.png){kind=icon}
返回
QBox: Partial Transfer Learning With Active Querying for Object Detection
.png){kind=icon}
PRE
AI
DOI：10.1109/TNNLS.2021.3111621.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Object detection requires plentiful data annotated with bounding boxes for model training. However, in many applications, it is difficult or even impossible to acquire a large set of labeled examples for the target task due to the privacy concern or lack of reliable annotators. On the other hand, due to the high-quality image search engines, such as Flickr and Google, it is relatively easy to obtain resource-rich unlabeled datasets, whose categories are a superset of those of target data. In this article, to improve the target model with cost-effective supervision from source data, we propose a partial transfer learning approach QBox to actively query labels for bounding boxes of source images. Specifically, we design two criteria, i.e., informativeness and transferability, to measure the potential utility of a bounding box for improving the target model. Based on these criteria, QBox actively queries the labels of the most useful boxes from the source domain and, thus, requires fewer training examples to save the labeling cost. Furthermore, the proposed query strategy allows annotators to simply labeling a specific region, instead of the whole image, and, thus, significantly reduces the labeling difficulty. Extensive experiments are performed on various partial transfer benchmarks and a real COVID-19 detection task. The results validate that QBox improves the detection accuracy with lower labeling cost compared to state-of-the-art query strategies for object detection.
Keyword:
Object detection
Labeling
Task analysis
Transfer learning
Training
Costs
Data models
Active learning (AL)
object detection
semisupervised learning
transfer learning
期刊
IF:
8.9
论文数:
7.6K
被引数:
7.2W
机构
暂无机构信息
引用论文
.png){kind=icon}
Mechanisms of Disease: local renin–angiotensin–aldosterone systems and the pathogenesis and treatment of cardiovascular disease疾病机制: 局部肾素-血管紧张素-醛固酮系统与心血管疾病的发病机制和治疗
PREAI
分享收藏The mechanism of cumene hydroperoxide-dependent lipid peroxidation: The function of cytochrome P-450
PREAI
分享收藏Insulin-like growth factor 2 and its enterocyte receptor are not required for adaptation in response to massive small bowel resection胰岛素样生长因子2及其肠上皮细胞受体不需要适应大量小肠切除术
OAAI
OAAI分享收藏
查看更多内容