Abstract
Accurate and rapid fine-grained visual classification (FGVC) of tree species within the same family can provide technical support for tree surveys, research, and conservation. However, FGVC faces challenges such as large intraclass differences and small interclass differences. Recognizing tree species within the same family requires focusing on and correlating overall and multiorgan features of the trees while mitigating the influence of complex natural backgrounds, occlusion effects and other factors. To address these challenges, we propose multiscale feature fusion (MFF) and enhancement in transformers to improve recognition performance. The method consists of a Swin transformer backbone , an MFF module, a discriminative feature enhancement (DFE) module, and a texture feature enhancement (TFE) module. The MFF module aims to strike a balance between global and local feature extraction. The DFE module is employed to mitigate the impact of background noise, whereas the TFE module is used to enhance the feature extraction associated with complex textures and spatial patterns. We conducted experiments on a constructed dataset of tree species from the same family, achieving a top-1 accuracy of 90.3 % and a top-3 accuracy of 96.8 %. In addition, the method performed well on three popular FGVC datasets, namely, the Flavia , Oxford Flowers, and PlantCLEF 2015 datasets, with top-1 accuracies of 100 %, 99.2 %, and 81.4 %, respectively. The ablation experiments and module visualizations also yielded satisfactory results. Thus, this work provides a solution to enhance the FGVC task.
Abstract from the paper’s OpenAlex record; open copy licensed cc-by-nc-nd. Read at the source ↗
The text the model read, with the source record’s inline markup (italics, sub- and superscripts) rendered and its character entities decoded; quote offsets refer to the raw text.
Claims 6
Claim · model-written summary
The transformer attained 90.3% top-1 accuracy on a same-family tree species dataset.
Verbatim
e0“We conducted experiments on a constructed dataset of tree species from the same family, achieving a top-1 accuracy of 90.3 % and a top-3 accuracy of 96.8 %.”
Claim · model-written summary
The transformer attained 96.8% top-3 accuracy on a same-family tree species dataset.
Verbatim
e0“We conducted experiments on a constructed dataset of tree species from the same family, achieving a top-1 accuracy of 90.3 % and a top-3 accuracy of 96.8 %.”
Claim · model-written summary
The method attained 100% top-1 accuracy on the Flavia dataset.
Verbatim
e0“the method performed well on three popular FGVC datasets, namely, the Flavia , Oxford Flowers, and PlantCLEF 2015 datasets, with top-1 accuracies of 100 %, 99.2 %, and 81.4 %, respectively.”
Claim · model-written summary
The method attained 99.2% top-1 accuracy on the Oxford Flowers dataset.
Verbatim
e0“the method performed well on three popular FGVC datasets, namely, the Flavia , Oxford Flowers, and PlantCLEF 2015 datasets, with top-1 accuracies of 100 %, 99.2 %, and 81.4 %, respectively.”
Claim · model-written summary
The method attained 81.4% top-1 accuracy on the PlantCLEF 2015 dataset.
Verbatim
e0“the method performed well on three popular FGVC datasets, namely, the Flavia , Oxford Flowers, and PlantCLEF 2015 datasets, with top-1 accuracies of 100 %, 99.2 %, and 81.4 %, respectively.”
Claim · model-written summary
Ablation experiments and module visualizations gave satisfactory results.
- Outcome
- satisfactory resultse0
Not reportedComparator
Verbatim
e0“The ablation experiments and module visualizations also yielded satisfactory results.”