无需源数据，仅用少量目标图像即可提升显微镜图像检测性能。
MIAdapt: Source-free Few-shot Domain Adaptive Object Detection for Microscopic Images
- 基于无源少样本域适应框架，利用目标域少量无标注图像进行模型优化。
- 在Raabin-WBC数据集上比现有无源方法高21.3% mAP，比少样本方法高4.7% mAP。
- 适合医疗影像等源数据受限场景，尤其适用于隐私敏感的医学图像分析。
现有的通用无监督域适应方法需要在适配过程中同时访问大规模带标签源数据集和充足的无标签目标数据集。然而，在医学影像中，即使收集大量无标签数据也面临挑战且成本高昂；此外，隐私限制可能导致源数据无法获取。针对这些难题，我们提出MIAdapt，一种面向显微镜图像自适应的源无关少样本域适应对象检测方法（SF-FSDA）。我们还定义了两个竞争基线：(1) Faster-FreeShot 和 (2) MT-FreeShot。在具有挑战性的M5-Malaria和Raabin-WBC数据集上的大量实验验证了MIAdapt的有效性。在未使用任何源域图像的情况下，MIAdapt在Raabin-WBC数据集上比最先进的无源无监督域适应（SF-UDA）方法高出21.3% mAP，比少样本域适应（FSDA）方法高出4.7% mAP。代码与模型将公开发布。
原文摘要 · Abstract (English)
Existing generic unsupervised domain adaptation approaches require access to both a large labeled source dataset and a sufficient unlabeled target dataset during adaptation. However, collecting a large dataset, even if unlabeled, is a challenging and expensive endeavor, especially in medical imaging. In addition, constraints such as privacy issues can result in cases where source data is unavailable. Taking in consideration these challenges, we propose MIAdapt, an adaptive approach for Microscopic Imagery Adaptation as a solution for Source-free Few-shot Domain Adaptive Object detection (SF-FSDA). We also define two competitive baselines (1) Faster-FreeShot and (2) MT-FreeShot. Extensive experiments on the challenging M5-Malaria and Raabin-WBC datasets validate the effectiveness of MIAdapt. Without using any image from the source domain MIAdapt surpasses state-of-the-art source-free UDA (SF-UDA) methods by +21.3% mAP and few-shot domain adaptation (FSDA) approaches by +4.7% mAP on Raabin-WBC. Our code and models will be publicly available.
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。