Residual Attribute Attention Network for Face Image Super-Resolution

Authors: Jingwei Xin, Nannan Wang, Xinbo Gao, Jie Li9054-9061

AAAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments on benchmark database illustrate that RAAN significantly outperforms state-of-the-arts for very low-resolution face SR problem, both quantitatively and qualitatively.
Researcher Affiliation Academia Jingwei Xin, Nannan Wang, Xinbo Gao, Jie Li State Key Laboratory of Integrated Services Networks, School of Electronic Engineering, Xidian University, Xi an 710071, China State Key Laboratory of Integrated Services Networks, School of Telecommunications Engineering, Xidian University, Xi an 710071, China Corresponding author: Nannan Wang (nnwang@xidian.edu.cn)
Pseudocode No The paper describes the network architecture and mathematical formulations but does not include any structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide an explicit statement about the availability of open-source code or a link to a code repository.
Open Datasets Yes We conduct extensive experiments on celeb A dataset (Liu, Luo, and Wang 2015). We use the first 18000 images for training, and the following 100 images for testing.
Dataset Splits No We use the first 18000 images for training, and the following 100 images for testing.
Hardware Specification Yes Training a basic RAAN on celeb A dataset generally takes 5 hours with one Titan X Pascal GPU.
Software Dependencies No We implement our moel using the pytorch environment.
Experiment Setup Yes Adam with an initial learning rate of 3 10 4 are used in our model. The batch size is set to 16. We empirically set "lambda" = 1 and "gamma" = 0.01.