no code implementations • 23 Jun 2022 • Xia Hua, Mingxin Li, Junxiong Fei, Yu Shi, Jianguo Liu, Hanyu Hong
In most of these networks, only the features refined by the attention maps can be passed to the next layer and the attention maps of different layers are separated from each other, which does not make full use of the attention information from different layers in the CNN.