Learning in data-scarce settings has recently gained significant attention in the research community. Semi-supervised object detection(SSOD) aims to improve detection performance by leveraging a large number of unlabeled images alongside a limited number of labeled images(a.k.a.,few-shot learning). In this paper, we present a comprehensive comparison of three state-of-the-art SSOD approaches, including MixPL, Semi-DETR and Consistent-Teacher, with the goal of understanding how performance varies with the number of labeled images. We conduct experiments using the MS-COCO and Pascal VOC datasets, two popular object detection benchmarks which allow for standardized evaluation. In addition, we evaluate the SSOD approaches on a custom Beetle dataset which enables us to gain insights into their performance on specialized datasets with a smaller number of object categories. Our findings highlight the trade-offs between accuracy, model size, and latency, providing insights into which methods are best suited for low-data regimes.

翻译：数据稀缺环境下的学习近来在学术界受到广泛关注。半监督目标检测旨在通过利用大量未标注图像与有限数量的标注图像（即少样本学习）来提升检测性能。本文对三种前沿的SSOD方法——包括MixPL、Semi-DETR与Consistent-Teacher——进行了全面比较，旨在探究其性能随标注图像数量变化的规律。我们在MS-COCO与Pascal VOC这两个支持标准化评估的流行目标检测基准数据集上开展实验。此外，我们在自定义的Beetle数据集上评估了这些SSOD方法，从而深入理解其在目标类别较少的专用数据集上的表现。研究结果揭示了精度、模型规模与延迟之间的权衡关系，为低数据场景下的方法选择提供了实践指导。