期刊
IET COMPUTER VISION
卷 16, 期 8, 页码 747-758出版社
WILEY
DOI: 10.1049/cvi2.12122
关键词
-
资金
- National Natural Science Foundation of China [61801190]
- National Key Research and Development Project of China [2019YFC0409105]
- Industrial Technology Research and Development Funds of Jilin Province [2019C054-3]
- 'Thirteenth Five-Year Pla' Scientific Research Planning Project of Education Department of Jilin Province [JKH20200678KJ, JJKH20200997KJ]
- Fundamental Research Funds for the Central Universities, JLU
- Graduate Innovation Fund of Jilin University
This paper presents a method to improve face detection by replacing misaligned annotations with predicted bounding-boxes. The proposed Bounding-Box Deep Calibration (BDC) method achieves higher precision and recall rates without increasing inference time and memory consumption.
Modern convolutional neural networks (CNNs)-based face detectors have achieved tremendous strides due to large annotated datasets. However, misaligned results with high detection confidence but low localization accuracy restrict the further improvement of detection performance. In this paper, the authors first predict high confidence detection results on the training set itself. Surprisingly, a considerable part of them exist in the same misalignment problem. Then, the authors carefully examine these cases and point out that annotation misalignment is the main reason. Later, a comprehensive discussion is given for the replacement rationality between predicted and annotated bounding-boxes. Finally, the authors propose a novel Bounding-Box Deep Calibration (BDC) method to reasonably replace misaligned annotations with model predicted bounding-boxes and offer calibrated annotations for the training set. Extensive experiments on multiple detectors and two popular benchmark datasets show the effectiveness of BDC on improving models' precision and recall rate, without adding extra inference time and memory consumption. Our simple and effective method provides a general strategy for improving face detection, especially for light-weight detectors in real-time situations.
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