• Home
  • Search
  • ACR Loss: Adaptive Coordinate-based Regression Loss for Face Alignment
  • Open Access IconOpen Access
  • Cite Icon11
  • https://doi.org/10.1109/icpr56361.2022.9956683Copy DOI Icon

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

  • Aug 21, 2022
  • Ali Pourramezan Fard +1 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Although deep neural networks have achieved reasonable accuracy in solving face alignment, it is still a challenging task, specifically when dealing 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 fewer 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 more 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.

Similar Papers
  • Conference Article

Face Joint Alignment Using Local Method

  • Jan 01, 2016
  • Gang Zhang +2
  • Conference Article
  • Citations36

ASMNet: a Lightweight Deep Neural Network for Face Alignment and Pose Estimation

  • Jun 01, 2021
  • Ali Pourramezan Fard +2
  • Research Article
  • Citations25

Facial landmark points detection using knowledge distillation-based neural networks

  • Nov 26, 2021
  • Computer Vision and Image Understanding
  • Ali Pourramezan Fard +1
  • Research Article
  • Citations24

Landmark perturbation-based data augmentation for unconstrained face recognition

  • Apr 01, 2016
  • Signal Processing: Image Communication
  • Jiang-Jing Lv +4
  • Conference Article
  • Citations2

Face Alignment Refinement

  • Jan 01, 2015
  • Andy Zeng +3
  • Book Chapter
  • Citations4

Advances and Trends in Video Face Alignment

  • Dec 15, 2018
  • Gang Zhang +3
  • PDF
  • Research Article
  • Citations6

Multi-feature shape regression for face alignment

  • Aug 02, 2018
  • EURASIP Journal on Advances in Signal Processing
  • Wei-Jong Yang +3
  • Research Article
  • Citations14

3D face reconstruction and dense alignment with a new generated dataset

  • Oct 23, 2021
  • Displays
  • Mingcheng Cai +3
  • Dissertation

Designing Customized Loss Functions for Training Deep Neural Networks

  • Nov 22, 2024
  • Ali Pourramezan Fard
  • Research Article
  • Citations12

Recognizing gender from human facial regions using genetic algorithm

  • Aug 09, 2018
  • Soft Computing
  • Avirup Bhattacharyya +4
  • Research Article
  • Citations3

Comparison of the registration methods for the three-dimensional facial scans applied to the design of full-arch implant supported restoration

  • Dec 24, 2020
  • Beijing da xue xue bao. Yi xue ban = Journal of Peking University. Health sciences
  • Dewen Guo +5
  • Conference Article
  • Citations5

Face decorating system based on improved active shape models

  • Jun 14, 2006
  • Shuchang Wang +2
  • Research Article
  • Citations25

ACN: Occlusion-tolerant face alignment by attentional combination of heterogeneous regression networks

  • Dec 02, 2020
  • Pattern Recognition
  • Hyunsung Park +1
  • Research Article
  • Citations5

A complementary regression network for accurate face alignment

  • Jan 22, 2020
  • Image and Vision Computing
  • Hyunsung Park +1
  • Research Article
  • Citations50

Learning Deep Sharable and Structural Detectors for Face Alignment.

  • Jan 23, 2017
  • IEEE Transactions on Image Processing
  • Hao Liu +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.