Abstract
This manuscript presents a series of my selected contributions to the topic of label-efficient learning in computer vision and remote sensing. The central focus of this research is to develop and adapt methods that can learn effectively from limited or partially annotated data, and can leverage abundant unlabeled data in real-world applications. The contributions span both methodological developments and domain-specific adaptations, in particular addressing challenges unique to Earth observation data such as multi-modality, spatial resolution variability, and scene heterogeneity. The manuscript is organized around four main axes including (1) weakly supervised learning for object discovery and detection based on anomaly-aware representations learned from large amounts of background images; (2) multi-task learning that jointly trains on multiple datasets with disjoint annotations to improve performance on object detection and semantic segmentation; (3) self-supervised and supervised contrastive learning with multimodal data to enhance scene classification in remote sensing; and (4) few-shot learning for hierarchical scene classification using both explicit and implicit modeling of class hierarchies. These contributions are supported by extensive experimental results across natural and remote sensing datasets, reflecting the outcomes of several collaborative research projects. The manuscript concludes by outlining ongoing and future research directions focused on scaling and enhancing label-efficient learning for real-world applications.
Abstract (translated)
这份手稿展示了我为计算机视觉和遥感领域中标签高效学习主题所选的一系列贡献。这项研究的核心在于开发并调整能够从有限或部分标注的数据中有效学习的方法，并且能够在实际应用中利用丰富的未标注数据。这些贡献涵盖了方法论的发展以及特定领域的适应，特别是针对地球观测数据的多模态、空间分辨率变化和场景异质性等独特挑战。手稿围绕四个主要方面组织： 1. 弱监督学习：基于从大量背景图像中学到的异常感知表示来进行对象发现与检测。 2. 多任务学习：在同一套不同标注的数据集上联合训练，以提高目标检测和语义分割的性能。 3. 自监督及监督对比学习：利用多模态数据增强遥感中的场景分类。 4. 少量样本学习：通过显式和隐式的类层级模型来进行分层场景分类。 这些贡献得到了跨自然与遥感数据集的大量实验结果的支持，反映了多个合作研究项目的成果。手稿最后概述了正在进行和未来的研究方向，重点在于扩大并提升标签高效学习在实际应用中的规模和效果。
URL
https://arxiv.org/abs/2508.15973
