Attention Pooling Enhances NCA-based Classification of Microscopy Images

TL;DR

This paper introduces an attention pooling mechanism to enhance Neural Cellular Automata (NCA) for microscopy image classification, achieving higher accuracy and efficiency while maintaining interpretability.

Contribution

We integrate attention pooling into NCA models, significantly improving their performance on microscopy datasets compared to existing NCA approaches.

Findings

Outperforms existing NCA methods in accuracy

Maintains lower parameter count than CNNs and transformers

Demonstrates improved focus on informative image regions

Abstract

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.