Multiscale Attention-Based Model for Image Enhancement and Classification

Fine-grained image classification plays a crucial role in various applications, such as agricultural disease detection, medical diagnosis, and industrial inspection. However, achieving a high classification accuracy while maintaining computational efficiency remains a significant challenge. To addre...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Journal of advanced computational intelligence and intelligent informatics Ročník 29; číslo 6; s. 1484 - 1499
Hlavní autoři: Guo, Mingyu, Takubo, Tomohito
Médium: Journal Article
Jazyk:angličtina
Vydáno: Tokyo Fuji Technology Press Co. Ltd 20.11.2025
Témata:
Ablation
Accuracy
Artificial neural networks
Attention
Classification
Efficiency
Graphics processing units
Image classification
Image enhancement
Inference
Medical imaging
Modules
ISSN:1343-0130, 1883-8014
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Fine-grained image classification plays a crucial role in various applications, such as agricultural disease detection, medical diagnosis, and industrial inspection. However, achieving a high classification accuracy while maintaining computational efficiency remains a significant challenge. To address this issue, in this study, enhanced DetailNet (EDNET), a convolutional neural network (CNN) model designed to balance fine-detail preservation and global context understanding, was developed. EDNET integrates multiscale attention mechanisms and self-attention modules, enabling it to capture both local and global information simultaneously. Extensive ablation studies were conducted to evaluate the contribution of each module and EDNET was compared with the mainstream benchmark models ResNet50, EfficientNet, and vision transformers. The results demonstrate that EDNET achieves highly competitive performance in terms of accuracy, F1-score, and area under the receiver operating characteristic curve, while maintaining an optimal balance between parameter count and inference efficiency. In addition, EDNET was tested in both high-performance graphics processing unit (NVIDIA RTX 3090) and resource-constrained environments (Jetson Nano simulation). The results confirm that EDNET is deployable on edge devices, achieving an inference efficiency comparable to that of EfficientNet, while outperforming traditional CNN models in fine-grained classification tasks.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1343-0130
1883-8014
DOI:10.20965/jaciii.2025.p1484