Fine-Grained Image Analysis with Deep Learning: A Survey
Research output: Contribution to journal › Journal article › Research › peer-review
Standard
Fine-Grained Image Analysis with Deep Learning : A Survey. / Wei, Xiu Shen; Song, Yi Zhe; Mac Aodha, Oisin; Wu, Jianxin; Peng, Yuxin; Tang, Jinhui; Yang, Jian; Belongie, Serge.
In: IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 44, No. 12, 2022, p. 8927-8948.Research output: Contribution to journal › Journal article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - Fine-Grained Image Analysis with Deep Learning
T2 - A Survey
AU - Wei, Xiu Shen
AU - Song, Yi Zhe
AU - Mac Aodha, Oisin
AU - Wu, Jianxin
AU - Peng, Yuxin
AU - Tang, Jinhui
AU - Yang, Jian
AU - Belongie, Serge
N1 - Publisher Copyright: IEEE
PY - 2022
Y1 - 2022
N2 - Fine-grained image analysis (FGIA) is a longstanding and fundamental problem in computer vision and pattern recognition, which underpins a diverse set of real-world applications. The task of FGIA targets analyzing visual objects from subordinate categories, e.g., species of birds or models of cars. The small inter-class and large intra-class variation inherent to fine-grained image analysis makes it a challenging problem. Capitalizing on advances in deep learning, in recent years we have witnessed remarkable progress in deep learning powered FGIA. In this paper we present a systematic survey of these advances, where we attempt to re-define and broaden the field of FGIA by consolidating two fundamental fine-grained research areas -- fine-grained image recognition and fine-grained image retrieval. In addition, we also review other key issues of FGIA, such as publicly available benchmark datasets and related domain-specific applications. We conclude by highlighting several research directions and open problems which need further exploration from the community.
AB - Fine-grained image analysis (FGIA) is a longstanding and fundamental problem in computer vision and pattern recognition, which underpins a diverse set of real-world applications. The task of FGIA targets analyzing visual objects from subordinate categories, e.g., species of birds or models of cars. The small inter-class and large intra-class variation inherent to fine-grained image analysis makes it a challenging problem. Capitalizing on advances in deep learning, in recent years we have witnessed remarkable progress in deep learning powered FGIA. In this paper we present a systematic survey of these advances, where we attempt to re-define and broaden the field of FGIA by consolidating two fundamental fine-grained research areas -- fine-grained image recognition and fine-grained image retrieval. In addition, we also review other key issues of FGIA, such as publicly available benchmark datasets and related domain-specific applications. We conclude by highlighting several research directions and open problems which need further exploration from the community.
KW - Birds
KW - Deep Learning
KW - Deep learning
KW - Fine-Grained Image Recognition
KW - Fine-Grained Image Retrieval
KW - Fine-Grained Images Analysis
KW - Image analysis
KW - Image recognition
KW - Image retrieval
KW - Task analysis
KW - Visualization
U2 - 10.1109/TPAMI.2021.3126648
DO - 10.1109/TPAMI.2021.3126648
M3 - Journal article
C2 - 34752384
AN - SCOPUS:85120048736
VL - 44
SP - 8927
EP - 8948
JO - IEEE Transactions on Pattern Analysis and Machine Intelligence
JF - IEEE Transactions on Pattern Analysis and Machine Intelligence
SN - 0162-8828
IS - 12
ER -
ID: 301817074