期刊
ACM COMPUTING SURVEYS
卷 54, 期 11S, 页码 -出版社
ASSOC COMPUTING MACHINERY
DOI: 10.1145/3519022
关键词
Deep learning for few-shot object detection; dataset for object detection; benchmarks and metrics for object detection
资金
- MIUR grant Departments of Excellence 2018-2022 of the Sapienza University Computer Science Department
- ERC [802554]
Deep learning approaches have made significant progress in many fields with the support of large amounts of data. However, few-shot learning research is of great practical importance as it can effectively address the problem of scarce data, reducing the cost of data acquisition and achieving better generalization capability.
Deep learning approaches have recently raised the bar in many fields, from Natural Language Processing to Computer Vision, by leveraging large amounts of data. However, they could fail when the retrieved information is not enough to fit the vast number of parameters, frequently resulting in overfitting and therefore in poor generalizability. Few-Shot Learning aims at designing models that can effectively operate in a scarce data regime, yielding learning strategies that only need few supervised examples to be trained. These procedures are of both practical and theoretical importance, as they are crucial for many real-life scenarios in which data is either costly or even impossible to retrieve. Moreover, they bridge the distance between current data-hungry models and human-like generalization capability. Computer vision offers various tasks that can be few-shot inherent, such as person re-identification. This survey, which to the best of our knowledge is the first tackling this problem, is focused on Few-Shot Object Detection, which has received far less attention compared to Few-Shot Classification due to the intrinsic challenge level. In this regard, this review presents an extensive description of the approaches that have been tested in the current literature, discussing their pros and cons, and classifying them according to a rigorous taxonomy.
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