Attention Pooling Enhances NCA-based Classification of Microscopy Images

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, Chen, Deutges, Michael, Liu, Jingsong, Li, Han, Navab, Nassir, Marr, Carsten, Sadafi, Ario
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909739658510336
author Yang, Chen
Deutges, Michael
Liu, Jingsong
Li, Han
Navab, Nassir
Marr, Carsten
Sadafi, Ario
author_facet Yang, Chen
Deutges, Michael
Liu, Jingsong
Li, Han
Navab, Nassir
Marr, Carsten
Sadafi, Ario
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_12324
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Attention Pooling Enhances NCA-based Classification of Microscopy Images
Yang, Chen
Deutges, Michael
Liu, Jingsong
Li, Han
Navab, Nassir
Marr, Carsten
Sadafi, Ario
Computer Vision and Pattern Recognition
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.
title Attention Pooling Enhances NCA-based Classification of Microscopy Images
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.12324