The Devil is in the Decoder: Classification, Regression and GANs
View Researcher's Other CodesDisclaimer: The provided code links for this paper are external links. Science Nest has no responsibility for the accuracy, legality or content of these links. Also, by downloading this code(s), you agree to comply with the terms of use as set out by the author(s) of the code(s).
Please contact us in case of a broken link from here
Authors | Nathan Silberman, Jasper Uijlings, Liang-Chieh Chen, Alireza Fathi, Vittorio Ferrari, Zbigniew Wojna, Sergio Guadarrama |
Journal/Conference Name | International Journal of Computer Vision |
Paper Category | Artificial Intelligence |
Paper 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. |
Date of publication | 2017 |
Code Programming Language | Python |
Comment |