Learning to Zoom: a Saliency-Based Sampling Layer for Neural Networks
© Springer Nature Switzerland AG 2018. We introduce a saliency-based distortion layer for convolutional neural networks that helps to improve the spatial sampling of input data for a given task. Our differentiable layer can be added as a preprocessing block to existing task networks and trained alto...
Main Authors: | Recasens, Adrià, Kellnhofer, Petr, Stent, Simon, Matusik, Wojciech, Torralba, Antonio |
---|---|
Other Authors: | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
Format: | Article |
Language: | English |
Published: |
Springer International Publishing
2021
|
Online Access: | https://hdl.handle.net/1721.1/137841 |
Similar Items
-
Gaze360: Physically Unconstrained Gaze Estimation in the Wild
by: Kellnhofer, Petr, et al.
Published: (2021) -
Where Should Saliency Models Look Next?
by: Borji, Ali, et al.
Published: (2018) -
Neural inverse knitting: From images to manufacturing instructions
by: Kaspar, Alexandre, et al.
Published: (2021) -
Eye Tracking for Everyone
by: Kellnhofer, Petr, et al.
Published: (2017) -
Contextual Influences on Saliency
by: Torralba, Antonio
Published: (2005)