On normalization-equivariance properties of supervised and unsupervised denoising methods: a survey

• URL: http://arxiv.org/abs/2402.15352v1
• Date: Fri, 23 Feb 2024 14:39:12 GMT
• Title: On normalization-equivariance properties of supervised and unsupervised denoising methods: a survey
• Authors: S\'ebastien Herbreteau and Charles Kervrann
• Abstract summary: We propose a survey of guided tour of supervised and unsupervised learning methods for image denoising. We give insights on the rationales and limitations of the most performant methods in the literature. It is of paramount importance that intensity shifting or scaling applied to the input image results in a corresponding change in the denoiser output.
• Score: 4.24243593213882
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Image denoising is probably the oldest and still one of the most active research topic in image processing. Many methodological concepts have been introduced in the past decades and have improved performances significantly in recent years, especially with the emergence of convolutional neural networks and supervised deep learning. In this paper, we propose a survey of guided tour of supervised and unsupervised learning methods for image denoising, classifying the main principles elaborated during this evolution, with a particular concern given to recent developments in supervised learning. It is conceived as a tutorial organizing in a comprehensive framework current approaches. We give insights on the rationales and limitations of the most performant methods in the literature, and we highlight the common features between many of them. Finally, we focus on on the normalization equivariance properties that is surprisingly not guaranteed with most of supervised methods. It is of paramount importance that intensity shifting or scaling applied to the input image results in a corresponding change in the denoiser output.

Related papers

• Deep Learning for Video Anomaly Detection: A Review [52.74513211976795]
  Video anomaly detection (VAD) aims to discover behaviors or events deviating from the normality in videos. In the era of deep learning, a great variety of deep learning based methods are constantly emerging for the VAD task. This review covers the spectrum of five different categories, namely, semi-supervised, weakly supervised, fully supervised, unsupervised and open-set supervised VAD.
  arXiv  Detail & Related papers  (2024-09-09T07:31:16Z)
• Denoising: from classical methods to deep CNNs [0.0]
  We briefly review classical methods such as Fourier analysis and wavelet bases, highlighting the challenges they faced until the emergence of neural networks. We discuss the prerequisites for genuine learning of probability densities, offering insights that extend from mathematical research to the implications of universal structures.
  arXiv  Detail & Related papers  (2024-04-25T13:56:54Z)
• Low-Trace Adaptation of Zero-shot Self-supervised Blind Image Denoising [23.758547513866766]
  We propose a trace-constraint loss function and low-trace adaptation Noise2Noise (LoTA-N2N) model to bridge the gap between self-supervised and supervised learning. Our method achieves state-of-the-art performance within the realm of zero-shot self-supervised image denoising approaches.
  arXiv  Detail & Related papers  (2024-03-19T02:47:33Z)
• Unsupervised approaches based on optimal transport and convex analysis for inverse problems in imaging [6.202226277935329]
  We review theoretically principled unsupervised learning schemes for solving imaging inverse problems. We focus on methods rooted in optimal transport and convex analysis. We give an overview of a recent line of works on provably convergent learned optimization algorithms.
  arXiv  Detail & Related papers  (2023-11-15T14:04:37Z)
• Unleashing the Power of Self-Supervised Image Denoising: A Comprehensive Review [7.387921606240273]
  The advent of deep learning has brought a revolutionary transformation to image denoising techniques. The persistent challenge of acquiring noise-clean pairs for supervised methods in real-world scenarios remains formidable. This paper focuses on self-supervised image denoising methods that offer effective solutions.
  arXiv  Detail & Related papers  (2023-08-01T03:00:36Z)
• Two Approaches to Supervised Image Segmentation [55.616364225463066]
  The present work develops comparison experiments between deep learning and multiset neurons approaches. The deep learning approach confirmed its potential for performing image segmentation. The alternative multiset methodology allowed for enhanced accuracy while requiring little computational resources.
  arXiv  Detail & Related papers  (2023-07-19T16:42:52Z)
• Masked Image Training for Generalizable Deep Image Denoising [53.03126421917465]
  We present a novel approach to enhance the generalization performance of denoising networks. Our method involves masking random pixels of the input image and reconstructing the missing information during training. Our approach exhibits better generalization ability than other deep learning models and is directly applicable to real-world scenarios.
  arXiv  Detail & Related papers  (2023-03-23T09:33:44Z)
• Single-Layer Vision Transformers for More Accurate Early Exits with Less Overhead [88.17413955380262]
  We introduce a novel architecture for early exiting based on the vision transformer architecture. We show that our method works for both classification and regression problems. We also introduce a novel method for integrating audio and visual modalities within early exits in audiovisual data analysis.
  arXiv  Detail & Related papers  (2021-05-19T13:30:34Z)
• A Survey on Deep Semi-supervised Learning [51.26862262550445]
  We first present a taxonomy for deep semi-supervised learning that categorizes existing methods. We then offer a detailed comparison of these methods in terms of the type of losses, contributions, and architecture differences.
  arXiv  Detail & Related papers  (2021-02-28T16:22:58Z)
• Can Semantic Labels Assist Self-Supervised Visual Representation Learning? [194.1681088693248]
  We present a new algorithm named Supervised Contrastive Adjustment in Neighborhood (SCAN) In a series of downstream tasks, SCAN achieves superior performance compared to previous fully-supervised and self-supervised methods. Our study reveals that semantic labels are useful in assisting self-supervised methods, opening a new direction for the community.
  arXiv  Detail & Related papers  (2020-11-17T13:25:00Z)
• Supervised Learning of Sparsity-Promoting Regularizers for Denoising [13.203765985718205]
  We present a method for supervised learning of sparsity-promoting regularizers for image denoising. Our experiments show that the proposed method can learn an operator that outperforms well-known regularizers.
  arXiv  Detail & Related papers  (2020-06-09T21:38:05Z)

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.