Attention Pooling Enhances NCA-based Classification of Microscopy Images
This work addresses the problem of improving classification accuracy for microscopy images using explainable NCA models, though it appears incremental as it builds on existing NCA methods with attention pooling.
The authors tackled the performance gap between Neural Cellular Automata (NCA) and larger architectures for microscopy image classification by integrating attention pooling to enhance feature extraction. They demonstrated significant improvements over existing NCA methods on eight diverse datasets while maintaining parameter efficiency and explainability.
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.