Unsupervised feature extraction from a foundation model zoo for cell similarity search in oncological microscopy across devices
Year: 2025
Type: conference-paper
Abstract: Acquiring high-quality datasets in medical and biological research is costly and labor-intensive. Traditional supervised learning requires extensive labeled data and faces challenges due to diverse imaging equipment and protocols. We propose Entropy-guided Weighted Combinational FAISS (EWC-FAISS), using foundation models trained on natural images without fine-tuning, as feature extractors in an efficient and adaptive k-nearest neighbor search. Our approach shows superior generalization across diverse conditions, achieving competitive performance compared to fine-tuned DINO-based models and NMTune, whilst reducing computational demands. Experiments validate the effectiveness of EWC-FAISS for efficient and robust cell image analysis.
DOI: 10.6094/unifr/255467
Authors: Kalweit, Gabriel, Klett, Anusha, Naouar, Mehdi, Rahnfeld, Jens, Vogt, Yannick, Ramirez, Diana Laura Infante, Berger, Rebecca, Duque Afonso, Jesus, Hartmann, Tanja Nicole, Follo, Marie, Lübbert, Michael, Mertelsmann, Roland, Ullrich, Evelyn, Boedecker, Joschka, Kalweit, Maria
Language: English
Subfield: Biophysics
Domain: Life Sciences
Open Access status: green
OpenAlex ID: W7105005784
FWCI:
Cites:
Cited by:
Related to: