A Decoder-free Transformer-like Architecture for High-efficiency Single Image Deraining

Authors: Xiao Wu, Ting-Zhu Huang, Liang-Jian Deng, Tian-Jing Zhang

IJCAI 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments demonstrate the superiority of DFTL compared with competitive Transformer architectures, e.g., Vi T, DETR, IPT, Uformer, and Restormer. The code is available at https://github.com/Xiao Xiao Woo/derain. In this section, we demonstrate the advantages of proposed method via comprehensive experiments on both synthetic and real datasets.
Researcher Affiliation Academia Xiao Wu , Ting-Zhu Huang , Liang-Jian Deng and Tian-Jing Zhang University of Electronic Science and Technology of China, Chengdu, 611731 wxwsx1997@gmail.com, tingzhuhuang@126.com, liangjian.deng@uestc.edu.cn, zhangtianjinguestc@163.com
Pseudocode No The paper does not contain any pseudocode or algorithm blocks.
Open Source Code Yes The code is available at https://github.com/Xiao Xiao Woo/derain.
Open Datasets Yes We evaluate our model on five synthetic datasets to compare quantitative results... Methods Datasets Rain12 Rain200L Rain200H DID-Data DDN-Data
Dataset Splits No The paper discusses evaluating models on various datasets but does not explicitly provide details about specific training, validation, or test dataset splits, such as percentages or sample counts.
Hardware Specification No The paper mentions 'GPU memory requirements' and training on a 'single GPU' but does not provide specific hardware details such as GPU model numbers, CPU types, or memory amounts used for experiments.
Software Dependencies No The paper does not provide specific software dependency details, such as programming language versions or library version numbers, needed to replicate the experiment.
Experiment Setup No The paper states 'All models are trained in the same framework with default settings as their original codes' and refers to supplementary materials for 'implementation details', but does not include specific hyperparameter values or training configurations in the main text.