arXiv 2510.082692025-12-10cs.CV

适应性梯度校准用于遥感图像场景分类中的单正多标签学习

Adaptive Gradient Calibration for Single-Positive Multi-Label Learning in Remote Sensing Image Scene Classification

Chair of Data Science in Earth Observation, Technical University of Munich (TUM), and Munich Center for Machine Learning (MCML)（地球观测数据科学主任，慕尼黑技术大学（TUM）和慕尼黑机器学习中心（MCML））；Department of Information Engineering and Computer Science, University of Trento（信息工程与计算机科学系，特伦托大学）

Chenying Liu, Gianmarco Perantoni, Lorenzo Bruzzone, Xiao Xiang Zhu

备注：: 14 pages, 7 figures; revised version
发表信息：: IEEE Transactions on Geoscience and Remote Sensing, vol. 64, 2026, Art no. 4404615
DOI：: 10.1109/TGRS.2026.3660680

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出AdaGC框架，通过双指数移动平均模块实现鲁棒的伪标签生成，解决遥感图像单正多标签学习中的监督模糊问题，实验表明其在两种噪声类型下均取得SOTA性能。

摘要：

多标签分类（MLC）相比传统单标签分类（SLC）能更全面地理解遥感（RS）影像的语义。然而，由于标注过程的复杂性和高成本，获得完整的MLC标注尤为困难。作为实用替代方案，单正多标签学习（SPML）已出现，其中每张图像仅标注一个相关标签，模型需恢复完整的标签集。尽管SPML具有可扩展性，但引入了显著的监督模糊性，需要专门的解决方案进行模型训练。尽管计算机视觉领域已提出多种SPML方法，但RS领域的研究仍有限。为填补这一空白，我们提出了适应性梯度校准（AdaGC），一种针对RS影像的新型且通用的SPML框架。AdaGC采用梯度校准（GC）机制，结合双指数移动平均（EMA）模块进行鲁棒伪标签生成。我们引入了一个理论基础的、基于训练动态的指标，以适应性触发GC，确保GC的有效性，防止其受模型欠拟合或过拟合标签噪声的影响。在两个基准RS数据集上，针对两种不同的标签噪声类型进行的大量实验表明，AdaGC在保持对不同设置的强鲁棒性的同时，实现了最先进的性能。代码和数据将在https://github.com/rslab-unitrento/AdaGC上发布。

英文摘要：

Multi-label classification (MLC) offers a more comprehensive semantic understanding of Remote Sensing (RS) imagery compared to traditional single-label classification (SLC). However, obtaining complete annotations for MLC is particularly challenging due to the complexity and high cost of the labeling process. As a practical alternative, single-positive multi-label learning (SPML) has emerged, where each image is annotated with only one relevant label, and the model is expected to recover the full set of labels. While scalable, SPML introduces significant supervision ambiguity, demanding specialized solutions for model training. Although various SPML methods have been proposed in the computer vision domain, research in the RS context remains limited. To bridge this gap, we propose Adaptive Gradient Calibration (AdaGC), a novel and generalizable SPML framework tailored to RS imagery. AdaGC adopts a gradient calibration (GC) mechanism with a dual exponential moving average (EMA) module for robust pseudo-label generation. We introduce a theoretically grounded, training-dynamics-based indicator to adaptively trigger GC, which ensures GC's effectiveness by preventing it from being affected by model underfitting or overfitting to label noise. Extensive experiments on two benchmark RS datasets under two distinct label noise types demonstrate that AdaGC achieves state-of-the-art (SOTA) performance while maintaining strong robustness across diverse settings. The codes and data will be released at https://github.com/rslab-unitrento/AdaGC.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。