Probabilistic Regression with Huber Distributions
This work addresses robust regression for computer vision tasks like pose estimation, offering an incremental improvement with specific gains in outlier robustness and invariance.
The paper tackles robust probabilistic regression for object position estimation by introducing a novel Huber-inspired distribution and a new parameterization for positive definite matrices, achieving performance on par or exceeding non-heatmap methods on body pose and facial landmark datasets.
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