demonstrates superior performance and robust generalization, surpassing the SOTA methods across most aspects.
  arXiv  Detail & Related papers  (2024-07-21T12:16:20Z)
• Importance-Aware Adaptive Dataset Distillation [53.79746115426363]
  Development of deep learning models is enabled by the availability of large-scale datasets. dataset distillation aims to synthesize a compact dataset that retains the essential information from the large original dataset. We propose an importance-aware adaptive dataset distillation (IADD) method that can improve distillation performance.
  arXiv  Detail & Related papers  (2024-01-29T03:29:39Z)
• Sequential Subset Matching for Dataset Distillation [44.322842898670565]
  We propose a new dataset distillation strategy called Sequential Subset Matching (SeqMatch) Our analysis indicates that SeqMatch effectively addresses the coupling issue by sequentially generating the synthetic instances. Our code is available at https://github.com/shqii1j/seqmatch.
  arXiv  Detail & Related papers  (2023-11-02T19:49:11Z)
• Improved Distribution Matching for Dataset Condensation [91.55972945798531]
  We propose a novel dataset condensation method based on distribution matching. Our simple yet effective method outperforms most previous optimization-oriented methods with much fewer computational resources.
  arXiv  Detail & Related papers  (2023-07-19T04:07:33Z)
• Generalizing Dataset Distillation via Deep Generative Prior [75.9031209877651]
  We propose to distill an entire dataset's knowledge into a few synthetic images. The idea is to synthesize a small number of synthetic data points that, when given to a learning algorithm as training data, result in a model approximating one trained on the original data. We present a new optimization algorithm that distills a large number of images into a few intermediate feature vectors in the generative model's latent space.
  arXiv  Detail & Related papers  (2023-05-02T17:59:31Z)
• Minimizing the Accumulated Trajectory Error to Improve Dataset Distillation [151.70234052015948]
  We propose a novel approach that encourages the optimization algorithm to seek a flat trajectory. We show that the weights trained on synthetic data are robust against the accumulated errors perturbations with the regularization towards the flat trajectory. Our method, called Flat Trajectory Distillation (FTD), is shown to boost the performance of gradient-matching methods by up to 4.7%.
  arXiv  Detail & Related papers  (2022-11-20T15:49:11Z)
• Dataset Distillation via Factorization [58.8114016318593]
  We introduce a emphdataset factorization approach, termed emphHaBa, which is a plug-and-play strategy portable to any existing dataset distillation (DD) baseline. emphHaBa explores decomposing a dataset into two components: data emphHallucination networks and emphBases. Our method can yield significant improvement on downstream classification tasks compared with previous state of the arts, while reducing the total number of compressed parameters by up to 65%.
  arXiv  Detail & Related papers  (2022-10-30T08:36:19Z)
• Dataset Condensation via Efficient Synthetic-Data Parameterization [40.56817483607132]
  Machine learning with massive amounts of data comes at a price of huge computation costs and storage for training and tuning. Recent studies on dataset condensation attempt to reduce the dependence on such massive data by synthesizing a compact training dataset. We propose a novel condensation framework that generates multiple synthetic data with a limited storage budget via efficient parameterization considering data regularity.
  arXiv  Detail & Related papers  (2022-05-30T09:55:31Z)

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.