期刊
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
卷 44, 期 12, 页码 8927-8948出版社
IEEE COMPUTER SOC
DOI: 10.1109/TPAMI.2021.3126648
关键词
Image recognition; Image analysis; Deep learning; Task analysis; Image retrieval; Birds; Visualization; Fine-grained images analysis; deep learning; fine-grained image recognition; fine-grained image retrieval
资金
- National Key R&D Program of China [2021YFA1001100]
- Natural Science Foundation of Jiangsu Province of China [BK20210340]
- National Natural Science Foundation of China [61925201, 62132001, 61772256]
- Fundamental Research Funds for the Central Universities [30920041111]
- CAAI-Huawei MindSpore Open Fund
- 111 Program [B13022]
Fine-grained image analysis is a longstanding and fundamental problem in computer vision, and has seen remarkable progress driven by deep learning. This field involves analyzing visual objects from subordinate categories and presents challenges due to small inter-class and large intra-class variation.
Fine-grained image analysis (FGIA) is a longstanding and fundamental problem in computer vision and pattern recognition, and 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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据