paper-with-me

홈 › Papers

UNSURE: self-supervised learning with Unknown Noise level and Stein's Unbiased Risk Estimate

2024-09-03 · Julián Tachella, Mike Davies, Laurent Jacques

Recently, many self-supervised learning methods for image reconstruction have been proposed that can learn from noisy data alone, bypassing the need for ground-truth references. Most existing methods cluster around two classes: i) Stein's Unbiased Risk Estimate (SURE) and similar approaches that assume full knowledge of the noise distribution, and ii) Noise2Self and similar cross-validation methods that require very mild knowledge about the noise distribution. The first class of methods tends to be impractical, as the noise level is often unknown in real-world applications, and the second class is often suboptimal compared to supervised learning. In this paper, we provide a theoretical framework that characterizes this expressivity-robustness trade-off and propose a new approach based on SURE, but unlike the standard SURE, does not require knowledge about the noise level. Throughout a series of experiments, we show that the proposed estimator outperforms other existing self-supervised methods on various imaging inverse problems.

📄 PDF Abstract BibTeX arXiv:2409.01985

Code (1)

tachella/unsure 공식 구현 pytorch

Tasks

Image ReconstructionSelf-Supervised Learning

Similar Papers 제목 키워드 기반

AP-BSN: Self-Supervised Denoising for Real-World Images via Asymmetric PD and Blind-Spot Network

2022-03-22 · CVPR 2022 1 · Wooseok Lee, Sanghyun Son, Kyoung Mu Lee

Blind-spot network (BSN) and its variants have made significant advances in self-supervised denoising. Nevertheless, they are still bound to synthetic noisy inputs due to less practical assumptions like pixel-wise indepe…

Denoising

Crowdsourcing with Unsure Option

2016-09-01 · Yao-Xiang Ding, Zhi-Hua Zhou

One of the fundamental problems in crowdsourcing is the trade-off between the number of the workers needed for high-accuracy aggregation and the budget to pay. For saving budget, it is important to ensure high quality of…

LLM Abstention Can Be a Prompt Artifact, in Addition to Genuine Uncertainty

2025-07-22 · Zipeng Ling, Shuliang Liu, Yuehao Tang, Junqi Yang 외 arxiv

Large Language Models (LLMs) are increasingly trained to abstain from answering questions they are unsure about. However, this ability is often misused: in real-world applications, input prompts sometimes contain uncerta…

Patch-Craft Self-Supervised Training for Correlated Image Denoising

2022-11-17 · CVPR 2023 1 · Gregory Vaksman, Michael Elad

Supervised neural networks are known to achieve excellent results in various image restoration tasks. However, such training requires datasets composed of pairs of corrupted images and their corresponding ground truth ta…

DenoisingImage DenoisingImage RestorationPatch Matching

Self-Supervised Image Denoising for Real-World Images with Context-aware Transformer

2023-04-04 · Dan Zhang, Fangfang Zhou

In recent years, the development of deep learning has been pushing image denoising to a new level. Among them, self-supervised denoising is increasingly popular because it does not require any prior knowledge. Most of th…

DenoisingImage DenoisingSSIM