Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Improved Distribution Matching for Dataset Condensation

About

Dataset Condensation aims to condense a large dataset into a smaller one while maintaining its ability to train a well-performing model, thus reducing the storage cost and training effort in deep learning applications. However, conventional dataset condensation methods are optimization-oriented and condense the dataset by performing gradient or parameter matching during model optimization, which is computationally intensive even on small datasets and models. In this paper, we propose a novel dataset condensation method based on distribution matching, which is more efficient and promising. Specifically, we identify two important shortcomings of naive distribution matching (i.e., imbalanced feature numbers and unvalidated embeddings for distance computation) and address them with three novel techniques (i.e., partitioning and expansion augmentation, efficient and enriched model sampling, and class-aware distribution regularization). Our simple yet effective method outperforms most previous optimization-oriented methods with much fewer computational resources, thereby scaling data condensation to larger datasets and models. Extensive experiments demonstrate the effectiveness of our method. Codes are available at https://github.com/uitrbn/IDM

Ganlong Zhao, Guanbin Li, Yipeng Qin, Yizhou Yu• 2023

Related benchmarks

TaskDatasetResultRank
Image ClassificationCIFAR-100 (test)
Accuracy50
3518
Image ClassificationCIFAR-10 (test)
Accuracy67.5
3381
Image ClassificationCIFAR-10
Accuracy67.5
507
ClassificationCIFAR10 (test)
Accuracy67.5
266
Image ClassificationTiny-ImageNet
Accuracy27.7
227
ClassificationCIFAR-100 (test)
Accuracy50
129
Image ClassificationTinyImageNet
Accuracy27.7
108
Image ClassificationCIFAR-10 Long Tailed Imbalance Ratio 50 (test)
Top-1 Accuracy56.1
57
Long-Tailed Image ClassificationCIFAR10-LT imbalance factor 100 (test)
Top-1 Accuracy53.1
46
Medical Image ClassificationCovid (test)
Accuracy79.28
43
Showing 10 of 15 rows

Other info

Code

Follow for update