...
机译:Generating self-attention activation maps for visual interpretations of convolutional neural networks
Tongji Univ, Dept Comp Sci & Technol, Shanghai 201804, Peoples R China;
Brunel Univ London, Dept Elect & Elect Engn, Uxbridge UB8 3PH, England;
Interpretable machine learning; Black -box models; Transparent models; Deep learning; Explainable artificial intelligence;