ACR Loss: Adaptive Coordinate-based Regression Loss for Face Alignment

TL;DR

This paper introduces an Adaptive Coordinate-based Regression (ACR) loss that enhances face alignment accuracy by adaptively focusing on challenging landmarks, outperforming traditional methods especially under occlusion and extreme poses.

Contribution

The paper proposes a novel ACR Loss inspired by ASM that adaptively adjusts its influence based on landmark difficulty, improving coordinate-based regression for face alignment.

Findings

ACR Loss improves landmark prediction accuracy.

The method performs well under occlusion and extreme poses.

It outperforms traditional CBR and HBR methods.

Abstract

Although deep neural networks have achieved reasonable accuracy in solving face alignment, it is still a challenging task, specifically when we deal with facial images, under occlusion, or extreme head poses. Heatmap-based Regression (HBR) and Coordinate-based Regression (CBR) are among the two mainly used methods for face alignment. CBR methods require less computer memory, though their performance is less than HBR methods. In this paper, we propose an Adaptive Coordinate-based Regression (ACR) loss to improve the accuracy of CBR for face alignment. Inspired by the Active Shape Model (ASM), we generate Smooth-Face objects, a set of facial landmark points with less variations compared to the ground truth landmark points. We then introduce a method to estimate the level of difficulty in predicting each landmark point for the network by comparing the distribution of the ground truth landmark points and the corresponding Smooth-Face objects. Our proposed ACR Loss can adaptively modify its curvature and the influence of the loss based on the difficulty level of predicting each landmark point in a face. Accordingly, the ACR Loss guides the network toward challenging points than easier points, which improves the accuracy of the face alignment task. Our extensive evaluation shows the capabilities of the proposed ACR Loss in predicting facial landmark points in various facial images.