Adaptive Denoising via GainTuning

• URL: http://arxiv.org/abs/2107.12815v1
• Date: Tue, 27 Jul 2021 13:35:48 GMT
• Title: Adaptive Denoising via GainTuning
• Authors: Sreyas Mohan, Joshua L. Vincent, Ramon Manzorro, Peter A. Crozier, Eero P. Simoncelli, Carlos Fernandez-Granda
• Abstract summary: Deep convolutional neural networks (CNNs) for image denoising are usually trained on large datasets. We propose "GainTuning", in which CNN models pre-trained on large datasets are adaptively and selectively adjusted for individual test images. We show that GainTuning improves state-of-the-art CNNs on standard image-denoising benchmarks, boosting their denoising performance on nearly every image in a held-out test set.
• Score: 17.72738152112575
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep convolutional neural networks (CNNs) for image denoising are usually trained on large datasets. These models achieve the current state of the art, but they have difficulties generalizing when applied to data that deviate from the training distribution. Recent work has shown that it is possible to train denoisers on a single noisy image. These models adapt to the features of the test image, but their performance is limited by the small amount of information used to train them. Here we propose "GainTuning", in which CNN models pre-trained on large datasets are adaptively and selectively adjusted for individual test images. To avoid overfitting, GainTuning optimizes a single multiplicative scaling parameter (the "Gain") of each channel in the convolutional layers of the CNN. We show that GainTuning improves state-of-the-art CNNs on standard image-denoising benchmarks, boosting their denoising performance on nearly every image in a held-out test set. These adaptive improvements are even more substantial for test images differing systematically from the training data, either in noise level or image type. We illustrate the potential of adaptive denoising in a scientific application, in which a CNN is trained on synthetic data, and tested on real transmission-electron-microscope images. In contrast to the existing methodology, GainTuning is able to faithfully reconstruct the structure of catalytic nanoparticles from these data at extremely low signal-to-noise ratios.

Related papers

• Learning with Noisy Foundation Models [95.50968225050012]
  This paper is the first work to comprehensively understand and analyze the nature of noise in pre-training datasets. We propose a tuning method (NMTune) to affine the feature space to mitigate the malignant effect of noise and improve generalization.
  arXiv  Detail & Related papers  (2024-03-11T16:22:41Z)
• Decoupled Mixup for Generalized Visual Recognition [71.13734761715472]
  We propose a novel "Decoupled-Mixup" method to train CNN models for visual recognition. Our method decouples each image into discriminative and noise-prone regions, and then heterogeneously combines these regions to train CNN models. Experiment results show the high generalization performance of our method on testing data that are composed of unseen contexts.
  arXiv  Detail & Related papers  (2022-10-26T15:21:39Z)
• Enhancing convolutional neural network generalizability via low-rank weight approximation [6.763245393373041]
  Sufficient denoising is often an important first step for image processing. Deep neural networks (DNNs) have been widely used for image denoising. We introduce a new self-supervised framework for image denoising based on the Tucker low-rank tensor approximation.
  arXiv  Detail & Related papers  (2022-09-26T14:11:05Z)
• Multi-stage image denoising with the wavelet transform [125.2251438120701]
  Deep convolutional neural networks (CNNs) are used for image denoising via automatically mining accurate structure information. We propose a multi-stage image denoising CNN with the wavelet transform (MWDCNN) via three stages, i.e., a dynamic convolutional block (DCB), two cascaded wavelet transform and enhancement blocks (WEBs) and residual block (RB)
  arXiv  Detail & Related papers  (2022-09-26T03:28:23Z)
• Robust Deep Ensemble Method for Real-world Image Denoising [62.099271330458066]
  We propose a simple yet effective Bayesian deep ensemble (BDE) method for real-world image denoising. Our BDE achieves +0.28dB PSNR gain over the state-of-the-art denoising method. Our BDE can be extended to other image restoration tasks, and achieves +0.30dB, +0.18dB and +0.12dB PSNR gains on benchmark datasets.
  arXiv  Detail & Related papers  (2022-06-08T06:19:30Z)
• Image Denoising using Attention-Residual Convolutional Neural Networks [0.0]
  We propose a new learning-based non-blind denoising technique named Attention Residual Convolutional Neural Network (ARCNN) and its extension to blind denoising named Flexible Attention Residual Convolutional Neural Network (FARCNN) ARCNN achieved an overall average PSNR results of around 0.44dB and 0.96dB for Gaussian and Poisson denoising, respectively FARCNN presented very consistent results, even with slightly worsen performance compared to ARCNN.
  arXiv  Detail & Related papers  (2021-01-19T16:37:57Z)
• Unrolling of Deep Graph Total Variation for Image Denoising [106.93258903150702]
  In this paper, we combine classical graph signal filtering with deep feature learning into a competitive hybrid design. We employ interpretable analytical low-pass graph filters and employ 80% fewer network parameters than state-of-the-art DL denoising scheme DnCNN.
  arXiv  Detail & Related papers  (2020-10-21T20:04:22Z)
• Enhancement of a CNN-Based Denoiser Based on Spatial and Spectral Analysis [23.11994688706024]
  We propose a discrete wavelet denoising CNN (WDnCNN) which restores images corrupted by various noise with a single model. To address this issue, we present a band normalization module (BNM) to normalize the coefficients from different parts of the frequency spectrum. We evaluate the proposed WDnCNN, and compare it with other state-of-the-art denoisers.
  arXiv  Detail & Related papers  (2020-06-28T05:25:50Z)
• CycleISP: Real Image Restoration via Improved Data Synthesis [166.17296369600774]
  We present a framework that models camera imaging pipeline in forward and reverse directions. By training a new image denoising network on realistic synthetic data, we achieve the state-of-the-art performance on real camera benchmark datasets.
  arXiv  Detail & Related papers  (2020-03-17T15:20:25Z)
• Noise2Inverse: Self-supervised deep convolutional denoising for tomography [0.0]
  Noise2Inverse is a deep CNN-based denoising method for linear image reconstruction algorithms. We develop a theoretical framework which shows that such training indeed obtains a denoising CNN. On simulated CT datasets, Noise2Inverse demonstrates an improvement in peak signal-to-noise ratio and structural similarity index.
  arXiv  Detail & Related papers  (2020-01-31T12:50:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.