CAFE Learning to Condense Dataset by Aligning Features

Kai Wang, Bo Zhao, Xiangyu Peng, Zheng Zhu, Shuo Yang, Shuo Wang, Guan Huang, Hakan Bilen, Xinchao Wang, Yang You

Research output: Chapter in Book/Report/Conference proceedingConference contribution


Dataset condensation aims at reducing the network training effort through condensing a cumbersome training set into a compact synthetic one. State-of-the-art approaches largely rely on learning the synthetic data by matching the gradients between the real and synthetic data batches. Despite the intuitive motivation and promising results, such gradient-based methods, by nature, easily overfit to a biased set of samples that produce dominant gradients, and thus lack global supervision of data distribution. In this paper, we propose a novel scheme to Condense dataset by Aligning FEatures (CAFE), which explicitly attempts to preserve the real-feature distribution as well as the discriminant power of the resulting synthetic set, lending itself to strong generalization capability to various architectures. At the heart of our approach is an effective strategy to align features from the real and synthetic data across various scales, while accounting for the classification of real samples. Our scheme is further backed up by a novel dynamic bi-level optimization, which adaptively adjusts parameter updates to prevent over-/under-fitting. We validate the proposed CAFE across various datasets, and demonstrate that it generally outperforms the state of the art: on the SVHN dataset, for example, the performance gain is up to 11%. Extensive experiments and analyses verify the effectiveness and necessity of proposed designs.
Original languageEnglish
Title of host publicationProceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Number of pages10
ISBN (Electronic)978-1-6654-6946-3
ISBN (Print)978-1-6654-6947-0
Publication statusPublished - 27 Sep 2022
EventIEEE/CVF Conference on Computer Vision and Pattern Recognition 2022
- New Orleans, United States
Duration: 19 Jun 202224 Jun 2022

Publication series

NameIEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
ISSN (Print)1063-6919
ISSN (Electronic)2575-7075


ConferenceIEEE/CVF Conference on Computer Vision and Pattern Recognition 2022
Abbreviated titleCVPR 2022
Country/TerritoryUnited States
CityNew Orleans
Internet address


  • Computer Vision
  • Machine Learning (ML)
  • dataset synthesis
  • dataset condensation


Dive into the research topics of 'CAFE Learning to Condense Dataset by Aligning Features'. Together they form a unique fingerprint.

Cite this