Towards Robust Object Detection: Bayesian RetinaNet for Homoscedastic Aleatoric Uncertainty Modeling

TL;DR

This paper introduces a Bayesian approach to object detection that models label noise using homoscedastic aleatoric uncertainty, enhancing interpretability and performance of RetinaNet on noisy datasets like COCO.

Contribution

It proposes novel loss functions based on Bayesian inference for homoscedastic aleatoric uncertainty modeling integrated into RetinaNet for robust object detection.

Findings

Improved detection accuracy on COCO dataset.

Enhanced model interpretability through uncertainty estimation.

Effective handling of label noise in large-scale datasets.

Abstract

According to recent studies, commonly used computer vision datasets contain about 4% of label errors. For example, the COCO dataset is known for its high level of noise in data labels, which limits its use for training robust neural deep architectures in a real-world scenario. To model such a noise, in this paper we have proposed the homoscedastic aleatoric uncertainty estimation, and present a series of novel loss functions to address the problem of image object detection at scale. Specifically, the proposed functions are based on Bayesian inference and we have incorporated them into the common community-adopted object detection deep learning architecture RetinaNet. We have also shown that modeling of homoscedastic aleatoric uncertainty using our novel functions allows to increase the model interpretability and to improve the object detection performance being evaluated on the COCO dataset.