Depth as Attention for Face Representation Learning

@article{Uppal2021DepthAA,
  title={Depth as Attention for Face Representation Learning},
  author={Hardik Uppal and Alireza Sepas-Moghaddam and Michael A. Greenspan and Ali Etemad},
  journal={IEEE Transactions on Information Forensics and Security},
  year={2021},
  volume={16},
  pages={2461-2476}
}
Face representation learning solutions have recently achieved great success for various applications such as verification and identification. However, face recognition approaches that are based purely on RGB images rely solely on intensity information, and therefore are more sensitive to facial variations, notably pose, occlusions, and environmental changes such as illumination and background. A novel depth-guided attention mechanism is proposed for deep multi-modal face recognition using low… Expand
Teacher-Student Adversarial Depth Hallucination to Improve Face Recognition
TLDR
A Teacher-Student Generative Adversarial Network to generate depth images from single RGB images in order to boost the performance of face recognition systems and performs rigorous experiments to show the superiority of TS-GAN over other methods in generating synthetic depth images. Expand

References

SHOWING 1-10 OF 82 REFERENCES
Rgb-D Based Multi-Modal Deep Learning for Face Identification
TLDR
This work proposes a multi-modal learning method that achieves 99.7% classification accuracy and exceeds the most state-of-the-art methods, and the global descriptors of model output are designed to be binarized. Expand
Two-Level Attention-based Fusion Learning for RGB-D Face Recognition
TLDR
Comparative evaluations demonstrate that the proposed method outperforms other state-of-the-art approaches, including both traditional and deep neural network-based methods, on the challenging CurtinFaces and IIIT-D RGB-D benchmark databases, achieving classification accuracies over 98.2% and 99.3% respectively. Expand
RGB-D Face Recognition via Deep Complementary and Common Feature Learning
TLDR
This work proposes a novel approach for RGB-D face recognition that is able to learn complementary features from multiple modalities and common features between different modalities, and introduces a joint loss taking activation from both modality-specific feature learning networks, and enforcing the features to be learned in a complementary way. Expand
Robust RGB-D Face Recognition Using Attribute-Aware Loss
TLDR
A new CNN-based face recognition approach that incorporates such attributes into the training process using an attribute-aware loss function that regularizes the feature mapping using attribute proximity, which greatly improve the accuracy and robustness of face recognition. Expand
LIGHT FIELD BASED FACE RECOGNITION VIA A FUSED DEEP REPRESENTATION
TLDR
This paper proposes the first deep CNN solution for light field based face recognition, exploiting the richer information available in a lenslet light field image, and for the first time, the exploitation of disparity maps together with 2D-RGB images and depth maps has been considered in the context of a fusion scheme to improve the face recognition performance. Expand
Face Verification from Depth using Privileged Information
TLDR
The proposed approach efficiently verifies if two face images belong to the same person while handling a great variety of head poses and occlusions, despite the lack of deep-oriented depth-based datasets. Expand
Improving 2D Face Recognition via Discriminative Face Depth Estimation
TLDR
Experiments show that the proposed face recognition method using RGB and estimated depth information can achieve better accuracy than using RGB modality alone. Expand
Occlusion Robust Face Recognition Based on Mask Learning With Pairwise Differential Siamese Network
TLDR
Comprehensive experiments on both synthesized and realistic occluded face datasets show that the proposed algorithm significantly outperforms the state-of-the-art systems. Expand
Distance Metric Learning Using Privileged Information for Face Verification and Person Re-Identification
In this paper, we propose a new approach to improve face verification and person re-identification in the RGB images by leveraging a set of RGB-D data, in which we have additional depth images in theExpand
Deep Face Recognition: A Survey
TLDR
A comprehensive review of the recent developments on deep FR, covering broad topics on algorithm designs, databases, protocols, and application scenes, and the technical challenges and several promising directions are highlighted. Expand
...
1
2
3
4
5
...