AdaptiveCDM:显微图像细胞检测的源数据不可用少样本域自适应
AdaptiveCDM: Source-Free Few-Shot Domain Adaptation for Cell Detection in Microscopic Images
AI总结:
针对显微图像细胞检测的跨域性能下降,提出源数据不可用少样本域自适应框架AdaptiveCDM,结合分辨率感知增强与类别感知表示学习,仅用少量目标标注图像即可达到SOTA性能。
摘要:
跨域显微图像细胞检测因成像域间的分布偏移而遭受性能下降。无监督域自适应(UDA)策略试图在不需目标域标注数据的情况下克服域偏移。然而,需要源域标注数据和大量目标域数据这两项要求在现实场景中都是具有挑战性的限制。这在医学影像中尤为突出,因为隐私要求可能阻止访问带标注的源数据,而昂贵的数据采集限制了目标域的大规模采样。为应对这些挑战,我们提出了AdaptiveCDM,一个用于源数据不可用少样本域自适应目标检测(SF-FSDAOD)设置的模块化框架,该框架仅使用少量带标注的目标图像即可适配预训练的源模型,无需访问源数据。AdaptiveCDM结合了分辨率感知增强(RAug)和类别感知表示学习(CARL)。RAug通过增强实例平衡的训练样本来缓解数据稀缺和类别不平衡问题,同时保留细胞结构的尺度保真度和形态特性。CARL通过鼓励类别一致的提议来增强判别性表示学习,改善定位和分类。我们还为所提出的设置引入了两个竞争性基线:Faster-FreeShot和MT-FreeShot。我们的方法在M5上达到40.4/43.4 mAP0.5,在Raabin-WBC上达到67.1/75.5 mAP0.5,分别对应2-shot和5-shot自适应。尽管仅使用少量带标注的目标图像且无源数据,AdaptiveCDM在各自监督设置下与SOTA方法相比取得了具有竞争力或更优的性能。消融实验和定性分析进一步证实了每个组件的贡献以及AdaptiveCDM在低数据场景下的有效性。代码和模型将公开。
英文摘要:
Cross-domain cell detection for microscopic images suffers from performance degradation due to distribution shifts across imaging domains. Unsupervised Domain Adaptation (UDA) strategies, attempt to overcome domain sift without requiring annotated data from target. However, requirement of availability of annotated data from the source domain and large-size data from target domain are both challenging limitations for realistic scenarios. This is especially true in medical imaging, where privacy requirements might prevent access to annotated source data, and costly data acquisition restricts extensive sampling of the target domain. To address these challenges, we propose AdaptiveCDM, a modular framework for Source-Free Few-Shot Domain Adaptive Object Detection (SF-FSDAOD) setting, that adapts a pretrained source model using only few labeled target images without accessing source data. AdaptiveCDM combines Resolution-Aware Augmentation (RAug) and Category-Aware Representation Learning (CARL). RAug alleviates the scarcity and class imbalance by augmenting instance balanced training examples, while preserving the scale fidelity and morphological properties of cellular structures. CARL enhances discriminative representation learning by encouraging class-consistent proposals, improving both localization and classification. We also introduce two competitive baselines for proposed setting: Faster-FreeShot and MT-FreeShot. Our approach achieves 40.4/43.4 mAP0.5 on M5 and 67.1/75.5 mAP0.5 on Raabin-WBC under 2-/5-shot adaptation. Despite using only a few labeled target images and no source data, AdaptiveCDM achieves competitive or superior performance compared with SOTA methods under their respective supervision settings. Ablations and qualitative analyses further substantiate the contribution of each component and the effectiveness of AdaptiveCDM in low-data regimes. Code/models will be available.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。