When training an estimator such as a neural network for tasks like image denoising, it is often preferred to train one estimator and apply it to all noise levels. The de facto training protocol to achieve this goal is to train the estimator with noisy samples whose noise levels are uniformly distributed across the range of interest. However, why should we allocate the samples uniformly? Can we have more training samples that are less noisy, and fewer samples that are more noisy? What is the optimal distribution? How do we obtain such a distribution? The goal of this paper is to address this training sample distribution problem from a minimax risk optimization perspective. We derive a dual ascent algorithm to determine the optimal sampling distribution of which the convergence is guaranteed as long as the set of admissible estimators is closed and convex. For estimators with non-convex admissible sets such as deep neural networks, our dual formulation converges to a solution of the convex relaxation. We discuss how the algorithm can be implemented in practice. We evaluate the algorithm on linear estimators and deep networks.
We propose a new image denoising algorithm, dubbed as Fully Convolutional Adaptive Image DEnoiser (FC-AIDE), that can learn from an offline supervised training set with a fully convolutional neural network as well as adaptively fine-tune the supervised model for each given noisy image. We significantly extend the framework of the recently proposed Neural AIDE, which formulates the denoiser to be context-based pixelwise mappings and utilizes the unbiased estimator of MSE for such denoisers. The two main contributions we make are; 1) implementing a novel fully convolutional architecture that boo…
Ulsan National Institute of Science and Technology (UNIST)（蔚山科学技术院（UNIST））
Recently, Stein's unbiased risk estimator (SURE) has been applied to unsupervised training of deep neural network Gaussian denoisers that outperformed classical non-deep learning based denoisers and yielded comparable performance to those trained with ground truth. While SURE requires only one noise realization per image for training, it does not take advantage of having multiple noise realizations per image when they are available (e.g., two uncorrelated noise realizations per image for Noise2Noise). Here, we propose an extended SURE (eSURE) to train deep denoisers with correlated pairs of no…
We devise a novel neural network-based universal denoiser for the finite-input, general-output (FIGO) channel. Based on the assumption of known noisy channel densities, which is realistic in many practical scenarios, we train the network such that it can denoise as well as the best sliding window denoiser for any given underlying clean source data. Our algorithm, dubbed as Generalized CUDE (Gen-CUDE), enjoys several desirable properties; it can be trained in an unsupervised manner (solely based on the noisy observation data), has much smaller computational complexity compared to the previously…
Washington University in St. Louis（圣路易斯华盛顿大学）；University of Southern California（南加州大学）
We investigate unsupervised pre-training of deep architectures as feature generators for "shallow" classifiers. Stacked Denoising Autoencoders (SdA), when used as feature pre-processing tools for SVM classification, can lead to significant improvements in accuracy - however, at the price of a substantial increase in computational cost. In this paper we create a simple algorithm which mimics the layer by layer training of SdAs. However, in contrast to SdAs, our algorithm requires no training through gradient descent as the parameters can be computed in closed-form. It can be implemented in less…
A flexible discriminative image denoiser is introduced in which multi-task learning methods are applied to a densoising FCN based on U-Net. The activations of the U-Net model are modified by affine transforms that are a learned function of conditioning inputs. The learning procedure for multiple noise types and levels involves applying a distribution of noise parameters during training to the conditioning inputs, with the same noise parameters applied to a noise generating layer at the input (similar to the approach taken in a denoising autoencoder). It is shown that this flexible denoising mo…
Uniform Diffusion Models Revisited: Leave-One-Out Denoiser and Absorbing State Reformulation
CMAP, Ecole polytechnique（巴黎高等学院CMAP实验室）；Institute of Foundation Models（基础模型研究所）；Inria, PSL Research University（法国国家信息与自动化研究所）；MBZUAI（马尔科姆·布罗德本特大学人工智能研究所）；EPITA, LRE（EPITA实验室）
GDSD: Reinforcement Learning as Guided Denoiser Self-Distillation for Diffusion Language Models
UCL Dept. of Statistical Science（伦敦大学学院统计科学系）；UCL Centre for AI（伦敦大学学院人工智能中心）；Alibaba Group（阿里巴巴集团）；Dept. of EEE（电子工程系）；Imperial College London（伦敦帝国理工学院）；UNIST（全南大学）；University of Basel（巴塞尔大学）
Enabling Unsupervised Training of Deep EEG Denoisers With Intelligent Partitioning
Department of Electrical and Electronic Engineering, Imperial College London（帝国理工学院伦敦校区电子与电气工程系）；Dyson School of Design Engineering, Imperial College London（帝国理工学院伦敦校区戴森设计工程学院）
Deep neural network based methods are the state of the art in various image restoration problems. Standard supervised learning frameworks require a set of noisy measurement and clean image pairs for which a distance between the output of the restoration model and the ground truth, clean images is minimized. The ground truth images, however, are often unavailable or very expensive to acquire in real-world applications. We circumvent this problem by proposing a class of structured denoisers that can be decomposed as the sum of a nonlinear image-dependent mapping, a linear noise-dependent term an…
Self-supervised training of deep denoisers in multi-coil MRI considering noise correlations
Department of Electrical and Computer Engineering, Seoul National University（电气电子工程系，首尔国立大学）；INMC & IPAI, Seoul National University（INMC与IPAI，首尔国立大学）；Division of Computer Engineering, Hankuk University of Foreign Studies（计算机工程系，韩文大学）；Department of Radiology, Johns Hopkins University School of Medicine（放射科，约翰霍普金斯大学医学院）
Signal Analysis and Interpretation Laboratory (SAIL)（信号分析与解释实验室）；University of Southern California（南加州大学）
In this paper we investigate speech denoising as a defense against adversarial attacks on automatic speech recognition (ASR) systems. Adversarial attacks attempt to force misclassification by adding small perturbations to the original speech signal. We propose to counteract this by employing a neural-network based denoiser as a pre-processor in the ASR pipeline. The denoiser is independent of the downstream ASR model, and thus can be rapidly deployed in existing systems. We found that training the denoisier using a perceptually motivated loss function resulted in increased adversarial robustne…
Sungkyunkwan University（成均馆大学）；Yonsei University（延世大学）；Seoul National University（首尔国立大学）
We tackle a challenging blind image denoising problem, in which only single distinct noisy images are available for training a denoiser, and no information about noise is known, except for it being zero-mean, additive, and independent of the clean image. In such a setting, which often occurs in practice, it is not possible to train a denoiser with the standard discriminative training or with the recently developed Noise2Noise (N2N) training; the former requires the underlying clean image for the given noisy image, and the latter requires two independently realized noisy image pair for a clean …
The Plug-and-Play (PnP) framework makes it possible to integrate advanced image denoising priors into optimization algorithms, to efficiently solve a variety of image restoration tasks generally formulated as Maximum A Posteriori (MAP) estimation problems. The Plug-and-Play alternating direction method of multipliers (ADMM) and the Regularization by Denoising (RED) algorithms are two examples of such methods that made a breakthrough in image restoration. However, while the former method only applies to proximal algorithms, it has recently been shown that there exists no regularization that exp…
Certified defense using randomized smoothing is a popular technique to provide robustness guarantees for deep neural networks against l2 adversarial attacks. Existing works use this technique to provably secure a pretrained non-robust model by training a custom denoiser network on entire training data. However, access to the training set may be restricted to a handful of data samples due to constraints such as high transmission cost and the proprietary nature of the data. Thus, we formulate a novel problem of "how to certify the robustness of pretrained models using only a few training samples…
With recent deep learning based approaches showing promising results in removing noise from images, the best denoising performance has been reported in a supervised learning setup that requires a large set of paired noisy images and ground truth for training. The strong data requirement can be mitigated by unsupervised learning techniques, however, accurate modelling of images or noise variance is still crucial for high-quality solutions. The learning problem is ill-posed for unknown noise distributions. This paper investigates the tasks of image denoising and noise variance estimation in a si…
Beyond MMSE: Enhancing PnP Restoration with ProxiMAP
Univ. Grenoble Alpes（格勒诺布尔阿尔卑斯大学）；Inria（法国国家科学研究中心）；CNRS（法国国家科学研究中心）；Grenoble INP（格勒诺布尔理工大学）；LJK（实验室）；MaLGa Centre（MaLGa中心）；DIBRIS（DIBRIS研究所）；Università di Genova（热那亚大学）；MMS（MMS机构）；Italian Institute of Technology（意大利理工学院）
We propose a new grayscale image denoiser, dubbed as Neural Affine Image Denoiser (Neural AIDE), which utilizes neural network in a novel way. Unlike other neural network based image denoising methods, which typically apply simple supervised learning to learn a mapping from a noisy patch to a clean patch, we formulate to train a neural network to learn an \emph{affine} mapping that gets applied to a noisy pixel, based on its context. Our formulation enables both supervised training of the network from the labeled training dataset and adaptive fine-tuning of the network parameters using the giv…
This work systematically investigates the adversarial robustness of deep image denoisers (DIDs), i.e, how well DIDs can recover the ground truth from noisy observations degraded by adversarial perturbations. Firstly, to evaluate DIDs' robustness, we propose a novel adversarial attack, namely Observation-based Zero-mean Attack ({\sc ObsAtk}), to craft adversarial zero-mean perturbations on given noisy images. We find that existing DIDs are vulnerable to the adversarial noise generated by {\sc ObsAtk}. Secondly, to robustify DIDs, we propose an adversarial training strategy, hybrid adversarial t…
