He, Yang, Lingao Xiao, and Joey Tianyi Zhou. "You only condense once: Two rules for pruning condensed datasets." Advances in Neural Information Processing Systems 36 (2023).
Abstract:
Dataset condensation is a crucial tool for enhancing training efficiency by reducing the size of the training dataset, particularly in on-device scenarios. However, these scenarios have two significant challenges: 1) the varying computational resources available on the devices require a dataset size different from the pre-defined condensed dataset, and 2) the limited computational resources often preclude the possibility of conducting additional condensation processes. We introduce You Only Condense Once (YOCO) to overcome these limitations. On top of one condensed dataset, YOCO produces smaller condensed datasets with two embarrassingly simple dataset pruning rules: Low LBPE Score and Balanced Construction. YOCO offers two key advantages: 1) it can flexibly resize the dataset to fit varying computational constraints, and 2) it eliminates the need for extra condensation processes, which can be computationally prohibitive. Experiments validate our findings on networks including ConvNet, ResNet and DenseNet, and datasets including CIFAR-10, CIFAR-100 and ImageNet. For example, our YOCO surpassed various dataset condensation and dataset pruning methods on CIFAR-10 with ten Images Per Class (IPC), achieving 6.98-8.89% and 6.31-23.92% accuracy gains, respectively. The code is available at: https://github.com/he-y/you-only-condense-once.
License type:
Attribution 4.0 International (CC BY 4.0)
Funding Info:
This research / project is supported by the Agency for Science, Technology and Research - Singapore Government’s Research, Innovation and Enterprise 2020 Plan (Advanced Manufacturing and Engineering domain)
Grant Reference no. : A18A1b0045
This research / project is supported by the Agency for Science, Technology and Research - Science and Engineering Research Council (SERC) - Central Research Fund (Use- inspired Basic Research)
Grant Reference no. :