Notice: This website is continuously updated as new conference proceedings and journal volumes are published. Consequently, the figures presented here may differ from those reported in our publications.
A brief overview of our methodology is provided on the Methods page, along with references to publications documenting our approach and links to the code and data used in each study.
The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates.
Attention-based Pyramid Dilated Lattice Network for Blind Image Denoising
Authors: Mohammad Nikzad, Yongsheng Gao, Jun Zhou
IJCAI 2021 | Venue PDF | LLM Run Details | Input Tokens: 16,169 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 4,704 Total number of tokens produced by the LLM (including reasoning/thinking tokens) for this paper's analysis.
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Our extensive experimental investigation verifies the effectiveness and efficiency of the APDL architecture for image denoising as well as JPEG artifacts suppression tasks. |
| Researcher Affiliation | Academia | Mohammad Nikzad , Yongsheng Gao and Jun Zhou Institute for Integrated and Intelligent Systems (IIIS), Griffith University, Australia m.nikzaddehaji@griffithuni.edu.au, yongsheng.gao, jun.zhou@griffith.edu.au |
| Pseudocode | No | The paper includes architectural diagrams (Figure 1 and Figure 2) and descriptions of components, but it does not contain structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide any statement about releasing source code or a link to a code repository. |
| Open Datasets | Yes | We use 400 images of size 180 180 from Berkeley segmentation dataset (BSD500) [Arbelaez et al., 2010] as the training data for the image restoration tasks. |
| Dataset Splits | No | The paper mentions training and test datasets but does not explicitly provide details about a validation dataset split or how it was used in relation to training and testing. |
| Hardware Specification | Yes | All models are trained using a single NVIDIA Geforce Titan RTX GPU card. |
| Software Dependencies | No | The paper mentions using the 'Adam optimizer' and 'cosine annealing technique' but does not specify version numbers for any software dependencies or frameworks (e.g., Python, PyTorch, TensorFlow). |
| Experiment Setup | Yes | We adopt Adam optimizer with default hyper-parameters and 10 5 as the weight decay for the training of the proposed models. All models are trained for 100 epochs with minibatch size of 32 and initial learning rate of 0.001 which is decayed to 10 5 by adopting cosine annealing technique . |