paper-with-me

Papers

Denoising and Regularization via Exploiting the Structural Bias of Convolutional Generators

2019-10-31 · ICLR 2020 1 · Reinhard Heckel, Mahdi Soltanolkotabi

Convolutional Neural Networks (CNNs) have emerged as highly successful tools for image generation, recovery, and restoration. A major contributing factor to this success is that convolutional networks impose strong prior assumptions about natural images. A surprising experiment that highlights this architectural bias towards natural images is that one can remove noise and corruptions from a natural image without using any training data, by simply fitting (via gradient descent) a randomly initialized, over-parameterized convolutional generator to the corrupted image. While this over-parameterized network can fit the corrupted image perfectly, surprisingly after a few iterations of gradient descent it generates an almost uncorrupted image. This intriguing phenomenon enables state-of-the-art CNN-based denoising and regularization of other inverse problems. In this paper, we attribute this effect to a particular architectural choice of convolutional networks, namely convolutions with fixed interpolating filters. We then formally characterize the dynamics of fitting a two-layer convolutional generator to a noisy signal and prove that early-stopped gradient descent denoises/regularizes. Our proof relies on showing that convolutional generators fit the structured part of an image significantly faster than the corrupted portion.

📄 PDF Abstract BibTeX arXiv:1910.14634

Code (1)

MLI-lab/overparameterized_convolutional_generators 공식 구현 pytorch

Tasks

AttributeDenoisingImage Generation

Similar Papers 제목 키워드 기반

A Fully Convolutional Approach to Denoising Structural Dynamics Data from X-Ray Photon Correlation Spectroscopy

2026-05-28 · Nisar Nellikunnummel, Andi Barbour, Lutz Wiegart, Tatiana Konstantinova 외 arxiv

We present a fully convolutional denoising autoencoder (FC-DAE) for denoising two-time intensity-intensity correlation functions ($C_2$) in X-ray photon correlation spectroscopy (XPCS). Unlike conventional denoising auto…

Computational EfficiencyData Augmentation

Absum: Simple Regularization Method for Reducing Structural Sensitivity of Convolutional Neural Networks

2019-09-19 · Sekitoshi Kanai, Yasutoshi Ida, Yasuhiro Fujiwara, Masanori Yamada 외

We propose Absum, which is a regularization method for improving adversarial robustness of convolutional neural networks (CNNs). Although CNNs can accurately recognize images, recent studies have shown that the convoluti…

Adversarial AttackAdversarial RobustnessSensitivity

RELD: Regularization by Latent Diffusion Models for Image Restoration

2025-03-28 · Pasquale Cascarano, Lorenzo Stacchio, Andrea Sebastiani, Alessandro Benfenati 외

In recent years, Diffusion Models have become the new state-of-the-art in deep generative modeling, ending the long-time dominance of Generative Adversarial Networks. Inspired by the Regularization by Denoising principle…

DeblurringDenoisingImage DenoisingImage Restoration+1

Mixing-Denoising Generalizable Occupancy Networks

2023-11-20 · Amine Ouasfi, Adnane Boukhayma

While current state-of-the-art generalizable implicit neural shape models rely on the inductive bias of convolutions, it is still not entirely clear how properties emerging from such biases are compatible with the task o…

3D ReconstructionDecoderDenoisingInductive Bias

Noise2Inverse: Self-supervised deep convolutional denoising for tomography

2020-01-31 · Allard A. Hendriksen, Daniel M. Pelt, K. Joost Batenburg

Recovering a high-quality image from noisy indirect measurements is an important problem with many applications. For such inverse problems, supervised deep convolutional neural network (CNN)-based denoising methods have …

DenoisingImage DenoisingImage Reconstruction