针对一次即可识别图中物体(You Only Look Once v8,YOLOv8)的模型在密集缺陷检测任务中因特征提取能力不足导致的漏检、错检等问题,文章提出SE-YOLO算法。改进后的SE-YOLO密集缺陷检测算法为了使模型关注更多维度的特征信息,使用Swin Tr...针对一次即可识别图中物体(You Only Look Once v8,YOLOv8)的模型在密集缺陷检测任务中因特征提取能力不足导致的漏检、错检等问题,文章提出SE-YOLO算法。改进后的SE-YOLO密集缺陷检测算法为了使模型关注更多维度的特征信息,使用Swin Transformer网络作为主干网络。文章引入中心化特征金字塔模块,以提取全局长距离相关性,可以尽可能地保留输入图像的局部角点区域信息。改进后的SE-YOLO密集缺陷检测算法可以更加准确地检测出缺陷的类别和位置,在密集缺陷检测任务中具有较高的精确度与鲁棒性。展开更多
In the quantum Monte Carlo(QMC)method,the pseudo-random number generator(PRNG)plays a crucial role in determining the computation time.However,the hidden structure of the PRNG may lead to serious issues such as the br...In the quantum Monte Carlo(QMC)method,the pseudo-random number generator(PRNG)plays a crucial role in determining the computation time.However,the hidden structure of the PRNG may lead to serious issues such as the breakdown of the Markov process.Here,we systematically analyze the performance of different PRNGs on the widely used QMC method known as the stochastic series expansion(SSE)algorithm.To quantitatively compare them,we introduce a quantity called QMC efficiency that can effectively reflect the efficiency of the algorithms.After testing several representative observables of the Heisenberg model in one and two dimensions,we recommend the linear congruential generator as the best choice of PRNG.Our work not only helps improve the performance of the SSE method but also sheds light on the other Markov-chain-based numerical algorithms.展开更多
文摘针对一次即可识别图中物体(You Only Look Once v8,YOLOv8)的模型在密集缺陷检测任务中因特征提取能力不足导致的漏检、错检等问题,文章提出SE-YOLO算法。改进后的SE-YOLO密集缺陷检测算法为了使模型关注更多维度的特征信息,使用Swin Transformer网络作为主干网络。文章引入中心化特征金字塔模块,以提取全局长距离相关性,可以尽可能地保留输入图像的局部角点区域信息。改进后的SE-YOLO密集缺陷检测算法可以更加准确地检测出缺陷的类别和位置,在密集缺陷检测任务中具有较高的精确度与鲁棒性。
基金Project supported by the National Natural Science Foundation of China(Grant Nos.12274046,11874094,and 12147102)Chongqing Natural Science Foundation(Grant No.CSTB2022NSCQ-JQX0018)Fundamental Research Funds for the Central Universities(Grant No.2021CDJZYJH-003).
文摘In the quantum Monte Carlo(QMC)method,the pseudo-random number generator(PRNG)plays a crucial role in determining the computation time.However,the hidden structure of the PRNG may lead to serious issues such as the breakdown of the Markov process.Here,we systematically analyze the performance of different PRNGs on the widely used QMC method known as the stochastic series expansion(SSE)algorithm.To quantitatively compare them,we introduce a quantity called QMC efficiency that can effectively reflect the efficiency of the algorithms.After testing several representative observables of the Heisenberg model in one and two dimensions,we recommend the linear congruential generator as the best choice of PRNG.Our work not only helps improve the performance of the SSE method but also sheds light on the other Markov-chain-based numerical algorithms.