reproducibilityindex.ai

Towards Compact Single Image Super-Resolution via Contrastive Self-distillation

Authors: Yanbo Wang, Shaohui Lin, Yanyun Qu, Haiyan Wu, Zhizhong Zhang, Yuan Xie, Angela Yao

Reproducibility Variable	Result	LLM Response
Research Type	Experimental	Extensive experiments demonstrate that the proposed CSD scheme effectively compresses and accelerates several standard SR models such as EDSR, RCAN and CARN.
Researcher Affiliation	Academia	1East China Normal University 2Xiamen University 3National University of Singapore
Pseudocode	Yes	Algorithm 1 Pseudocode of CSD in a Py Torch-like style
Open Source Code	Yes	Code is available at https://github.com/Booooooooooo/CSD.
Open Datasets	Yes	We train all SR models with 800 training images on DIV2K and evaluate on the 100 validation images. We additionally test on four SR benchmarks: Set5[Bevilacqua et al., 2012], Set14[Zeyde et al., 2010], BSD100[Martin et al., 2001] and Urban100[Huang et al., 2015].
Dataset Splits	Yes	We train all SR models with 800 training images on DIV2K and evaluate on the 100 validation images.
Hardware Specification	Yes	Our CSD scheme is implemented by Py Torch 1.2.0 and Mind Spore 1.2.0[Huawei, 2020] with one NVIDIA TITAN RTX GPU.
Software Dependencies	Yes	Our CSD scheme is implemented by Py Torch 1.2.0 and Mind Spore 1.2.0[Huawei, 2020]
Experiment Setup	Yes	The models are trained with ADAM optimizer by setting β1 = 0.9, β2 = 0.999, and ϵ = 10 8. The batch size and total epochs are set to 16 and 300 epochs, respectively. The initial learning rate is 10 4 and decayed by 10 at every 2 105 iterations.