Examining the role of attention during feature binding in visuospatial working memory

2Guangxi Key Laboratory of Hybrid Computation and IC Design Analysis, Nan Ning, China Correspondence Shi-Bin Xuan, School of Artificial Intelligence, Guangxi Minzu University, Daxue East Road 188, Nanning, China. Email: xshibin1997@126.com Funding information National Natural Science Foundation of China, Grant/Award Number: 61866003 gent medical treatment. It can preprocess medical images to help doctors better diagnose diseases. Class activation map (CAM) is an important technology in weakly supervised segmentation, which can achieve image segmentation without pixel-level label training. This technology can well meet the needs of medical image segmentation. However, CAM obtaining is still unperfect due to global average pooling (GAP). GAP will cause important and non-important regions to be given equal attention during the training process. So, CAM cannot demarcate the boundary of the target regions well. In order to solve this problem, a global weighted average pooling network fusing the grayscale information of medical images is proposed. The proposed network can solve the problem that GAP has the same concern for important regions and non-important regions of the feature map, because the different weights can be learned for different positions of the feature map before the GAP in the proposed model. At the same time, because of the grayscale difference between the tumor area and the non-tumor area in the brain tumor image, the low-level grayscale information of the medical image is fused with the high-level semantic

Automated summary

A global weighted average pooling network is proposed in this study to solve the imperfection of class activation map (CAM) obtained in weakly supervised segmentation. The proposed model allows learning different weights for different positions of the feature map before global average pooling (GAP), addressing the issue of equal attention given by GAP to important and non-important regions. Additionally, the low-level grayscale information of medical images is fused with high-level semantic information due to the grayscale difference between tumor and non-tumor areas in brain tumor images.