Diptychs of human and machine perceptions
This work addresses the challenge of understanding perception gaps in AI for researchers and practitioners, but it is incremental as it builds on existing saliency and attention methods.
The authors tackled the problem of visualizing differences between human and machine perceptions by creating diptychs based on saliency maps and human visual focus, using them to discuss issues in task-oriented AI.
We propose visual creations that put differences in algorithms and humans \emph{perceptions} into perspective. We exploit saliency maps of neural networks and visual focus of humans to create diptychs that are reinterpretations of an original image according to both machine and human attentions. Using those diptychs as a qualitative evaluation of perception, we discuss some crucial issues of current \textit{task-oriented} artificial intelligence.