IEEE Journal of Selected Topics in Signal Processing

Where Is the Model Looking At? Concentrate and Explain the Network Attention

An Explainable Attribute-based Multi-task (EAT) framework that concentrates model attention on discriminative image regions and grounds attribute-based textual explanations back onto the image.

Wenjia Xu, Jiuniu Wang, Yang Wang, Guangluan Xu, Daoyu Lin, Wei Dai, Yirong Wu