Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.12063 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912276895760384 |
|---|---|
| author | Yan, Yuqing Wu, Yirui |
| author_facet | Yan, Yuqing Wu, Yirui |
| contents | Cell counting remains a fundamental yet challenging task in medical and biological research due to the diverse morphology of cells, their dense distribution, and variations in image quality. We present DLA-Count, a breakthrough approach to cell counting that introduces three key innovations: (1) K-adjacent Hungarian Matching (KHM), which dramatically improves cell matching in dense regions, (2) Multi-scale Deformable Gaussian Convolution (MDGC), which adapts to varying cell morphologies, and (3) Gaussian-enhanced Feature Decoder (GFD) for efficient multi-scale feature fusion. Our extensive experiments on four challenging cell counting datasets (ADI, MBM, VGG, and DCC) demonstrate that our method outperforms previous methods across diverse datasets, with improvements in Mean Absolute Error of up to 46.7\% on ADI and 42.5\% on MBM datasets. Our code is available at https://anonymous.4open.science/r/DLA-Count. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_12063 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DLA-Count: Dynamic Label Assignment Network for Dense Cell Distribution Counting Yan, Yuqing Wu, Yirui Computer Vision and Pattern Recognition Cell counting remains a fundamental yet challenging task in medical and biological research due to the diverse morphology of cells, their dense distribution, and variations in image quality. We present DLA-Count, a breakthrough approach to cell counting that introduces three key innovations: (1) K-adjacent Hungarian Matching (KHM), which dramatically improves cell matching in dense regions, (2) Multi-scale Deformable Gaussian Convolution (MDGC), which adapts to varying cell morphologies, and (3) Gaussian-enhanced Feature Decoder (GFD) for efficient multi-scale feature fusion. Our extensive experiments on four challenging cell counting datasets (ADI, MBM, VGG, and DCC) demonstrate that our method outperforms previous methods across diverse datasets, with improvements in Mean Absolute Error of up to 46.7\% on ADI and 42.5\% on MBM datasets. Our code is available at https://anonymous.4open.science/r/DLA-Count. |
| title | DLA-Count: Dynamic Label Assignment Network for Dense Cell Distribution Counting |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.12063 |