Few-Shot Learning for Domain-Specific Fine-Grained Image Classification

Xin Sun*, Hongwei Xv, Junyu Dong, Huiyu Zhou, Changrui Chen, Qiong Li

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

4 Citations (Scopus)

Abstract

Learning to recognize novel visual categories from a few examples is a challenging task for machines in real-world industrial applications. In contrast, humans have the ability to discriminate even similar objects with little supervision. This article attempts to address the few-shot fine-grained image classification problem. We propose a feature fusion model to explore discriminative features by focusing on key regions. The model utilizes the focus-area location mechanism to discover the perceptually similar regions among objects. High-order integration is employed to capture the interaction information among intraparts. We also design a center neighbor loss to form robust embedding space distributions. Furthermore, we build a typical fine-grained and few-shot learning dataset miniPPlankton from the real-world application in the area of marine ecological environments. Extensive experiments are carried out to validate the performance of our method. The results demonstrate that our model achieves competitive performance compared with state-of-the-art models. Our work is a valuable complement to the model domain-specific industrial applications.

Original languageEnglish
Pages (from-to)3588-3598
Number of pages11
JournalIEEE Transactions on Industrial Electronics
Volume68
Issue number4
Early online date06 Mar 2020
DOIs
Publication statusPublished - Apr 2021
Externally publishedYes

Bibliographical note

Funding Information:
This work was supported in part by the National Natural Science Foundation of China under Grant U1706218, Grant 61971388, and Grant L1824025, in part by the Key Research and Development Program of Shandong Province under Grant GG201703140154, and in part by the Major Program of Natural Science Foundation of Shandong Province under Grant ZR2018ZB0852. The work of H. Zhou was supported in part by the Royal Society-Newton Advanced Fellowship under Grant NA160342, and in part by the European Union?s Horizon 2020 Research and Innovation Program under the Marie-Sklodowska-Curie under Grant 720325.

Funding Information:
Manuscript received August 1, 2019; revised November 3, 2019, December 20, 2019, and January 29, 2020; accepted February 16, 2020. Date of publication March 6, 2020; date of current version December 8, 2020. This work was supported in part by the National Natural Science Foundation of China under Grant U1706218, Grant 61971388, and Grant L1824025, in part by the Key Research and Development Program of Shandong Province under Grant GG201703140154, and in part by the Major Program of Natural Science Foundation of Shandong Province under Grant ZR2018ZB0852. The work of H. Zhou was supported in part by the Royal Society-Newton Advanced Fellowship under Grant NA160342, and in part by the European Union’s Horizon 2020 Research and Innovation Program under the Marie-Sklodowska-Curie under Grant 720325. (Corresponding author: Xin Sun.) Xin Sun, Hongwei Xv, Junyu Dong, Changrui Chen, and Qiong Li are with the Department of Computer Science and Technology, Ocean University of China, Qingdao 266100, China (e-mail: sunxin1984@ieee.org; xhw@stu.ouc.edu.cn; dongjunyu@ouc.edu.cn; geoffreychen777@gmail.com; liqiong@stu.ouc.edu.cn).

Publisher Copyright:
© 1982-2012 IEEE.

Copyright:
Copyright 2020 Elsevier B.V., All rights reserved.

Keywords

  • Computer vision
  • few-shot learning
  • representation learning

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Few-Shot Learning for Domain-Specific Fine-Grained Image Classification'. Together they form a unique fingerprint.

Cite this