arXiv Open Access 2026

Colony Grounded SAM2: Zero-shot detection and segmentation of bacterial colonies using foundation models

Daan Korporaal Patrick de Kruijf Ralph H. G. M. Litjens Bas H. M. van der Velden
Lihat Sumber

Abstrak

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.

Topik & Kata Kunci

Penulis (4)

D

Daan Korporaal

P

Patrick de Kruijf

R

Ralph H. G. M. Litjens

B

Bas H. M. van der Velden

Format Sitasi

Korporaal, D., Kruijf, P.d., Litjens, R.H.G.M., Velden, B.H.M.v.d. (2026). Colony Grounded SAM2: Zero-shot detection and segmentation of bacterial colonies using foundation models. https://arxiv.org/abs/2603.13393

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2026
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓