Robust And Interpretable Blind Image Denoising Via Bias-Free Convolutional Neural Networks
Authors: Sreyas Mohan, Zahra Kadkhodaie, Eero P. Simoncelli, Carlos Fernandez-Granda
ICLR 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We provide extensive empirical evidence that current state-of-the-art architectures systematically overfit to the noise levels in the training set, performing very poorly at new noise levels. We show that strong generalization can be achieved through a simple architectural modification: removing all additive constants. The resulting "bias-free" networks attain state-of-the-art performance over a broad range of noise levels, even when trained over a narrow range. |
| Researcher Affiliation | Academia | Sreyas Mohan Center for Data Science New York University sm7582@nyu.edu, Zahra Kadkhodaie Center for Data Science New York University zk388@nyu.edu, Eero P. Simoncelli Center for Neural Science, and Howard Hughes Medical Institute New York University eero.simoncelli@nyu.edu, Carlos Fernandez-Granda Center for Data Science, and Courant Inst. of Mathematical Sciences New York University cfgranda@cims.nyu.edu |
| Pseudocode | No | The paper describes algorithms and architectures in text but does not include structured pseudocode or algorithm blocks. |
| Open Source Code | No | No explicit statement or link providing access to open-source code for the described methodology. |
| Open Datasets | Yes | Our experiments are carried out on 180 180 natural images from the Berkeley Segmentation Dataset (Martin et al., 2001) to be consistent with previous results (Schmidt & Roth, 2014; Chen & Pock, 2017; Zhang et al., 2017). |
| Dataset Splits | No | The paper mentions using "validation PSNR" for early stopping but does not specify the size or percentage of the validation set within the provided training or testing images. It states "We use a training set of 400 images. ... A test set containing 68 images is used for evaluation." |
| Hardware Specification | No | No specific hardware details (e.g., GPU/CPU models, memory specifications) used for running experiments are provided in the paper. |
| Software Dependencies | No | The paper mentions the use of "Adam Optimizer" and "Batch Normalization" and specific architectures like "Dn CNN", "Recurrent CNN", "UNet", and "Simplified Dense Net", but does not provide specific version numbers for any software libraries or frameworks used in their implementation. |
| Experiment Setup | Yes | We train Dn CNN and its bias-free counterpart using the Adam Optimizer (Kingma & Ba, 2014) over 70 epochs with an initial learning rate of 10 3 and a decay factor of 0.5 at the 50th and 60th epochs, with no early stopping. We train the other models using the Adam optimizer with an initial learning rate of 10 3 and train for 50 epochs with a learning rate schedule which decreases by a factor of 0.25 if the validation PSNR decreases from one epoch to the next. |