4篇
您的检索式：作者名="TANG Linbo"
|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | Multi-scale object detection by top-down and bottom-up feature pyramid network显示文摘While moving ahead with the object detection technology, especially deep neural networks, many related tasks, such as medical application and industrial automation, have achieved great success. However, the detection of objects with multiple aspect ratios and scales is still a key problem. This paper proposes a top-down and bottom-up feature pyramid network(TDBU-FPN),which combines multi-scale feature representation and anchor generation at multiple aspect ratios. First, in order to build the multi-scale feature map, this paper puts a number of fully convolutional layers after the backbone. Second, to link neighboring feature maps, top-down and bottom-up flows are adopted to introduce context information via top-down flow and supplement suboriginal information via bottom-up flow. The top-down flow refers to the deconvolution procedure, and the bottom-up flow refers to the pooling procedure. Third, the problem of adapting different object aspect ratios is tackled via many anchor shapes with different aspect ratios on each multi-scale feature map. The proposed method is evaluated on the pattern analysis, statistical modeling and computational learning visual object classes(PASCAL VOC)dataset and reaches an accuracy of 79%, which exhibits a 1.8% improvement with a detection speed of 23 fps. | ZHAO Baojun ZHAO Boya TANG Linbo WANG Wenzheng WU Chen | 2019 | Journal of Systems Engineering and Electronics2019，30，1： | 11 |
| 2 | Increasing Momentum-Like Factors:A Method for Reducing Training Errors on Multiple GPUs显示文摘In distributed training,increasing batch size can improve parallelism,but it can also bring many difficulties to the training process and cause training errors.In this work,we investigate the occurrence of training errors in theory and train ResNet-50 on CIFAR-10 by using Stochastic Gradient Descent(SGD) and Adaptive moment estimation(Adam) while keeping the total batch size in the parameter server constant and lowering the batch size on each Graphics Processing Unit(GPU).A new method that considers momentum to eliminate training errors in distributed training is proposed.We define a Momentum-like Factor(MF) to represent the influence of former gradients on parameter updates in each iteration.Then,we modify the MF values and conduct experiments to explore how different MF values influence the training performance based on SGD,Adam,and Nesterov accelerated gradient.Experimental results reveal that increasing MFs is a reliable method for reducing training errors in distributed training.The analysis of convergent conditions in distributed training with consideration of a large batch size and multiple GPUs is presented in this paper. | Yu Tang Zhigang Kan Lujia Yin Zhiquan Lai Zhaoning Zhang Linbo Qiao Dongsheng Li | 2022 | Tsinghua Science and Technology2022，27，1： | 1 |
| 3 | Tissue Engineering Materials: Preshaping and Injectable显示文摘 | Dianying Jing Zhen Wang Wen Zhu Junchuan Zhang Shifeng Duan Stefan Graeter Jianguo Sun Jinghuan Huang Huan Zhang Jian Tang Peng Liu Linbo Wu Hong Zhang Jiandong Ding | 2005 | Journal of US-China Medical Science2005，2，4： | 0 |
| 4 | High-throughput sorting of two-color fluorescent-labeled zebrafish embryos显示文摘The zebrafish embryos were widely employed in genetics,development and drug discovery studies as miniatured animal models.Sorting of two-color fluorescent embryos is often required in large-scale experiments but it is challenging to manually sort with high efficiency.Here,we reported a high-throughput sorting system for two-color fluorescent zebraflsh embryos.The embryos can be automatically loaded from a sample pool and sorted based on the average fluorescent intensity.The two-color fluorescent signals were split into two lines and detected by an area array camera.The system achieves the sorting of 100 embryos in less than 10 min with an accuracy of greater than 95%. | Hongzhen Tang Linbo Wang Xiaohu Chen Chong Chen Hui Li Guang Yang | 2023 | Journal of Innovative Optical Health Sciences2023，16，5： | 0 |
您所在的机构暂未开通此部分的功能，请联系管理员