解决跨域少样本目标检测中的特征混淆问题
CDFormer: Cross-Domain Few-Shot Object Detection Transformer Against Feature Confusion
- 设计背景与物体区分模块，减少误判
- 在1/5/10样本设置下分别提升12.9%/11.0%/10.4%的mAP
- 适合做跨域少样本检测的研究者参考
跨域少样本目标检测（CD-FSOD）旨在用少量实例检测不同域中的新物体。特征混淆（包括物体-背景混淆和物体-物体混淆）在跨域和少样本场景中构成重大挑战。本文提出CDFormer，一种对抗特征混淆的跨域少样本目标检测变压器。该方法通过两个核心模块解决混淆问题：物体-背景区分（OBD）模块利用可学习的背景标记来区分物体与背景；物体-物体区分（OOD）模块增强不同类别物体之间的区分度。实验结果表明，相较于先前最优方法，CDFormer在微调后分别在1/5/10样本设置下实现12.9%、11.0%和10.4%的mAP提升。
原文摘要 · Abstract (English)
Cross-domain few-shot object detection (CD-FSOD) aims to detect novel objects across different domains with limited class instances. Feature confusion, including object-background confusion and object-object confusion, presents significant challenges in both cross-domain and few-shot settings. In this work, we introduce CDFormer, a cross-domain few-shot object detection transformer against feature confusion, to address these challenges. The method specifically tackles feature confusion through two key modules: object-background distinguishing (OBD) and object-object distinguishing (OOD). The OBD module leverages a learnable background token to differentiate between objects and background, while the OOD module enhances the distinction between objects of different classes. Experimental results demonstrate that CDFormer outperforms previous state-of-the-art approaches, achieving 12.9% mAP, 11.0% mAP, and 10.4% mAP improvements under the 1/5/10 shot settings, respectively, when fine-tuned.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。