paper-with-me

Papers

Attention Pooling Enhances NCA-based Classification of Microscopy Images

2025-08-17 · Chen Yang, Michael Deutges, Jingsong Liu, Han Li, Nassir Navab, Carsten Marr, Ario Sadafi arxiv

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.

📄 PDF Abstract BibTeX arXiv:2508.12324

Code (0)

등록된 구현이 없습니다.

Tasks

Image Classification

Similar Papers 제목 키워드 기반

Classifying and Segmenting Microscopy Images Using Convolutional Multiple Instance Learning

2015-11-17 · Oren Z. Kraus, Lei Jimmy Ba, Brendan Frey

Convolutional neural networks (CNN) have achieved state of the art performance on both classification and segmentation tasks. Applying CNNs to microscopy images is challenging due to the lack of datasets labeled at the s…

General Classificationimage-classificationImage ClassificationMultiple Instance Learning+1

Deep Learning for Size and Microscope Feature Extraction and Classification in Oral Cancer: Enhanced Convolution Neural Network

2022-08-06 · Prakrit Joshi, Omar Hisham Alsadoon, Abeer Alsadoon, Nada AlSallami 외

Background and Aim: Over-fitting issue has been the reason behind deep learning technology not being successfully implemented in oral cancer images classification. The aims of this research were reducing overfitting for …

Dimensionality Reduction

Micro-Net: A unified model for segmentation of various objects in microscopy images

2018-04-22 · Shan E Ahmed Raza, Linda Cheung, Muhammad Shaban, Simon Graham 외

Object segmentation and structure localization are important steps in automated image analysis pipelines for microscopy images. We present a convolution neural network (CNN) based deep learning architecture for segmentat…

Deep LearningMulti-tissue Nucleus SegmentationSegmentationSemantic Segmentation

Deep learning enables reference-free isotropic super-resolution for volumetric fluorescence microscopy

2021-04-19 · Hyoungjun Park, Myeongsu Na, Bumju Kim, Soohyun Park 외

Volumetric imaging by fluorescence microscopy is often limited by anisotropic spatial resolution from inferior axial resolution compared to the lateral resolution. To address this problem, here we present a deep-learning…

Generative Adversarial NetworkSuper-Resolution

Augmented Equivariant Attention Networks for Microscopy Image Reconstruction

2020-11-06 · Yaochen Xie, Yu Ding, Shuiwang Ji

It is time-consuming and expensive to take high-quality or high-resolution electron microscopy (EM) and fluorescence microscopy (FM) images. Taking these images could be even invasive to samples and may damage certain su…

image-classificationImage ClassificationImage ReconstructionImage Super-Resolution+1