Robust and Precise Facial Landmark Detection by Self-Calibrated Pose
Attention Network
- URL: http://arxiv.org/abs/2112.12328v1
- Date: Thu, 23 Dec 2021 02:51:08 GMT
- Title: Robust and Precise Facial Landmark Detection by Self-Calibrated Pose
Attention Network
- Authors: Jun Wan, Hui Xi, Jie Zhou, Zhihui Lai, Witold Pedrycz, Xu Wang and
Hang Sun
- Abstract summary: We propose a semi-supervised framework to achieve more robust and precise facial landmark detection.
A Boundary-Aware Landmark Intensity (BALI) field is proposed to model more effective facial shape constraints.
A Self-Calibrated Pose Attention (SCPA) model is designed to provide a self-learned objective function that enforces intermediate supervision.
- Score: 73.56802915291917
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Current fully-supervised facial landmark detection methods have progressed
rapidly and achieved remarkable performance. However, they still suffer when
coping with faces under large poses and heavy occlusions for inaccurate facial
shape constraints and insufficient labeled training samples. In this paper, we
propose a semi-supervised framework, i.e., a Self-Calibrated Pose Attention
Network (SCPAN) to achieve more robust and precise facial landmark detection in
challenging scenarios. To be specific, a Boundary-Aware Landmark Intensity
(BALI) field is proposed to model more effective facial shape constraints by
fusing boundary and landmark intensity field information. Moreover, a
Self-Calibrated Pose Attention (SCPA) model is designed to provide a
self-learned objective function that enforces intermediate supervision without
label information by introducing a self-calibrated mechanism and a pose
attention mask. We show that by integrating the BALI fields and SCPA model into
a novel self-calibrated pose attention network, more facial prior knowledge can
be learned and the detection accuracy and robustness of our method for faces
with large poses and heavy occlusions have been improved. The experimental
results obtained for challenging benchmark datasets demonstrate that our
approach outperforms state-of-the-art methods in the literature.
Related papers
- Toward Motion Robustness: A masked attention regularization framework in remote photoplethysmography [5.743550396843244]
MAR-r is a framework that integrates the impact of ROI localization and complex motion artifacts.
MAR-r employs a masked attention regularization mechanism into the r field to capture semantic consistency of facial clips.
It also employs a masking technique to prevent the model from overfitting on inaccurate ROIs and subsequently degrading its performance.
arXiv Detail & Related papers (2024-07-09T08:25:30Z) - Improving Facial Landmark Detection Accuracy and Efficiency with Knowledge Distillation [4.779050216649159]
This paper introduces a novel approach to address these challenges through the development of a knowledge distillation method.
Our goal is to design models capable of accurately locating facial landmarks under varying conditions.
This method was successfully implemented and achieved a top 6th place finish out of 165 participants in the IEEE ICME 2024 PAIR competition.
arXiv Detail & Related papers (2024-04-09T05:30:58Z) - Extreme Miscalibration and the Illusion of Adversarial Robustness [66.29268991629085]
Adversarial Training is often used to increase model robustness.
We show that this observed gain in robustness is an illusion of robustness (IOR)
We urge the NLP community to incorporate test-time temperature scaling into their robustness evaluations.
arXiv Detail & Related papers (2024-02-27T13:49:12Z) - RARE: Robust Masked Graph Autoencoder [45.485891794905946]
Masked graph autoencoder (MGAE) has emerged as a promising self-supervised graph pre-training (SGP) paradigm.
We propose a novel SGP method termed Robust mAsked gRaph autoEncoder (RARE) to improve the certainty in inferring masked data.
arXiv Detail & Related papers (2023-04-04T03:35:29Z) - Attribute-preserving Face Dataset Anonymization via Latent Code
Optimization [64.4569739006591]
We present a task-agnostic anonymization procedure that directly optimize the images' latent representation in the latent space of a pre-trained GAN.
We demonstrate through a series of experiments that our method is capable of anonymizing the identity of the images whilst -- crucially -- better-preserving the facial attributes.
arXiv Detail & Related papers (2023-03-20T17:34:05Z) - Certified Interpretability Robustness for Class Activation Mapping [77.58769591550225]
We present CORGI, short for Certifiably prOvable Robustness Guarantees for Interpretability mapping.
CORGI is an algorithm that takes in an input image and gives a certifiable lower bound for the robustness of its CAM interpretability map.
We show the effectiveness of CORGI via a case study on traffic sign data, certifying lower bounds on the minimum adversarial perturbation.
arXiv Detail & Related papers (2023-01-26T18:58:11Z) - Occlusion-Robust FAU Recognition by Mining Latent Space of Masked
Autoencoders [23.39566752915331]
Facial action units (FAUs) are critical for fine-grained facial expression analysis.
New approach takes advantage of rich information from the latent space of masked autoencoder (MAE) and transforms it into FAU features.
FAUs can achieve comparable performance as state-of-the-art methods under normal conditions.
arXiv Detail & Related papers (2022-12-08T01:57:48Z) - Adversarially-Aware Robust Object Detector [85.10894272034135]
We propose a Robust Detector (RobustDet) based on adversarially-aware convolution to disentangle gradients for model learning on clean and adversarial images.
Our model effectively disentangles gradients and significantly enhances the detection robustness with maintaining the detection ability on clean images.
arXiv Detail & Related papers (2022-07-13T13:59:59Z) - Suppressing Uncertainties for Large-Scale Facial Expression Recognition [81.51495681011404]
This paper proposes a simple yet efficient Self-Cure Network (SCN) which suppresses the uncertainties efficiently and prevents deep networks from over-fitting uncertain facial images.
Results on public benchmarks demonstrate that our SCN outperforms current state-of-the-art methods with textbf88.14% on RAF-DB, textbf60.23% on AffectNet, and textbf89.35% on FERPlus.
arXiv Detail & Related papers (2020-02-24T17:24:36Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.