An Optimized Hybrid Transformer for Enhanced Ultra-Fine-Grained Thin Sections Categorization via Integrated Region-to-Region and Token-to-Token Approaches
Applied Sciences · 04.07.2023 · 13 (13) · 7853
DOI: 10.3390/app13137853 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 04.07.2023. Verfasst von Hongmei Zhang und 1 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Coal Industry Engineering Research Center for Comprehensive Prevention and Control of Mine Water Disaster, Graduate Innovation Fund Project of Anhui University of Science and Technology, Scientific Research Foundation for High-level Talents of Anhui University of Science and Technology.
Abstract (Originalsprache)
The analysis of thin sections for lithology identification is a staple technique in geology. Although recent strides in deep learning have catalyzed the development of models for thin section recognition leveraging varied deep neural networks, there remains a substantial gap in the identification of ultra-fine-grained thin section types. Visual Transformer models, superior to convolutional neural networks (CNN) in fine-grained classification tasks, are underexploited, especially when dealing with limited, highly similar sample sets. To address this, we incorporated a dynamic sparse attention mechanism and tailored the structure of the Swin Transformer network. We initially applied a region-to-region (R2R) approach to conserving key regions in coarse-grained areas, which minimized the global information loss instigated by the original model’s local window mechanism and bolstered training efficiency with scarce samples. This was then fused with deep convolution, and a token-to-token (T2T) attention mechanism was introduced to extract local features from these regions, facilitating fine-grained classification. In comparison experiments, our approach surpassed various sophisticated models, showcasing superior accuracy, precision, recall, and F1-score. Furthermore, our method demonstrated impressive generalizability in experiments external to the original dataset. Notwithstanding our significant progress, several unresolved issues warrant further exploration. An in-depth investigation of the adaptability of different rock types, along with their distribution under fluctuating sample sizes, is advisable. This line of inquiry is anticipated to yield more potent tools for future geological studies, thereby widening the scope and impact of our research.
Förderung
- Coal Industry Engineering Research Center for Comprehensive Prevention and Control of Mine Water Disaster
- Graduate Innovation Fund Project of Anhui University of Science and Technology
- Scientific Research Foundation for High-level Talents of Anhui University of Science and Technology
Zitieren
APA
Zhang, H., & Wang, S. (2023). An Optimized Hybrid Transformer for Enhanced Ultra-Fine-Grained Thin Sections Categorization via Integrated Region-to-Region and Token-to-Token Approaches. Applied Sciences, 13(13), 7853. https://doi.org/10.3390/app13137853
Vancouver
Zhang H, Wang S. An Optimized Hybrid Transformer for Enhanced Ultra-Fine-Grained Thin Sections Categorization via Integrated Region-to-Region and Token-to-Token Approaches. Applied Sciences. 2023;13(13):7853. doi:10.3390/app13137853
BibTeX
@article{Zhang2023,
author = {Zhang, Hongmei and Wang, Shuiqing},
title = {An Optimized Hybrid Transformer for Enhanced Ultra-Fine-Grained Thin Sections Categorization via Integrated Region-to-Region and Token-to-Token Approaches},
journal = {Applied Sciences},
year = {2023},
volume = {13},
number = {13},
pages = {7853},
doi = {10.3390/app13137853}
}
EUVIMED