PuSH - Publikationsserver des Helmholtz Zentrums München

Yang, C. ; Deutges, M. ; Liu, J.* ; Li, H.* ; Navab, N.* ; Marr, C. ; Sadafi, A.

Attention Pooling Enhances NCA-Based Classification of Microscopy Images.

In: (Machine Learning in Medical Imaging). Berlin [u.a.]: Springer, 2026. 583 - 593 (Lect. Notes Comput. Sc. ; 16241 LNCS)
DOI
Neural Cellular Automata (NCA) offer a robust and interpretable approach to image classification, making them a promising choice for microscopy image analysis. However, a performance gap remains between NCA and larger, more complex architectures. We address this challenge by integrating attention pooling with NCA to enhance feature extraction and improve classification accuracy. The attention pooling mechanism refines the focus on the most informative regions, leading to more accurate predictions. We evaluate our method on eight diverse microscopy image datasets and demonstrate that our approach significantly outperforms existing NCA methods while remaining parameter-efficient and explainable. Furthermore, we compare our method with traditional lightweight convolutional neural network and vision transformer architectures, showing improved performance while maintaining a significantly lower parameter count. Our results highlight the potential of NCA-based models an alternative for explainable image classification.
Altmetric
Weitere Metriken?
[➜Einloggen]
Zusatzinfos bearbeiten [➜Einloggen]
Publikationstyp Artikel: Konferenzbeitrag
Schlagwörter Attention Pooling ; Classification ; Neural Cellular Automata
ISSN (print) / ISBN 0302-9743
e-ISSN 1611-3349
Konferenztitel Machine Learning in Medical Imaging
Zeitschrift Lecture Notes in Computer Science
Quellenangaben Band: 16241 LNCS, Heft: , Seiten: 583 - 593 Artikelnummer: , Supplement: ,
Verlag Springer
Verlagsort Berlin [u.a.]
Institut(e) Institute of AI for Health (AIH)