Most existing works on few-shot object detection (FSOD) focus on a setting
where both pre-training and few-shot learning datasets are from a similar
domain. However, few-shot algorithms are important in multiple domains; hence
evaluation needs to reflect the broad applications. We propose a Multi-dOmain
Few-Shot Object Detection (MoFSOD) benchmark consisting of 10 datasets from a
wide range of domains to evaluate FSOD algorithms. We comprehensively analyze
the impacts of freezing layers, different architectures, and different
pre-training datasets on FSOD performance. Our empirical results show several
key factors that have not been explored in previous works: 1) contrary to
previous belief, on a multi-domain benchmark, fine-tuning (FT) is a strong
baseline for FSOD, performing on par or better than the state-of-the-art (SOTA)
algorithms; 2) utilizing FT as the baseline allows us to explore multiple
architectures, and we found them to have a significant impact on down-stream
few-shot tasks, even with similar pre-training performances; 3) by decoupling
pre-training and few-shot learning, MoFSOD allows us to explore the impact of
different pre-training datasets, and the right choice can boost the performance
of the down-stream tasks significantly. Based on these findings, we list
possible avenues of investigation for improving FSOD performance and propose
two simple modifications to existing algorithms that lead to SOTA performance
on the MoFSOD benchmark. The code is available at
this https URL

本文提出了一个基于多领域的数据集的多领域少样本目标检测（MoFSOD）基准测试，以评估少样本算法的性能，并通过冻结层、不同体系结构和不同预训练数据集等方面的实验结果发现了多个影响少样本目标检测性能的关键因素，并提出了两种算法改进方法，在 MoFSOD 基准测试中实现 SOTA 表现。