Deep Autoresolution NetworksDownload PDF

29 Mar 2024 (modified: 18 Feb 2016)ICLR 2016 workshop submissionReaders: Everyone
Abstract: Despite the success of very deep convolutional neural networks, they currently operate at very low resolutions relative to modern cameras. Visual attention mechanisms address this by allowing models to access higher resolutions only when necessary. However, in certain cases, this higher resolution isn’t available. We show that autoresolution networks, which learn correspondences between lowresolution and high-resolution images, learn representations that improve lowresolution classification - without needing labeled high-resolution images.
Conflicts: google.com, usc.edu
4 Replies

Loading