CellMamba: Adaptive Mamba for Accurate and Efficient Cell Detection
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909976040046592 |
|---|---|
| author | Liu, Ruochen Tian, Yi Wang, Jiahao Liu, Hongbin Hou, Xianxu Liu, Jingxin |
| author_facet | Liu, Ruochen Tian, Yi Wang, Jiahao Liu, Hongbin Hou, Xianxu Liu, Jingxin |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_21803 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CellMamba: Adaptive Mamba for Accurate and Efficient Cell Detection Liu, Ruochen Tian, Yi Wang, Jiahao Liu, Hongbin Hou, Xianxu Liu, Jingxin Computer Vision and Pattern Recognition Artificial Intelligence 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. |
| title | CellMamba: Adaptive Mamba for Accurate and Efficient Cell Detection |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2512.21803 |