对比三种半监督目标检测方法，揭示小样本下的性能与效率权衡。
Practical Insights into Semi-Supervised Object Detection Approaches
- 对比MixPL、Semi-DETR与Consistent-Teacher在少标注数据下的表现
- 在MS-COCO和Pascal VOC上验证，小样本下精度差异显著
- 适合资源受限或标注成本高的实际部署场景
数据稀缺环境下的学习近年来受到广泛关注。半监督目标检测（SSOD）通过结合大量未标注图像与少量标注图像（即少样本学习），旨在提升检测性能。本文全面比较了三种前沿的SSOD方法：MixPL、Semi-DETR与Consistent-Teacher，重点分析其在不同标注图像数量下的性能变化。实验基于MS-COCO与Pascal VOC两个主流目标检测基准进行标准化评估，并在自建的Beetle数据集上测试，以了解其在类别较少的专业数据集上的表现。研究结果揭示了精度、模型规模与推理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用指导。
原文摘要 · Abstract (English)
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.
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。