# Soft Label Pruning and Quantization for Large-Scale Dataset Distillation

arXiv: https://arxiv.org/abs/2604.18135 · HTML: https://mlsanity.com/paper/2604.18135/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 45 of its 51 references that are in the map.
- First posted on arXiv 20 Apr 2026.

## Builds on (most cited first, 30 of 45)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [Swin Transformer V2: Scaling Up Capacity and Resolution](https://mlsanity.com/paper/2111.09883/) (2021)
- [ImageNet-21K Pretraining for the Masses](https://mlsanity.com/paper/2104.10972/) (2021)
- [Improved Knowledge Distillation via Teacher Assistant](https://mlsanity.com/paper/1902.03393/) (2019)
- [Dataset Condensation with Gradient Matching](https://mlsanity.com/paper/2006.05929/) (2020)
- [Dataset Distillation by Matching Training Trajectories](https://mlsanity.com/paper/2203.11932/) (2022)
- [Dreaming to Distill: Data-free Knowledge Transfer via DeepInversion](https://mlsanity.com/paper/1912.08795/) (2019)
- [Dataset Condensation with Distribution Matching](https://mlsanity.com/paper/2110.04181/) (2021)
- [Unifying distillation and privileged information](https://mlsanity.com/paper/1511.03643/) (2015)
- [Dataset Condensation via Efficient Synthetic-Data Parameterization](https://mlsanity.com/paper/2205.14959/) (2022)
- [Scaling Up Dataset Distillation to ImageNet-1K with Constant Memory](https://mlsanity.com/paper/2211.10586/) (2022)
- [Squeeze, Recover and Relabel: Dataset Condensation at ImageNet Scale From A New Perspective](https://mlsanity.com/paper/2306.13092/) (2023)
- [On the Diversity and Realism of Distilled Dataset: An Efficient Dataset Distillation Paradigm](https://mlsanity.com/paper/2312.03526/) (2023)
- [Efficient Dataset Distillation via Minimax Diffusion](https://mlsanity.com/paper/2311.15529/) (2023)
- [D4M: Dataset Distillation via Disentangled Diffusion Model](https://mlsanity.com/paper/2407.15138/) (2024)
- [Generalized Large-Scale Data Condensation via Various Backbone and Statistical Matching](https://mlsanity.com/paper/2311.17950/) (2023)
- [Annealing Knowledge Distillation](https://mlsanity.com/paper/2104.07163/) (2021)
- [A Fast Knowledge Distillation Framework for Visual Recognition](https://mlsanity.com/paper/2112.01528/) (2021)
- [M3D: Dataset Condensation by Minimizing Maximum Mean Discrepancy](https://mlsanity.com/paper/2312.15927/) (2023)
- [Diversity-Driven Synthesis: Enhancing Dataset Distillation through Directed Weight Adjustment](https://mlsanity.com/paper/2409.17612/) (2024)
- [Dataset Distillation via the Wasserstein Metric](https://mlsanity.com/paper/2311.18531/) (2023)
- [A Label is Worth a Thousand Images in Dataset Distillation](https://mlsanity.com/paper/2406.10485/) (2024)
- [Dataset Distillation via Curriculum Data Synthesis in Large Data Era](https://mlsanity.com/paper/2311.18838/) (2023)
- [You Only Condense Once: Two Rules for Pruning Condensed Datasets](https://mlsanity.com/paper/2310.14019/) (2023)
- [DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation](https://mlsanity.com/paper/2411.19946/) (2024)
- [Multisize Dataset Condensation](https://mlsanity.com/paper/2403.06075/) (2024)

## Abstract (arXiv)

Large-scale dataset distillation requires storing auxiliary soft labels that can be 30-40x larger on ImageNet-1K and 200x larger on ImageNet-21K than the condensed images, undermining the goal of dataset compression. We identify two fundamental issues necessitating such extensive labels: (1) insufficient image diversity, where high within-class similarity in synthetic images requires extensive augmentation, and (2) insufficient supervision diversity, where limited variety in supervisory signals during training leads to performance degradation at high compression rates. To address these challenges, we propose Label Pruning and Quantization for Large-scale Distillation (LPQLD). We enhance image diversity via class-wise batching and batch-normalization supervision during synthesis. For supervision diversity, we introduce Label Pruning with Dynamic Knowledge Reuse to improve label-per-augmentation diversity, and Label Quantization with Calibrated Student-Teacher Alignment to improve augmentation-per-image diversity. Our approach reduces soft label storage by 78x on ImageNet-1K and 500x on ImageNet-21K while improving accuracy by up to 7.2% and 2.8%, respectively. Extensive experiments validate the superiority of LPQLD across different network architectures and dataset distillation methods. Code is available at https://github.com/he-y/soft-label-pruning-quantization-for-dataset-distillation.