Patch-Level Consistency Regularization in Self-Supervised Transfer Learning for Fine-Grained Image Recognition

Patch-Level Consistency Regularization in Self-Supervised Transfer Learning for Fine-Grained Image Recognition

Fine-grained image recognition aims to classify fine subcategories belonging to the same parent category, such as vehicle model or bird species classification. This is an inherently challenging task because a classifier must capture subtle interclass differences under large intraclass variances. Mos...

Full description

Bibliographic Details
Main Authors: Yejin Lee, Suho Lee, Sangheum Hwang
Format: Article
Language:English
Published: MDPI AG 2023-09-01
Series:Applied Sciences
Subjects:
self-supervised learning
fine-grained image recognition
transfer learning
Vision Transformer
Online Access:https://www.mdpi.com/2076-3417/13/18/10493

Internet

https://www.mdpi.com/2076-3417/13/18/10493

Similar Items