Figure 1 from FaceX-Zoo: A PyTorch Toolbox for Face Recognition | Semantic Scholar (2024)

This paper initializes the model parameters via a proxy task of patch reconstruction and observes that the ViT backbone exhibits improved training stability with satisfactory performance for face recognition, and proposes FaceT, a holistic and masked face recognition framework based on prompts.

It is demonstrated that faces under strong occlusions, some types of illumination, and strong expressions are problems mastered by deep learning algorithms, whereas recognition with low-resolution images, extreme pose variations, and open-set recognition is still an open problem.

A multi-branch network is proposed to simultaneously complete the task of the masked face detection and recognition and improves the Swin Transformer for extraction of facial features and focuses on the face organs that are not covered by masks.

This paper compares three SOTA real-time face-verification methods for coping with specific problems in surveillance applications and found that EfficientNet-B0 could deal with both surveillance problems, but MobileFaceNet was better at handling extreme face rotation over 80 degrees.

A mask-to-face image blending approach based on UV texture mapping, and a self-learning based cleaning pipeline for processing noisy training datasets and a loss function named Balanced Curricular Loss are introduced.

A simple and effective data augmentation method, named MaskOut, which replaces a random region below the nose of a face with a random mask template to mask out original face features and shows that the performances in masked face recognition are improved with this method.

It is shown that a simple approach based on fine-tuning pSp encoder for StyleGAN allows to improve upon the state-of-the-art facial recognition and performs better compared to training on synthetic face identities.

A novel face recognition method that is robust to occlusions based on a single end-to-end deep neural network, named FROM (Face Recognition with Occlusion Masks), learns to discover the corrupted features from the deep convolutional neural networks, and clean them by the dynamically learned masks.

This work discovers the best recognition methods for different conditions like non-masked faces, masked faces, and faces with glasses by testing them with same backbone architecture in order to focus only on the face recognition solution instead of network architecture.

...

...

A robust single-stage face detector, named RetinaFace, which performs pixel-wise face localisation on various scales of faces by taking advantages of joint extra-supervised and self-super supervised multi-task learning.

Extensive experiments on various benchmarks of face recognition show the proposed method significantly improves the training, not only in shallow face learning, but also for conventional deep face data.

This paper investigates a neat model with promising detection accuracy under wild environments e.g., unconstrained pose, expression, lighting, and occlusion conditions) and super real-time speed on a mobile device.

A system that directly learns a mapping from face images to a compact Euclidean space where distances directly correspond to a measure offace similarity, and achieves state-of-the-art face recognition performance using only 128-bytes perface.

This paper proposes MagFace, a category of losses that learn a universal feature embedding whose magnitude can measure the quality of the given face, and introduces an adaptive mechanism to learn a well-structured within-class feature distributions.

There is a gap between current face detection performance and the real world requirements, and the WIDER FACE dataset, which is 10 times larger than existing datasets is introduced, which contains rich annotations, including occlusions, poses, event categories, and face bounding boxes.

A simple yet effective Boundary-Attention Semantic Segmentation (BASS) method is proposed for face parsing, which contains a three-branch network with elaborately developed loss functions to fully exploit the boundary information.

A Cross-Pose LFW (CPLFW) database is constructed to add pose influence in face recognition and assures that performance on the database indicates true ability to distinguish individuals using their identities instead of depending on differences in gender and race.

The MegaFace dataset is assembled, both for identification and verification performance, and performance with respect to pose and a persons age is evaluated, as a function of training data size (#photos and #people).

This paper develops a novel loss function, which adaptively emphasizes the mis-classified feature vectors to guide the discriminative feature learning and is the first attempt to inherit the advantages of feature margin and feature mining into a unified loss function.

...

...