Due to the simpleness and high efficiency, single-stage object detectors have been widely applied in many computer vision applications . However, the low correlation between the classification score and localization accuracy of the predicted detections has severely hurt the localization accuracy of models. In this paper, IoU-aware single-stage object detector is proposed to solve this problem. Specifically, IoU-aware single-stage object detector predicts the IoU for each detected box. Then the classification score and predicted IoU are multiplied to compute the final detection confidence, which is more correlated with the localization accuracy. The detection confidence is then used as the input of the subsequent NMS and COCO AP computation, which will substantially improve the localization accuracy of models. Sufficient experiments on COCO and PASCAL VOC datasets demonstrate the effectiveness of IoU-aware single-stage object detector on improving model's localization accuracy. Without whistles and bells, the proposed method can substantially improve AP by 1.7% ∼ 1.9% and AP75 by 2.2% ∼ 2.5% on COCO test-dev. On PASCAL VOC, the proposed method can substantially improve AP by 2.9% ∼ 4.4% and AP80, AP90 by 4.6% ∼ 10.2%. The source code will be made publicly available.

No abstract

No abstract

To strengthen rural health services, the Chinese government has launched a series of policies to promote health workforce development. This study aims to understand the current status of village doctors and to explore the factors associated with village doctors’ job satisfaction in western China. It also attempts to provide references for further building capacities of village doctors and promoting the development of rural health service policy. A multistage stratified sampling method was used to obtain data from a cross-sectional survey on village doctors across 2 provinces of western China during 2012 to 2013. Quantitative data were collected from village doctors face-to-face, through a self-administered questionnaire. Among the 370 respondents, 225 (60.8%) aged 25 to 44 years, and 268 (72.4%) were covered by health insurance. Their income and working time calculated by workloads were higher than their self-report results. Being healthy, working fewer years, and having government funding and facilities were the positive factors toward their job satisfaction. Village doctors working with government-funded village clinics or facilities were more likely to feel satisfied. Problems identified previously such as low income and lack of insurance, heavy workload and aging were not detected in our study. Instead, village doctors were better-paid and better-covered by social insurance than other local rural residents, with increased job satisfaction. Government policies should pay more attention to improving the quality of rural health services and the income and security system of village doctors, to maintain and increase their job satisfaction and work enthusiasm. Further experimental study could evaluate effects of government input to improve rural health human resources and system development.