Research Progress of Fine-grained Visual Classification: Basic Framework, Challenges, and Future Development

Congying Ma; Yuhan Pu

doi:10.1109/IAECST54258.2021.9695701

Research Progress of Fine-grained Visual Classification: Basic Framework, Challenges, and Future Development

Congying Ma, Yuhan Pu

University of California Davis

Research output: Chapter or section in a book/report/conference proceeding › Chapter in a published conference proceeding

1 Citation (SciVal)

Abstract

With the progress of multimedia technology, fine-grained visual classification (FGVC) has gradually attracted extensive attention in the field of computer vision. Thanks to the success of deep neural networks, both the accuracy and speed have achieved an unprecedented breakthrough. Hundreds of fine-grained classification techniques have been developed from the early, fully supervised methods to the current weakly ones. To this end, in this article, we provide a comprehensive survey of the recent achievements of FGVC. Specifically, we describe the formulation and setting of the FGVC, including the background, basic framework, and challenges. Then, we introduce the widely used datasets and compare the performance of different models. Lastly, we discuss the potential future directions of FGVC.

Original language	English
Title of host publication	2021 3rd International Academic Exchange Conference on Science and Technology Innovation (IAECST)
Place of Publication	U. S. A.
Publisher	IEEE
Pages	413-419
Number of pages	7
Volume	2021
ISBN (Electronic)	9781665402675
DOIs	https://doi.org/10.1109/IAECST54258.2021.9695701
Publication status	Published - 7 Feb 2022
Externally published	Yes
Event	3rd International Academic Exchange Conference on Science and Technology Innovation, IAECST 2021 - Guangzhou, China Duration: 10 Dec 2021 → 12 Dec 2021

Publication series

Name	2021 3rd International Academic Exchange Conference on Science and Technology Innovation, IAECST 2021

Conference

Conference	3rd International Academic Exchange Conference on Science and Technology Innovation, IAECST 2021
Country/Territory	China
City	Guangzhou
Period	10/12/21 → 12/12/21

Bibliographical note

Publisher Copyright:
© 2021 IEEE.

Keywords

deep learning
Fine-grained visual classification
weakly supervised learning
zero-shot learning

ASJC Scopus subject areas

Chemical Engineering (miscellaneous)
Computer Science Applications
Signal Processing
Information Systems and Management
Engineering (miscellaneous)
Ceramics and Composites
Electronic, Optical and Magnetic Materials
Metals and Alloys

Access to Document

10.1109/IAECST54258.2021.9695701

Cite this

Ma, C., & Pu, Y. (2022). Research Progress of Fine-grained Visual Classification: Basic Framework, Challenges, and Future Development. In 2021 3rd International Academic Exchange Conference on Science and Technology Innovation (IAECST) (Vol. 2021, pp. 413-419). (2021 3rd International Academic Exchange Conference on Science and Technology Innovation, IAECST 2021). IEEE. https://doi.org/10.1109/IAECST54258.2021.9695701

Research Progress of Fine-grained Visual Classification: Basic Framework, Challenges, and Future Development. / Ma, Congying; Pu, Yuhan.
2021 3rd International Academic Exchange Conference on Science and Technology Innovation (IAECST). Vol. 2021 U. S. A.: IEEE, 2022. p. 413-419 (2021 3rd International Academic Exchange Conference on Science and Technology Innovation, IAECST 2021).

Research output: Chapter or section in a book/report/conference proceeding › Chapter in a published conference proceeding

Ma, C & Pu, Y 2022, Research Progress of Fine-grained Visual Classification: Basic Framework, Challenges, and Future Development. in 2021 3rd International Academic Exchange Conference on Science and Technology Innovation (IAECST). vol. 2021, 2021 3rd International Academic Exchange Conference on Science and Technology Innovation, IAECST 2021, IEEE, U. S. A., pp. 413-419, 3rd International Academic Exchange Conference on Science and Technology Innovation, IAECST 2021, Guangzhou, China, 10/12/21. https://doi.org/10.1109/IAECST54258.2021.9695701

Ma C, Pu Y. Research Progress of Fine-grained Visual Classification: Basic Framework, Challenges, and Future Development. In 2021 3rd International Academic Exchange Conference on Science and Technology Innovation (IAECST). Vol. 2021. U. S. A.: IEEE. 2022. p. 413-419. (2021 3rd International Academic Exchange Conference on Science and Technology Innovation, IAECST 2021). doi: 10.1109/IAECST54258.2021.9695701

Ma, Congying ; Pu, Yuhan. / Research Progress of Fine-grained Visual Classification : Basic Framework, Challenges, and Future Development. 2021 3rd International Academic Exchange Conference on Science and Technology Innovation (IAECST). Vol. 2021 U. S. A. : IEEE, 2022. pp. 413-419 (2021 3rd International Academic Exchange Conference on Science and Technology Innovation, IAECST 2021).

@inproceedings{fdff18a403094501a80aa370ca17c9cc,

title = "Research Progress of Fine-grained Visual Classification: Basic Framework, Challenges, and Future Development",

abstract = "With the progress of multimedia technology, fine-grained visual classification (FGVC) has gradually attracted extensive attention in the field of computer vision. Thanks to the success of deep neural networks, both the accuracy and speed have achieved an unprecedented breakthrough. Hundreds of fine-grained classification techniques have been developed from the early, fully supervised methods to the current weakly ones. To this end, in this article, we provide a comprehensive survey of the recent achievements of FGVC. Specifically, we describe the formulation and setting of the FGVC, including the background, basic framework, and challenges. Then, we introduce the widely used datasets and compare the performance of different models. Lastly, we discuss the potential future directions of FGVC. ",

keywords = "deep learning, Fine-grained visual classification, weakly supervised learning, zero-shot learning",

author = "Congying Ma and Yuhan Pu",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 3rd International Academic Exchange Conference on Science and Technology Innovation, IAECST 2021 ; Conference date: 10-12-2021 Through 12-12-2021",

year = "2022",

month = feb,

day = "7",

doi = "10.1109/IAECST54258.2021.9695701",

language = "English",

volume = "2021",

series = "2021 3rd International Academic Exchange Conference on Science and Technology Innovation, IAECST 2021",

publisher = "IEEE",

pages = "413--419",

booktitle = "2021 3rd International Academic Exchange Conference on Science and Technology Innovation (IAECST)",

address = "USA United States",

}

TY - GEN

T1 - Research Progress of Fine-grained Visual Classification

T2 - 3rd International Academic Exchange Conference on Science and Technology Innovation, IAECST 2021

AU - Ma, Congying

AU - Pu, Yuhan

PY - 2022/2/7

Y1 - 2022/2/7

N2 - With the progress of multimedia technology, fine-grained visual classification (FGVC) has gradually attracted extensive attention in the field of computer vision. Thanks to the success of deep neural networks, both the accuracy and speed have achieved an unprecedented breakthrough. Hundreds of fine-grained classification techniques have been developed from the early, fully supervised methods to the current weakly ones. To this end, in this article, we provide a comprehensive survey of the recent achievements of FGVC. Specifically, we describe the formulation and setting of the FGVC, including the background, basic framework, and challenges. Then, we introduce the widely used datasets and compare the performance of different models. Lastly, we discuss the potential future directions of FGVC.

AB - With the progress of multimedia technology, fine-grained visual classification (FGVC) has gradually attracted extensive attention in the field of computer vision. Thanks to the success of deep neural networks, both the accuracy and speed have achieved an unprecedented breakthrough. Hundreds of fine-grained classification techniques have been developed from the early, fully supervised methods to the current weakly ones. To this end, in this article, we provide a comprehensive survey of the recent achievements of FGVC. Specifically, we describe the formulation and setting of the FGVC, including the background, basic framework, and challenges. Then, we introduce the widely used datasets and compare the performance of different models. Lastly, we discuss the potential future directions of FGVC.

KW - deep learning

KW - Fine-grained visual classification

KW - weakly supervised learning

KW - zero-shot learning

UR - http://www.scopus.com/inward/record.url?scp=85126962953&partnerID=8YFLogxK

U2 - 10.1109/IAECST54258.2021.9695701

DO - 10.1109/IAECST54258.2021.9695701

M3 - Chapter in a published conference proceeding

AN - SCOPUS:85126962953

VL - 2021

T3 - 2021 3rd International Academic Exchange Conference on Science and Technology Innovation, IAECST 2021

SP - 413

EP - 419

BT - 2021 3rd International Academic Exchange Conference on Science and Technology Innovation (IAECST)

PB - IEEE

CY - U. S. A.

Y2 - 10 December 2021 through 12 December 2021

ER -

Research Progress of Fine-grained Visual Classification: Basic Framework, Challenges, and Future Development

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this