2010
NIPS
NeurIPS 2010
Regularized estimation of image statistics by Score Matching
Abstract
Score Matching is a recently-proposed criterion for training high-dimensional density models for which maximum likelihood training is intractable. It has been applied to learning natural image statistics but has so-far been limited to simple models due to the difficulty of differentiating the loss with respect to the model parameters. We show how this differentiation can be automated with an extended version of the double-backpropagation algorithm. In addition, we introduce a regularization term for the Score Matching loss that enables its use for a broader range of problem by suppressing instabilities that occur with finite training sample sizes and quantized input values. Results are reported for image denoising and super-resolution.
🌉
Interdisciplinary Bridge
— Computer Vision and Deep Learning and Machine Learning
📈
Trend Setter
— Loss Functions
🧭
Keyword Pioneer
— density models
🐝
Cross-Pollinator
— Artificial Intelligence, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning
🌱
Topic Pioneer
— Diffusion Models
🐣
Hot Topic Early Bird
— density estimation
Authors
Topics
Machine Learning > Optimization & Theory > Loss Functions
Machine Learning > Optimization & Theory > Statistical Learning
Deep Learning > Models > Diffusion Models
Deep Learning > Models > Generative Models
Computer Vision > Processing > Image Restoration
Computer Vision > Processing > Image Processing