提升小而密集细菌菌落计数精度，兼顾跨物种泛化。
Learning to count small and clustered objects with application to bacterial colonies
- 用区域对齐池化与优化特征工程处理小尺寸和重叠菌落。
- 跨验证下平均归一化绝对误差仅9.64%，优于基线2.23%~12.71%。
- 适合微生物图像分析、药物研发等需要高精度计数的场景。
从图像中自动计数细菌菌落是疫苗与抗生素研发的关键数据来源。但菌落存在小尺寸、密集重叠、标注成本高及跨物种泛化能力差等挑战。现有FamNet虽能处理重叠对象且标注成本低，但对小菌落和跨物种性能未知。为此提出ACFamNet，通过新型区域感兴趣池化与特征工程解决小尺寸与聚集问题；进一步引入ACFamNet Pro，结合多头注意力与残差连接，实现对象动态加权与梯度优化。实验表明，ACFamNet Pro在5折交叉验证下均方归一化绝对误差（MNAE）为9.64%，较ACFamNet降低2.23%，较FamNet降低12.71%。
原文摘要 · Abstract (English)
Automated bacterial colony counting from images is an important technique to obtain data required for the development of vaccines and antibiotics. However, bacterial colonies present unique machine vision challenges that affect counting, including (1) small physical size, (2) object clustering, (3) high data annotation cost, and (4) limited cross-species generalisation. While FamNet is an established object counting technique effective for clustered objects and costly data annotation, its effectiveness for small colony sizes and cross-species generalisation remains unknown. To address the first three challenges, we propose ACFamNet, an extension of FamNet that handles small and clustered objects using a novel region of interest pooling with alignment and optimised feature engineering. To address all four challenges above, we introduce ACFamNet Pro, which augments ACFamNet with multi-head attention and residual connections, enabling dynamic weighting of objects and improved gradient flow. Experiments show that ACFamNet Pro achieves a mean normalised absolute error (MNAE) of 9.64% under 5-fold cross-validation, outperforming ACFamNet and FamNet by 2.23% and 12.71%, respectively.
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。