EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Hybrid Granularities Transformer for Fine-Grained Image Recognition

Ying Yu, Jinghui Wang

Entropy · 01.04.2023 · 25 (4) · 601

DOI: 10.3390/e25040601 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Entropy, online erschienen am 01.04.2023. Verfasst von Ying Yu und 1 weiteren Autor:innen. Beteiligte Einrichtung: School of Software, East China Jiaotong University, Nanchang 330013, China. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Jiangxi Province, State Key Laboratory of Computer Science Open Subject Fund.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Many current approaches for image classification concentrate solely on the most prominent features within an image, but in fine-grained image recognition, even subtle features can play a significant role in model classification. In addition, the large variations in the same class and small differences between different categories that are unique to fine-grained image recognition pose a great challenge for the model to extract discriminative features between different categories. Therefore, we aim to present two lightweight modules to help the network discover more detailed information in this paper. (1) Patches Hidden Integrator (PHI) module randomly selects patches from images and replaces them with patches from other images of the same class. It allows the network to glean diverse discriminative region information and prevent over-reliance on a single feature, which can lead to misclassification. Additionally, it does not increase the training time. (2) Consistency Feature Learning (CFL) aggregates patch tokens from the last layer, mining local feature information and fusing it with the class token for classification. CFL also utilizes inconsistency loss to force the network to learn common features in both tokens, thereby guiding the network to focus on salient regions. We conducted experiments on three datasets, CUB-200-2011, Stanford Dogs, and Oxford 102 Flowers. We achieved experimental results of 91.6%, 92.7%, and 99.5%, respectively, achieving a competitive performance compared to other works.

Schlagwörter

Stichwörter der Autor:innen

consistency featuredata enhancementfine-grained image recognitionvision transformer

Autor:innen und Institutionen

  • School of Software, East China Jiaotong University, Nanchang 330013, China.

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Jiangxi Province
  • State Key Laboratory of Computer Science Open Subject Fund
  • Postgraduate Innovation Fund of Education Department of Jiangxi Province
  • Double Thousand Plan of Jiangxi Province in China

Zitieren

APA

Yu, Y., & Wang, J. (2023). Hybrid Granularities Transformer for Fine-Grained Image Recognition. Entropy, 25(4), 601. https://doi.org/10.3390/e25040601

Vancouver

Yu Y, Wang J. Hybrid Granularities Transformer for Fine-Grained Image Recognition. Entropy. 2023;25(4):601. doi:10.3390/e25040601

BibTeX
@article{Yu2023,
  author = {Yu, Ying and Wang, Jinghui},
  title = {Hybrid Granularities Transformer for Fine-Grained Image Recognition},
  journal = {Entropy},
  year = {2023},
  volume = {25},
  number = {4},
  pages = {601},
  doi = {10.3390/e25040601}
}
Kostenlos starten →