Trained Model in Supervised Deep Learning is a Conditional Risk Minimizer

02/08/2022
by   Yutong Xie, et al.
13

We proved that a trained model in supervised deep learning minimizes the conditional risk for each input (Theorem 2.1). This property provided insights into the behavior of trained models and established a connection between supervised and unsupervised learning in some cases. In addition, when the labels are intractable but can be written as a conditional risk minimizer, we proved an equivalent form of the original supervised learning problem with accessible labels (Theorem 2.2). We demonstrated that many existing works, such as Noise2Score, Noise2Noise and score function estimation can be explained by our theorem. Moreover, we derived a property of classification problem with noisy labels using Theorem 2.1 and validated it using MNIST dataset. Furthermore, We proposed a method to estimate uncertainty in image super-resolution based on Theorem 2.2 and validated it using ImageNet dataset. Our code is available on github.

READ FULL TEXT

page 11

page 22

page 23

page 24

research
10/07/2019

Unsupervised Image Super-Resolution with an Indirect Supervised Path

The task of single image super-resolution (SISR) aims at reconstructing ...
research
06/02/2020

SRZoo: An integrated repository for super-resolution using deep learning

Deep learning-based image processing algorithms, including image super-r...
research
11/27/1999

Cox's Theorem Revisited

The assumptions needed to prove Cox's Theorem are discussed and examined...
research
04/23/2020

SimUSR: A Simple but Strong Baseline for Unsupervised Image Super-resolution

In this paper, we tackle a fully unsupervised super-resolution problem, ...
research
08/05/2022

Perception-Distortion Balanced ADMM Optimization for Single-Image Super-Resolution

In image super-resolution, both pixel-wise accuracy and perceptual fidel...
research
02/08/2019

Addressing Overfitting on Pointcloud Classification using Atrous XCRF

Advances in techniques for automated classification of pointcloud data i...

Please sign up or login with your details

Forgot password? Click here to reset