DeepGUM: Learning Deep Robust Regression with a Gaussian-Uniform Mixture Model

08/28/2018
by   Stéphane Lathuilière, et al.
0

In this paper, we address the problem of how to robustly train a ConvNet for regression, or deep robust regression. Traditionally, deep regression employs the L2 loss function, known to be sensitive to outliers, i.e. samples that either lie at an abnormal distance away from the majority of the training samples, or that correspond to wrongly annotated targets. This means that, during back-propagation, outliers may bias the training process due to the high magnitude of their gradient. In this paper, we propose DeepGUM: a deep regression model that is robust to outliers thanks to the use of a Gaussian-uniform mixture model. We derive an optimization algorithm that alternates between the unsupervised detection of outliers using expectation-maximization, and the supervised training with cleaned samples using stochastic gradient descent. DeepGUM is able to adapt to a continuously evolving outlier distribution, avoiding to manually impose any threshold on the proportion of outliers in the training set. Extensive experimental evaluations on four different tasks (facial and fashion landmark detection, age and head pose estimation) lead us to conclude that our novel robust technique provides reliability in the presence of various types of noise and protection against a high percentage of outliers.

READ FULL TEXT

page 18

page 19

page 20

page 23

page 24

page 25

page 27

page 30

research
12/15/2020

Robust Factorization Methods Using a Gaussian/Uniform Mixture Model

In this paper we address the problem of building a class of robust facto...
research
07/02/2019

Using Subset Log-Likelihoods to Trim Outliers in Gaussian Mixture Models

Mixtures of Gaussian distributions are a popular choice in model-based c...
research
05/23/2019

Robust Point Cloud Based Reconstruction of Large-Scale Outdoor Scenes

Outlier feature matches and loop-closures that survived front-end data a...
research
09/17/2019

Efficient and Robust Estimation of Linear Regression with Normal Errors

Linear regression with normally distributed errors - including particula...
research
12/12/2017

Practical Bayesian optimization in the presence of outliers

Inference in the presence of outliers is an important field of research ...
research
06/14/2021

Outlier detection in multivariate functional data through a contaminated mixture model

This work is motivated by an application in an industrial context, where...

Please sign up or login with your details

Forgot password? Click here to reset