Like Human Rethinking: Contour Transformer AutoRegression for Referring Remote Sensing Interpretation
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026-06 · 48 (6) · 6174-6191
DOI: 10.1109/tpami.2026.3654392 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026-06. Verfasst von Jinming Chai und 8 weiteren Autor:innen. Hauptthemen laut MEDLINE: Remote Sensing Technology, Image Processing, Computer-Assisted, Pattern Recognition, Automated. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 131 Literaturangaben. Gefördert von: National Natural Science Foundation of China, National Science and Technology Major Project, Fund for Foreign Scholars in University Research and Teaching Programs.
Abstract (Originalsprache)
Referring remote sensing interpretation holds significant application value in various scenarios such as ecological protection, resource exploration, and emergency management. However, referring remote sensing expression comprehension and segmentation (RRSECS) faces critical challenges, including micro-target localization drift problem caused by insufficient extraction of boundary features in existing paradigms. Moreover, when transferred to remote sensing domains, polygon-based methods encounter issues such as contour-boundary misalignment and multi-task co-optimization conflicts problems. In this paper, we propose SeeFormer, a novel contour autoregressive paradigm specifically designed for RRSECS, which accurately locates and segments micro, irregular targets in remote sensing imagery. We first introduce a brain-inspired feature refocus learning (BIFRL) module that progressively attends to effective object features via a coarse-to-fine scheme, significantly boosting small-object localization and segmentation. Next, we present a language-contour enhancer (LCE) that injects shape-aware contour priors, and a corner-based contour sampler (CBCS) to improve mask-polygon reconstruction fidelity. Finally, we develop an autoregressive dual-decoder paradigm (ARDDP) that preserves sequence consistency while alleviating multi-task optimization conflicts. Extensive experiments on RefDIOR, RRSISD, and OPTRSVG datasets under varying scenarios, scales, and task paradigms demonstrate transformative performance gains: compared to the baseline PolyFormer, our proposed SeeFormer improves oIoU and mIoU by 27.58% and 39.37% for referring image segmentation and by 18.94% and 28.90% for visual grounding on the RefDIOR dataset.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Förderung
- National Natural Science Foundation of China
- National Science and Technology Major Project
- Fund for Foreign Scholars in University Research and Teaching Programs
- Program for Cheung Kong Scholars and Innovative Research Team in University
- National Science Basic Research Plan in Shaanxi Province of China
- Science and Technology Innovation Project from the Chinese Ministry of Education
- National Key Laboratory of Human-Machine Hybrid Augmented Intelligence
- Xi’an Jiaotong University
Zitieren
APA
Chai, J., Jiao, L., Lu, X., Li, L., Liu, F., Sun, L., Liu, X., Ma, W., & Li, W. (2026). Like Human Rethinking: Contour Transformer AutoRegression for Referring Remote Sensing Interpretation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 48(6), 6174-6191. https://doi.org/10.1109/tpami.2026.3654392
Vancouver
Chai J, Jiao L, Lu X, Li L, Liu F, Sun L, et al. Like Human Rethinking: Contour Transformer AutoRegression for Referring Remote Sensing Interpretation. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2026;48(6):6174-6191. doi:10.1109/tpami.2026.3654392
BibTeX
@article{Chai2026,
author = {Chai, Jinming and Jiao, Licheng and Lu, Xiaoqiang and Li, Lingling and Liu, Fang and Sun, Long and Liu, Xu and Ma, Wenping and Li, Weibin},
title = {Like Human Rethinking: Contour Transformer AutoRegression for Referring Remote Sensing Interpretation},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2026},
volume = {48},
number = {6},
pages = {6174--6191},
doi = {10.1109/tpami.2026.3654392}
}
EUVIMED