ResNet, short for Residual Network, is a deep learning architecture proposed by He Kaiming, Zhang Xiangyu, Ren Shaoqing and Sun Jian from Microsoft Research in 2015.Deep Residual Learning for Image Recognition", the paper describes in detail the ResNet architecture design, implementation details and experimental results.

ResNet effectively solves the gradient vanishing and gradient exploding problems that occur as the network depth increases by adding residual connections (or shortcut connections) to the network, making it easy to stack the network to dozens or even hundreds of layers without performance degradation. In competitions such as ILSVRC and COCO, ResNet has won many first prizes.