Normalized Validity Scores for DNNs in Regression based Eye Feature Extraction

TL;DR

This paper introduces a normalized validity score for deep neural networks in regression-based eye feature extraction, enhancing landmark detection accuracy by balancing inaccuracy measures and reducing gradient impact from minor errors.

Contribution

It proposes a novel normalization and margin approach to improve landmark validity loss in DNN-based shape detection tasks.

Findings

Improved accuracy in landmark detection tasks.

Enhanced robustness to minor errors near ground truth.

Better numerical stability in loss calculation.

Abstract

We propose an improvement to the landmark validity loss. Landmark detection is widely used in head pose estimation, eyelid shape extraction, as well as pupil and iris segmentation. There are numerous additional applications where landmark detection is used to estimate the shape of complex objects. One part of this process is the accurate and fine-grained detection of the shape. The other part is the validity or inaccuracy per landmark, which can be used to detect unreliable areas, where the shape possibly does not fit, and to improve the accuracy of the entire shape extraction by excluding inaccurate landmarks. We propose a normalization in the loss formulation, which improves the accuracy of the entire approach due to the numerical balance of the normalized inaccuracy. In addition, we propose a margin for the inaccuracy to reduce the impact of gradients, which are produced by negligible errors close to the ground truth.