Probabilistic Regression with Huber Distributions

11/19/2021
by   David Mohlin, et al.
93

In this paper we describe a probabilistic method for estimating the position of an object along with its covariance matrix using neural networks. Our method is designed to be robust to outliers, have bounded gradients with respect to the network outputs, among other desirable properties. To achieve this we introduce a novel probability distribution inspired by the Huber loss. We also introduce a new way to parameterize positive definite matrices to ensure invariance to the choice of orientation for the coordinate system we regress over. We evaluate our method on popular body pose and facial landmark datasets and get performance on par or exceeding the performance of non-heatmap methods. Our code is available at github.com/Davmo049/Public_prob_regression_with_huber_distributions

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 3

page 10

page 30

06/17/2020

Probabilistic orientation estimation with matrix Fisher distributions

This paper focuses on estimating probability distributions over the set ...
10/03/2021

Hierarchical Kinematic Probability Distributions for 3D Human Shape and Pose Estimation from Images in the Wild

This paper addresses the problem of 3D human body shape and pose estimat...
04/15/2016

Positive Definite Estimation of Large Covariance Matrix Using Generalized Nonconvex Penalties

This work addresses the issue of large covariance matrix estimation in h...
12/02/2020

Neural Teleportation

In this paper, we explore a process called neural teleportation, a mathe...
09/01/2020

Heatmap Regression via Randomized Rounding

Heatmap regression has become the mainstream methodology for deep learni...
04/27/2013

Bingham Procrustean Alignment for Object Detection in Clutter

A new system for object detection in cluttered RGB-D images is presented...
10/03/2020

Gaussian Vector: An Efficient Solution for Facial Landmark Detection

Significant progress has been made in facial landmark detection with the...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.