First-Order Cross-Domain Meta Learning for Few-Shot Remote Sensing Object Classification
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026-06 · 48 (6) · 6365-6379
DOI: 10.1109/tpami.2026.3656494 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026-06. Verfasst von Wenda Zhao und 3 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 55 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Remote sensing images exhibit intrinsic domain complexity arising from multi-source sensor variances, which heterogeneity fundamentally challenges conventional cross-domain few-shot methods that assume simple distribution shifts. Addressing this, we propose a first-order Cross-Domain Meta Learning (CDML) for few-shot remote sensing object classification. CDML implements a dual-stage domain adaptation task as the fundamental meta-learning unit, and includes a cross-domain meta-train phase (CDMTrain) and a cross-domain meta-test phase (CDMTest). In CDMTrain, we propose an inner-loop multi-domain few-shot task sampling, which enables a teacher model encapsulate both cross-category discriminative features and authentic inter-domain distributional divergence. This alternating cyclic learning paradigm captures genuine domain shifts, with each update direction progressively guiding the model toward parameters that balance multi-domain performance. In CDMTest, we evaluate a domain diversity enhancement by transferring teacher parameters to the student model for cross-domain capability assessment on the reserved pseudo-unseen domain. The task-level design progressively improves domain generalization through iterative domain adaptive task learning. Meanwhile, to mitigate the conflicts and inadequacies caused by multi-domain scenarios, we propose a learnable affine transformation model. It adaptively learns affine transformation parameters through intermediate layer features to fine-tune the update direction. Extensive experiments on five remote sensing classification benchmarks demonstrate a superior performance of the proposed method compared with the state-of-the-art methods.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Zhao, W., Li, Y., Wang, H., & Lu, H. (2026). First-Order Cross-Domain Meta Learning for Few-Shot Remote Sensing Object Classification. IEEE Transactions on Pattern Analysis and Machine Intelligence, 48(6), 6365-6379. https://doi.org/10.1109/tpami.2026.3656494
Vancouver
Zhao W, Li Y, Wang H, Lu H. First-Order Cross-Domain Meta Learning for Few-Shot Remote Sensing Object Classification. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2026;48(6):6365-6379. doi:10.1109/tpami.2026.3656494
BibTeX
@article{Zhao2026,
author = {Zhao, Wenda and Li, Yunxiang and Wang, Haipeng and Lu, Huchuan},
title = {First-Order Cross-Domain Meta Learning for Few-Shot Remote Sensing Object Classification},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2026},
volume = {48},
number = {6},
pages = {6365--6379},
doi = {10.1109/tpami.2026.3656494}
}
EUVIMED