Bottom-Up Attention Guidance for Recurrent Image Recognition

Hamed R. Tavakoli, Ali Borji, Rao Muhammad Anwer, Esa Rahtu, Juho Kannala

Abstract

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.
BibTeX
@inproceedings{tavakoli2018bottom,
  author = {Hamed R. Tavakoli and Ali Borji and Rao Muhammad Anwer and Esa Rahtu and Juho Kannala},
  title = {{Bottom-Up Attention Guidance for Recurrent Image Recognition}},
  booktitle = {ICIP},
  year = {2018},
  doi = {10.1109/icip.2018.8451537},
}

Loading related content...

Figure