paper-with-me

홈 › Papers

Self-supervised regression learning using domain knowledge: Applications to improving self-supervised denoising in imaging

2022-05-10 · Il Yong Chun, Dongwon Park, Xuehang Zheng, Se Young Chun, Yong Long

Regression that predicts continuous quantity is a central part of applications using computational imaging and computer vision technologies. Yet, studying and understanding self-supervised learning for regression tasks - except for a particular regression task, image denoising - have lagged behind. This paper proposes a general self-supervised regression learning (SSRL) framework that enables learning regression neural networks with only input data (but without ground-truth target data), by using a designable pseudo-predictor that encapsulates domain knowledge of a specific application. The paper underlines the importance of using domain knowledge by showing that under different settings, the better pseudo-predictor can lead properties of SSRL closer to those of ordinary supervised learning. Numerical experiments for low-dose computational tomography denoising and camera image denoising demonstrate that proposed SSRL significantly improves the denoising quality over several existing self-supervised denoising methods.

📄 PDF Abstract BibTeX arXiv:2205.04821

Code (0)

등록된 구현이 없습니다.

Tasks

DenoisingImage DenoisingregressionSelf-Supervised Learning

Similar Papers 제목 키워드 기반

Self-supervised regression learning using domain knowledge: Applications to improving self-supervised image denoising

2021-09-29 · Il Yong Chun, Dongwon Park, Xuehang Zheng, Se Young Chun 외

Regression that predicts continuous quantity is a central part of applications using computational imaging and computer vision technologies. Yet, studying and understanding self-supervised learning for regression tasks -…

DenoisingImage DenoisingregressionSelf-Supervised Learning

Robust Alzheimer's Progression Modeling using Cross-Domain Self-Supervised Deep Learning

2022-11-15 · Saba Dadsetan, Mohsen Hejrati, Shandong Wu, Somaye Hashemifar

Developing successful artificial intelligence systems in practice depends on both robust deep learning models and large, high-quality data. However, acquiring and labeling data can be prohibitively expensive and time-con…

regressionSelf-Supervised Learning

Weakly-Supervised Domain Adaptation of Deep Regression Trackers via Reinforced Knowledge Distillation

2021-03-26 · Matteo Dunnhofer, Niki Martinel, Christian Micheloni

Deep regression trackers are among the fastest tracking algorithms available, and therefore suitable for real-time robotic applications. However, their accuracy is inadequate in many domains due to distribution shift and…

Domain AdaptationKnowledge DistillationregressionVisual Object Tracking

S$^3$R: Self-supervised Spectral Regression for Hyperspectral Histopathology Image Classification

2022-09-19 · Xingran Xie, Yan Wang, Qingli Li

Benefited from the rich and detailed spectral information in hyperspectral images (HSI), HSI offers great potential for a wide variety of medical applications such as computational pathology. But, the lack of adequate an…

Contrastive Learningimage-classificationImage Classificationregression

Functional Knowledge Transfer with Self-supervised Representation Learning

2023-03-12 · Prakash Chandra Chhipa, Muskaan Chopra, Gopal Mengi, Varun Gupta 외

This work investigates the unexplored usability of self-supervised representation learning in the direction of functional knowledge transfer. In this work, functional knowledge transfer is achieved by joint optimization …

Representation LearningSelf-Supervised LearningTransfer Learning