CD-FSOD: A Benchmark for Cross-domain Few-shot Object Detection
This work addresses the challenge of object detection with limited data across different domains, which is incremental as it builds on existing FSOD methods by providing a benchmark and baseline.
The paper tackles the problem of cross-domain few-shot object detection by proposing a new benchmark and showing that existing methods often fail, even underperforming naive fine-tuning; they introduce a baseline that alleviates overfitting and achieves an average improvement of 2.0% over existing approaches.
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}.