摘要
由一名新闻记者-机器人与机器学习的工作人员新闻编辑-每日新闻-机器学习的最新研究结果-智能系统已经出版。根据NewsRx编辑在中国山东的新闻报道，研究表明：“基于卷积神经网络(CNN)的目标检测器性能良好，但不能提取全局特征，不能建立目标像素之间的全局依赖关系。尽管变压器能够补偿这一点，但它没有融合卷积的优点。”这导致对局部特征细节的信息获取不足，速度慢，计算参数大。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Current study results on Machine Learning - Intelligent Systems have been published. According to news reporting out o f Shandong, People’s Republic of China, by NewsRx editors, research stated, “Convolutional neural network (CNN)-based object detectors perform excellently but l ack global feature extraction and cannot establish global dependencies between object pixels. Although the Transformer is able to compensate for this, it does not incorporate the advantages of convolution, which results in insufficient info rmation being obtained about the details of local features, as well as slow speed and large computational parameters.”
NETL
NSTL