Invertible Residual Rescaling Models
Authors: Jinmin Li, Tao Dai, Yaohua Zha, Yilu Luo, Longfei Lu, Bin Chen, Zhi Wang, Shu-Tao Xia, Jingyun Zhang
IJCAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments show that our IRRM performs significantly better than other state-of-the-art methods with much fewer parameters and complexity. |
| Researcher Affiliation | Collaboration | Jinmin Li1 , Tao Dai2, , Yaohua Zha1,3 , Yilu Luo1 , Longfei Lu1 , Bin Chen4 , Zhi Wang1 , Shu-Tao Xia1,3 , Jingyun Zhang5 1Tsinghua Shenzhen International Graduate School, Tsinghua University 2College of Computer Science and Software Engineering, Shenzhen University 3Research Center of Artificial Intelligence, Peng Cheng Laboratory 4Department of Computer Science and Technology, Harbin Institute of Technology, Shenzhen 5We Chat Pay Lab33, Tencent |
| Pseudocode | No | The paper describes the model architecture and mathematical formulations but does not include a clearly labeled pseudocode block or algorithm. |
| Open Source Code | Yes | The code will be available at https://github.com/THUKingmin/IRRM. |
| Open Datasets | Yes | The DIV2K dataset [Agustsson and Timofte, 2017] is adopted to train our IRRM. Besides, we evaluate our models with PSNR and SSIM metrics (Y channel) on commonly used benchmarks: Set5 [Bevilacqua et al., 2012], Set14 [Yang et al., 2010], B100 [Martin et al., 2001], Urban100 [Huang et al., 2015] and DIV2K valid [Agustsson and Timofte, 2017] datasets. |
| Dataset Splits | No | The paper mentions using DIV2K for training and other datasets including 'DIV2K valid' for evaluation, but it does not specify explicit train/validation/test splits of a single dataset, nor does it detail how validation data was used for hyperparameter tuning or early stopping during training. |
| Hardware Specification | No | The paper mentions 'The batch size is set to 16 for per GPU', but it does not specify the exact GPU model or any other hardware details used for running experiments. |
| Software Dependencies | No | The paper states 'Py Torch is used as the implementation framework' but does not provide specific version numbers for PyTorch or any other software dependencies. |
| Experiment Setup | Yes | Our IRRM is composed of one or two Residual Downscaling Modules (RDMs), containing eight Invertible Residual Blocks (IRBs). These models are trained using the ADAM [Kingma and Ba, 2014] optimizer with β1 = 0.9 and β2 = 0.999. The batch size is set to 16 for per GPU, and the initial learning rate is fixed at 2 10 4, which decays by half every 10k iterations. λ1, λ2 and λ3 are set to 8, 8 and 1, respectively. Finally, we augment training images by flipping and rotating. |