SRLibrary: Comparing different loss functions for super-resolution over various convolutional architectures
| Autor: | Erol Seke, Sahin Isik, Yildiray Anagun |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Computer science
business.industry Process (computing) 020207 software engineering Pattern recognition DSSim 02 engineering and technology Time cost Convolutional neural network Superresolution Noise Signal Processing 0202 electrical engineering electronic engineering information engineering Media Technology 020201 artificial intelligence & image processing Computer Vision and Pattern Recognition Artificial intelligence Electrical and Electronic Engineering Performance improvement business Parametric statistics |
| Zdroj: | Journal of Visual Communication and Image Representation. 61:178-187 |
| ISSN: | 1047-3203 |
| Popis: | This study analyzes the effectiveness of various loss functions on performance improvement for Single Image Super-Resolution (SISR) using Convolutional Neural Network (CNN) models by surrogating the reconstructive map between Low Resolution (LR) and High Resolution (HR) images with convolutional filters. In total, eight loss functions are separately incorporated with Adam optimizer. Through experimental evaluations on different datasets, it is observed that some parametric and non-parametric robust loss functions promise impressive accuracies whereas remaining ones are sensitive to noise that misleads the learning process and consequently resulting in lower quality HR outcomes. Eventually, it turns out that the use of either Difference of Structural Similarity (DSSIM), Charbonnier or L1 loss functions within the optimization mechanism would be a proper choice, by considering their excellent reconstruction results. Among them, Charbonnier and L1 loss functions are fastest ones when the computational time cost is examined during training stage. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect