Unsupervised Feature Extraction from a Foundation Model Zoo for Cell Similarity Search in Oncological Microscopy Across Devices
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.
Cite
Text
Kalweit et al. "Unsupervised Feature Extraction from a Foundation Model Zoo for Cell Similarity Search in Oncological Microscopy Across Devices." ICML 2024 Workshops: FM-Wild, 2024.Markdown
[Kalweit et al. "Unsupervised Feature Extraction from a Foundation Model Zoo for Cell Similarity Search in Oncological Microscopy Across Devices." ICML 2024 Workshops: FM-Wild, 2024.](https://mlanthology.org/icmlw/2024/kalweit2024icmlw-unsupervised/)BibTeX
@inproceedings{kalweit2024icmlw-unsupervised,
title = {{Unsupervised Feature Extraction from a Foundation Model Zoo for Cell Similarity Search in Oncological Microscopy Across Devices}},
author = {Kalweit, Gabriel and Klett, Anusha and Naouar, Mehdi and Rahnfeld, Jens and Vogt, Yannick and Ramirez, Diana Laura Infante and Berger, Rebecca and Afonso, Jesus Duque and Hartmann, Tanja Nicole and Follo, Marie and Luebbert, Michael and Mertelsmann, Roland and Ullrich, Evelyn and Boedecker, Joschka and Kalweit, Maria},
booktitle = {ICML 2024 Workshops: FM-Wild},
year = {2024},
url = {https://mlanthology.org/icmlw/2024/kalweit2024icmlw-unsupervised/}
}