YOLOv7: Trainable bag-of-freebies sets new state-of the art for real-time object detectorsMotivationIn the recent years the real-time object detector focus on architecture for different edge device or GPU. Authors focus on the optimized moduels and optimization methods which may increasing training cost for improving the accuracy of obejct detection, but without increasing the inference cost. Th..

Making VGG-style ConvNets Great AgainMotivationPrevious model that have multi branch like VGG require more time than single branch, So authors propose reparameterization VGG that combine multi branch with convolution and batch normalization layer after training. It can shorten inferrence time and reduce parameters.Main IdeaRecent architecture are based on automatic or manual architecture search ..