论文标题
CD-FSOD：跨域的基准少数射击对象检测
CD-FSOD: A Benchmark for Cross-domain Few-shot Object Detection
论文作者
论文摘要
在本文中，我们提出了一项研究跨域的几个射击对象检测（CD-FSOD）基准，该研究由来自不同数据域的图像数据组成。在拟议的基准上，我们评估了最先进的FSOD方法，包括元学习的FSOD方法和微调FSOD方法。结果表明，这些方法倾向于下降，甚至表现不佳。我们分析了它们失败的原因，并引入了强大的基线，该基线使用互惠互利的方式缓解了过度拟合的问题。我们的方法在拟议的基准上通过明显的利润率（平均2.0 \％）优于现有方法。我们的代码可在\ url {https://github.com/fsod/cd-fsod}上找到。
In this paper, we propose a study of the cross-domain few-shot object detection (CD-FSOD) benchmark, consisting of image data from a diverse data domain. On the proposed benchmark, we evaluate state-of-art FSOD approaches, including meta-learning FSOD approaches and fine-tuning FSOD approaches. The results show that these methods tend to fall, and even underperform the naive fine-tuning model. We analyze the reasons for their failure and introduce a strong baseline that uses a mutually-beneficial manner to alleviate the overfitting problem. Our approach is remarkably superior to existing approaches by significant margins (2.0\% on average) on the proposed benchmark. Our code is available at \url{https://github.com/FSOD/CD-FSOD}.
