Channel-masked Asymmetric Distribution Matching for Cross-Domain Generalized Dataset Distillation
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (9) · 7242-7250
DOI: 10.1609/aaai.v40i9.37661 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Qi Liu und 6 weiteren Autor:innen.
Abstract (Originalsprache)
Dataset distillation has achieved remarkable progress as an effective approach for data compression. However, real-world data often comes from diverse domains, leading to potential mismatches between the domains of synthesized images and those of the evaluation set. Existing methods primarily assume domain alignment between them, which limits their generalization ability in the above cross-domain scenarios. In this paper, we aim to ensure that images synthesized from known domains maintain robust performance on unseen domains and propose a novel framework called Channel-masked Asymmetric Distribution Matching (CADM). During asymmetric distribution matching, domain-sensitive channels of real data are selectively masked at different layers to extract domain-invariant features that guide synthetic data optimization. To further improve synthetic data representation, we introduce a class-focused domain-agnostic regularization to capture class-relevant knowledge while ignoring domain-specific information. Experiments show that our method produces domain-robust synthetic data and substantially improves generalization performance on unseen domains.
Zitieren
APA
Liu, Q., Xu, C., Yan, J., Lyu, G., Yang, E., Chen, G., & Yang, Y. (2026). Channel-masked Asymmetric Distribution Matching for Cross-Domain Generalized Dataset Distillation. Proceedings of the AAAI Conference on Artificial Intelligence, 40(9), 7242-7250. https://doi.org/10.1609/aaai.v40i9.37661
Vancouver
Liu Q, Xu C, Yan J, Lyu G, Yang E, Chen G, et al. Channel-masked Asymmetric Distribution Matching for Cross-Domain Generalized Dataset Distillation. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(9):7242-7250. doi:10.1609/aaai.v40i9.37661
BibTeX
@article{Liu2026,
author = {Liu, Qi and Xu, Chenghao and Yan, Jiexi and Lyu, Guangtao and Yang, Erkun and Chen, Guihai and Yang, Yanhua},
title = {Channel-masked Asymmetric Distribution Matching for Cross-Domain Generalized Dataset Distillation},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {9},
pages = {7242--7250},
doi = {10.1609/aaai.v40i9.37661}
}
EUVIMED