Bottom-Up Attention Guidance for Recurrent Image Recognition
Hamed R. Tavakoli, Ali Borji, Rao Muhammad Anwer, Esa Rahtu, Juho Kannala · 2018
This paper presents a recurrent neural network architecture, guided by the bottom-up attention, for the recognition task. The proposed architecture processes an input image as a sequence of selectively chosen patches. The patches are chosen from the salient regions of the input image. Using human driven saliency maps from gaze, the benefit of such a selection process is first shown. Next, the performance of computational models of bottom-up attention are assessed as alternative to human attention.