FE-VIT: a faster and extensible vision transformer based on self pre-training for pest recognition

Li Zhang; Jianming Du; Rujing Wang

doi:10.1117/12.2657205

18 October 2022 FE-VIT: a faster and extensible vision transformer based on self pre-training for pest recognition

Li Zhang, Jianming Du, Rujing Wang

Proceedings Volume 12349, International Conference on Agri-Photonics and Smart Agricultural Sensing Technologies (ICASAST 2022); 1234907 (2022) https://doi.org/10.1117/12.2657205
Event: International Conference on Agri-Photonics and Smart Agricultural Sensing Technologies (ICASAST 2022), 2022, Zhengzhou, China

Abstract

Agriculture has been the basic industry of mankind since ancient times. Accurate and robust crop pest identification system is an important step for reliable prediction of agricultural pests in precision agriculture community, which has attracted great attention from many countries. The development of computer vision and deep learning injects new vitality into this field. Many intelligent methods have been introduced into the field of pest recognition. However, long-time model preparation is the bottleneck of these methods, and expensive labels also make this method limited. At the same time, they can not be well compatible and extended when new pests appear. Therefore, we developed a pest identification algorithm based on self supervised learning. In the self supervised learning model(FE-VIT) proposed in this paper, we train a pretraining model through unlabeled data. In the pretext task, the purpose is to make the model match the downstream task(pest recognition). Besides, we simplify the model structure, reduce the time complexity from O (N2) to o (n*k), and make the proposed model Extensible. Our method can achieve about 17% time reduction and 1.1% accuracy improvement. A large number of detailed experiments show the accuracy and reliability of our model. Our code will be released in https://github.com/54zanly/FE-VIT .

Citation Download Citation

Li Zhang, Jianming Du, and Rujing Wang "FE-VIT: a faster and extensible vision transformer based on self pre-training for pest recognition", Proc. SPIE 12349, International Conference on Agri-Photonics and Smart Agricultural Sensing Technologies (ICASAST 2022), 1234907 (18 October 2022); https://doi.org/10.1117/12.2657205

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
8 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Machine learning

Data modeling

Visual process modeling

Transformers

Machine vision

Agriculture

Computer vision technology

Show All Keywords

Keywords/Phrases

Search In:

Publication Years