Image-Based Vehicle Classification by Synergizing Features from Supervised and Self-Supervised Learning Paradigms

This paper introduces a novel approach to leveraging features learned from both supervised and self-supervised paradigms, to improve image classification tasks, specifically for vehicle classification. Two state-of-the-art self-supervised learning methods, DINO and data2vec, were evaluated and compa...

Full description

Bibliographic Details

Published in:	Eng
Main Authors:	Shihan Ma, Jidong J. Yang
Format:	Article
Language:	English
Published:	MDPI AG 2023-02-01
Subjects:	vehicle classification vision transformer self-supervised learning supervised learning object detection
Online Access:	https://www.mdpi.com/2673-4117/4/1/27