EUVIMEDEUVIMED entdecken
Crossref

Augmentation-invariant Learning Strategy via Data Augmentation for Improving Model Generalization

Yu Miao, Juanjuan Zhao, Sijie Song, Ran Gong, Yuanqian Zhu, Lusha Qi, Yan Qiang

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (10) · 8061-8070

DOI: 10.1609/aaai.v40i10.37752 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Yu Miao und 6 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Data augmentation is an effective technique for regularizing deep networks, which helps to enhance the generalizability and robustness of the model. However, in the field of medical imaging, traditional data augmentation techniques such as cropping, rotation, and degradation may inadvertently alter the critical characteristics of pathological lesions. Conventional semantic augmentation methods, such as altering the color and contrast of the object background, may also affect the structural features of medical images in uncontrolled semantic directions. Such operational conditions compromise the model's diagnostic reliability in medical contexts. To address this issue, we propose a surprisingly efficient implicit augmentation-invariant learning strategy (AILS) via variational Bayesian inference on differentially constrained feature manifolds. Parameterizing probability measures over tangent space through deep networks enables precise estimation of semantic direction distributions. Subsequently, geodesic-aware semantic features are sampled from the reparameterized variational posterior, achieving semantic-consistent augmentation. Simultaneously, to mine augmentation distribution invariance, we design the AiHLoss, which constrains the augmentation distribution to facilitate the network to learn augmentation invariance. Extensive experiments demonstrate that AILS exhibits high performance on public medical image datasets, outperforming existing augmentation methods.

Zitieren

APA

Miao, Y., Zhao, J., Song, S., Gong, R., Zhu, Y., Qi, L., & Qiang, Y. (2026). Augmentation-invariant Learning Strategy via Data Augmentation for Improving Model Generalization. Proceedings of the AAAI Conference on Artificial Intelligence, 40(10), 8061-8070. https://doi.org/10.1609/aaai.v40i10.37752

Vancouver

Miao Y, Zhao J, Song S, Gong R, Zhu Y, Qi L, et al. Augmentation-invariant Learning Strategy via Data Augmentation for Improving Model Generalization. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(10):8061-8070. doi:10.1609/aaai.v40i10.37752

BibTeX
@article{Miao2026,
  author = {Miao, Yu and Zhao, Juanjuan and Song, Sijie and Gong, Ran and Zhu, Yuanqian and Qi, Lusha and Qiang, Yan},
  title = {Augmentation-invariant Learning Strategy via Data Augmentation for Improving Model Generalization},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {10},
  pages = {8061--8070},
  doi = {10.1609/aaai.v40i10.37752}
}
Kostenlos starten →