探索卫星图像小样本目标检测的鲁棒特征
Exploring Robust Features for Few-Shot Object Detection in Satellite Imagery
AI总结：
针对卫星图像小样本目标检测需求，提出基于两阶段架构的原型分类小样本检测器，微调原型提升性能，实验证明视觉特征优于视觉语言模型，检测器在SIMD、DIOR数据集上性能超现有全监督及小样本方法。
摘要：
本文的目标是仅用少量样本实现卫星图像中的目标检测，从而让用户能够以最少的标注指定任意目标类别。为此，我们探索了开放词汇检测领域的最新方法和思路，并将其应用于遥感领域。我们基于传统的两阶段架构开发了一款小样本目标检测器，其中分类模块被替换为基于原型的分类器。我们使用大规模预训练模型构建类别参考嵌入或原型，将其与区域候选内容进行比较以预测标签。此外，我们提出在可用的训练图像上微调原型，以提升性能并学习相似类别（例如不同飞机类型）之间的差异。我们在两个包含具有挑战性的稀有目标的遥感数据集上开展了广泛的评估。我们还研究了视觉特征和图文特征的性能，即DINOv2和CLIP，其中包括两款专门为遥感应用定制的CLIP模型。结果表明，视觉特征的性能远优于视觉-语言模型，因为后者缺乏必要的领域特定词汇。最后，尽管训练参数极少，我们开发的检测器在SIMD和DIOR数据集上的表现优于所评估的全监督方法和小样本方法。
英文摘要：
The goal of this paper is to perform object detection in satellite imagery with only a few examples, thus enabling users to specify any object class with minimal annotation. To this end, we explore recent methods and ideas from open-vocabulary detection for the remote sensing domain. We develop a few-shot object detector based on a traditional two-stage architecture, where the classification block is replaced by a prototype-based classifier. A large-scale pre-trained model is used to build class-reference embeddings or prototypes, which are compared to region proposal contents for label prediction. In addition, we propose to fine-tune prototypes on available training images to boost performance and learn differences between similar classes, such as aircraft types. We perform extensive evaluations on two remote sensing datasets containing challenging and rare objects. Moreover, we study the performance of both visual and image-text features, namely DINOv2 and CLIP, including two CLIP models specifically tailored for remote sensing applications. Results indicate that visual features are largely superior to vision-language models, as the latter lack the necessary domain-specific vocabulary. Lastly, the developed detector outperforms fully supervised and few-shot methods evaluated on the SIMD and DIOR datasets, despite minimal training parameters.
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。
