轻量级模型精准检测病理图像中的细胞，速度快且准确。
CellMamba: Adaptive Mamba for Accurate and Efficient Cell Detection
- 用自适应模块融合Mamba与注意力机制，提升空间分辨能力。
- 在CoNSeP和CytoDArk0数据集上精度超同类方法，模型更小、推理更快。
- 适合需要高分辨率细胞检测的医学影像分析场景。
病理图像中的细胞检测因目标密集、类间差异微弱及背景杂乱而面临独特挑战。本文提出CellMamba，一种专为细粒度生物医学实例检测设计的轻量级单阶段检测器。基于VSSD主干网络，CellMamba引入CellMamba Block，将NC-Mamba或多头自注意力（MSA）与新颖的三映射自适应耦合（TMAC）模块结合。TMAC通过双并行通道分支，分别配备双重特异性与单一共识注意力图，实现自适应融合，以保留局部敏感性与全局一致性。此外，设计自适应Mamba Head，通过可学习权重融合多尺度特征，增强对不同尺寸目标的鲁棒性。在两个公开数据集CoNSeP与CytoDArk0上的大量实验表明，CellMamba在精度上超越基于CNN、Transformer及Mamba的基线模型，同时显著降低模型大小与推理延迟。结果验证了CellMamba作为高分辨率细胞检测高效可靠解决方案的有效性。
原文摘要 · Abstract (English)
Cell detection in pathological images presents unique challenges due to densely packed objects, subtle inter-class differences, and severe background clutter. In this paper, we propose CellMamba, a lightweight and accurate one-stage detector tailored for fine-grained biomedical instance detection. Built upon a VSSD backbone, CellMamba integrates CellMamba Blocks, which couple either NC-Mamba or Multi-Head Self-Attention (MSA) with a novel Triple-Mapping Adaptive Coupling (TMAC) module. TMAC enhances spatial discriminability by splitting channels into two parallel branches, equipped with dual idiosyncratic and one consensus attention map, adaptively fused to preserve local sensitivity and global consistency. Furthermore, we design an Adaptive Mamba Head that fuses multi-scale features via learnable weights for robust detection under varying object sizes. Extensive experiments on two public datasets-CoNSeP and CytoDArk0-demonstrate that CellMamba outperforms both CNN-based, Transformer-based, and Mamba-based baselines in accuracy, while significantly reducing model size and inference latency. Our results validate CellMamba as an efficient and effective solution for high-resolution cell detection.
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。