UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

The Devil is in the Decoder: Classification, Regression and GANs

Wojna, Z; Ferrari, V; Guadarrama, S; Silberman, N; Chen, L-C; Fathi, A; Uijlings, J; (2019) The Devil is in the Decoder: Classification, Regression and GANs. International Journal of Computer Vision , 127 pp. 1694-1706. 10.1007/s11263-019-01170-8. Green open access

[thumbnail of 1707.05847.pdf]
Preview
Text
1707.05847.pdf - Accepted Version

Download (3MB) | Preview

Abstract

Many machine vision applications, such as semantic segmentation and depth prediction, require predictions for every pixel of the input image. Models for such problems usually consist of encoders which decrease spatial resolution while learning a high-dimensional representation, followed by decoders who recover the original input resolution and result in low-dimensional predictions. While encoders have been studied rigorously, relatively few studies address the decoder side. This paper presents an extensive comparison of a variety of decoders for a variety of pixel-wise tasks ranging from classification, regression to synthesis. Our contributions are: (1) decoders matter: we observe significant variance in results between different types of decoders on various problems. (2) We introduce new residual-like connections for decoders. (3) We introduce a novel decoder: bilinear additive upsampling. (4) We explore prediction artifacts.

Type: Article
Title: The Devil is in the Decoder: Classification, Regression and GANs
Open access status: An open access version is available from UCL Discovery
DOI: 10.1007/s11263-019-01170-8
Publisher version: https://doi.org/10.1007/s11263-019-01170-8
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
Keywords: Machine Vision, Computer Vision, Neural Network Architectures, Decoders, 2D imagery, perpixel prediction, semantic segmentation, depth prediction, GANs
UCL classification: UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Med Phys and Biomedical Eng
URI: https://discovery.ucl.ac.uk/id/eprint/10069373
Downloads since deposit
Loading...
55Downloads
Download activity - last month
Loading...
Download activity - last 12 months
Loading...
Downloads by country - last 12 months
Loading...

Archive Staff Only

View Item View Item