Multi-Scale Face Restoration With Sequential Gating Ensemble Network
Authors: Jianxin Lin, Tiankuang Zhou, Zhibo Chen
AAAI 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experiment results demonstrate that our SGEN is more effective at multiscale human face restoration with more image details and less noise than state-of-the-art image restoration models. |
| Researcher Affiliation | Academia | University of Science and Technology of China, Hefei, China {linjx, zhoutk}@mail.ustc.edu.cn, chenzhibo@ustc.edu.cn |
| Pseudocode | No | The paper describes the network architecture using mathematical formulas (Equations 1-8) and explains the Sequential Gating Unit with an equation (Equation 9), but does not provide structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not include any explicit statement about the availability of open-source code for the described methodology, nor does it provide a link to a code repository. |
| Open Datasets | Yes | We carry out experiments below on the widely used face dataset Celeb A (Liu et al. 2015) containing 202599 cropped celebrity faces. |
| Dataset Splits | Yes | We set aside 30000 images as test set, 20000 images as validation set, and the rest as training set. |
| Hardware Specification | Yes | We train all the networks on one NVIDIA K80 GPU. |
| Software Dependencies | No | The paper does not specify version numbers for any software dependencies, libraries, or frameworks used (e.g., Python, TensorFlow, PyTorch, CUDA, etc.). |
| Experiment Setup | Yes | In the experiments, we set N = 3 levels for the SGEN to achieve a trade-off between performance and computation cost and the weight λ is set to 0.1. We use the adaptive learning method Adam (Kingma and Ba 2014) as the optimization algorithm with learning rate of 0.0002. Minibatch size is set to 64 for every experiments. |