Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.13393 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914392508989440 |
|---|---|
| author | Korporaal, Daan de Kruijf, Patrick Litjens, Ralph H. G. M. van der Velden, Bas H. M. |
| author_facet | Korporaal, Daan de Kruijf, Patrick Litjens, Ralph H. G. M. van der Velden, Bas H. M. |
| contents | The detection and classification of bacterial colonies in images of agar-plates is important in microbiology, but is hindered by the lack of labeled datasets. Therefore, we propose Colony Grounded SAM2, a zero-shot inference pipeline to detect and segment bacterial colonies in multiple settings without any further training. By utilizing the pre-trained foundation models Grounding DINO and Segment Anything Model 2, fine-tuned to the microbiological domain, we developed a model that is robust to data changes. Results showed a mean Average Precision of 93.1\% and a $Dice@detection$ score of 0.85, showing excellent detection and segmentation capabilities on out-of-distribution datasets. The entire pipeline with model weights are shared open access to aid with annotation- and classification purposes in microbiology. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_13393 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Colony Grounded SAM2: Zero-shot detection and segmentation of bacterial colonies using foundation models Korporaal, Daan de Kruijf, Patrick Litjens, Ralph H. G. M. van der Velden, Bas H. M. Computer Vision and Pattern Recognition The detection and classification of bacterial colonies in images of agar-plates is important in microbiology, but is hindered by the lack of labeled datasets. Therefore, we propose Colony Grounded SAM2, a zero-shot inference pipeline to detect and segment bacterial colonies in multiple settings without any further training. By utilizing the pre-trained foundation models Grounding DINO and Segment Anything Model 2, fine-tuned to the microbiological domain, we developed a model that is robust to data changes. Results showed a mean Average Precision of 93.1\% and a $Dice@detection$ score of 0.85, showing excellent detection and segmentation capabilities on out-of-distribution datasets. The entire pipeline with model weights are shared open access to aid with annotation- and classification purposes in microbiology. |
| title | Colony Grounded SAM2: Zero-shot detection and segmentation of bacterial colonies using foundation models |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.13393 |