MASA-Net: Multi-Aspect Channel-Spatial Attention Network With Cross-Layer Feature Aggregation for Accurate Fungi Species Identification

100%

pmeo-2026-01-16_03_23_00-2025-bera-masa-net-multi-aspect-channel-spatial-attention-network-with-cross-layer.pdf

ABSTRACT

Accurate identification of fungal species is essential for effective diagnosis and treatment. Traditional microscopy-based methods are often subjective and time-consuming. Deep learning has emerged as a promising tool in this domain. However, existing deep learning models often struggle to generalize in the presence of class imbalance and subtle morphological differences, which are common in fungal image datasets. This study proposes MASA-Net, a deep learning framework that combines a fine-tuned DenseNet two hundred one backbone with a multi-aspect channel-spatial attention module. The attention mechanism refines spatial and channel-wise features by capturing multi-scale spatial patterns and adaptively emphasizing informative channels. This enhances the network's ability to focus on diagnostically relevant fungal structures while suppressing irrelevant features. The MASA-Net is evaluated on the DeFungi dataset and demonstrates superior performance in terms of accuracy, precision, recall, and F one-score. It also outperforms established attention mechanisms such as squeeze-and-excitation networks and convolutional block attention module under identical conditions. These results highlight MASA-Net's robustness and effectiveness in addressing class imbalance and structural variability, offering a reliable solution for automated fungal species identification.

One Introduction

Two Related Works

Three Methodology

Three point one. Base Model and Feature Extraction

Three point two. MASA

Three point two point one. Spatial Attention Mechanism

Three point two point two. Channel Attention Mechanism

Four. Experiments and Results

Four point two. Experimental Setup

Four point three. Data Partitioning

Four point four. Implementation Specification

Four point six Result Analysis

Four point six point one Performance Comparison on Random Split

Four point six point two Performance on Ten-Fold Cross Validation

Four point six point three | Ablation Study

Four point six point four | Feature Map Visualisation

Five. Discussion

Six. Conclusion

Overview

MASA-Net aims to improve the identification of fungal species using advanced deep learning techniques. By combining a specialized attention mechanism with a robust CNN backbone, it addresses challenges such as class imbalance and morphological variability in fungal datasets.

Key Points

1MASA-Net improves accuracy in fungal species identification; the framework utilizes a fine-tuned DenseNet-201 model for feature extraction; multi-aspect channel-spatial attention enhances relevant feature focus; tested on the DeFungi dataset, it outperforms existing methods; addresses challenges of class imbalance in fungal classification

Details

Authors: Indranil Bera, Rajesh Mukherjee, Bidesh Chakraborty
Category: Technology and Engineering

PDF
Group Decision Support Systems and Executive Support Systems
This document presents an overview of Group Decision Support Systems (GDSS) and Executive Support Systems (ESS), detailing their functions, benefits, limitations, and characteristics to aid in collective decision-making processes in business contexts.
PDF
Information Management and Decision Making
This document provides an overview of Decision Support Systems (DSS), discussing their components, types, and the importance of information management in decision-making processes for business executives.
PDF
Electronic Communication Systems
The document provides an overview of electronic communication systems, discussing various types such as electronic conferencing, meeting systems, and publishing, while also addressing benefits and risks associated with electronic publishing.
PDF
End-User Computing
This document provides a comprehensive overview of End-User Computing (EUC), discussing its definition, types, benefits, risks, and the tools used in EUC environments. It aims to explain how non-programmers can effectively participate in computing processes and develop their own applications.
PDF
FLASHATTENTION: Fast and Memory-Efficient Exact Attention with IO-Awareness
This document presents FLASHATTENTION, an IO-aware exact attention algorithm that significantly improves the speed and memory efficiency of Transformers on long sequences. It introduces methods to reduce memory reads and writes, resulting in faster training and better model performance compared to existing methods.