Learning to Zoom: a Saliency-Based Sampling Layer for Neural Networks

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...

Full description

Bibliographic Details
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

Internet

https://hdl.handle.net/1721.1/137841

Similar Items