• Corpus ID: 236881207

SphereFace2: Binary Classification is All You Need for Deep Face Recognition

  title={SphereFace2: Binary Classification is All You Need for Deep Face Recognition},
  author={Yandong Wen and Weiyang Liu and Adrian Weller and Bhiksha Raj and Rita Singh},
State-of-the-art deep face recognition methods are mostly trained with a softmax-based multi-class classification framework. Despite being popular and effective, these methods still have a few shortcomings that limit empirical performance. In this paper, we first identify the discrepancy between training and evaluation in the existing multi-class classification framework and then discuss the potential limitations caused by the “competitive” nature of softmax normalization. Motivated by these… 

FedFR: Joint Optimization Federated Framework for Generic and Personalized Face Recognition

A FL based framework called FedFR is proposed to improve the generic face representation in a privacy-aware manner and jointly optimizes personalized models for the corresponding clients via the proposed Decoupled Feature Customization module.

Combining Metric Learning and Attention Heads For Accurate and Efficient Multilabel Image Classification

This work revisits two popular approaches to multilabel classification: transformer-based heads and labels relations information graph processing branches, and argues that with the proper training strategy graph-based methods can demonstrate just a small accuracy drop, while spending less computational resources on inference.

Learning to Generate Image Embeddings with User-level Differential Privacy

DP-FedEmb, a variant of federated learning algorithms with per-user sensitivity control and noise addition, is proposed to train image embedding models using supervised training data centralized in the datacenter to achieve user-level DP for large image-to-embedding feature extractors.

Hyperspherical Learning in Multi-Label Classification

A novel perspective for learning multi-label classification in hyperspherical space is presented and the impact of false positives in noisy multi- label tasks is thoroughly explored and the margin based sigmoid function for multi- Label classification is proposed.

Additive Orthant Loss for Deep Face Recognition

A novel loss function for deep face recognition, called the additive orthant loss (Orthant loss), which can be combined for softmax-based loss functions to improve the feature-discriminative capability is proposed.

Evidential Neighborhood Contrastive Learning for Universal Domain Adaptation

A novel evidential neighborhood contrastive learning framework called TNT is proposed, which significantly outperforms previous state-of-the-art UniDA methods and proposes a new domain alignment principle: semantically consistent samples should be geometrically adjacent to each other, whether within or across domains.

SphereFace Revived: Unifying Hyperspherical Face Recognition

This paper introduces a unified framework to understand large angular margin in hyperspherical face recognition, and extends the study of SphereFace and proposes an improved variant with substantially better training stability -- SphereFace-R.



L2-constrained Softmax Loss for Discriminative Face Verification

This paper adds an L2-constraint to the feature descriptors which restricts them to lie on a hypersphere of a fixed radius and shows that integrating this simple step in the training pipeline significantly boosts the performance of face verification.

CosFace: Large Margin Cosine Loss for Deep Face Recognition

  • H. WangYitong Wang Wei Liu
  • Computer Science
    2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
  • 2018
This paper reformulates the softmax loss as a cosine loss by L2 normalizing both features and weight vectors to remove radial variations, based on which acosine margin term is introduced to further maximize the decision margin in the angular space, and achieves minimum intra-class variance and maximum inter- class variance by virtue of normalization and cosine decision margin maximization.

ArcFace: Additive Angular Margin Loss for Deep Face Recognition

This paper presents arguably the most extensive experimental evaluation against all recent state-of-the-art face recognition methods on ten face recognition benchmarks, and shows that ArcFace consistently outperforms the state of the art and can be easily implemented with negligible computational overhead.

NormFace: L2 Hypersphere Embedding for Face Verification

This work identifies and study four issues related to normalization through mathematical analysis, which yields understanding and helps with parameter settings, and proposes two strategies for training using normalized features.

Ring Loss: Convex Feature Normalization for Face Recognition

This work motivates and presents Ring loss, a simple and elegant feature normalization approach for deep networks designed to augment standard loss functions such as Softmax, and applies soft normalization, where it gradually learns to constrain the norm to the scaled unit circle while preserving convexity leading to more robust features.

Partial FC: Training 10 Million Identities on a Single Machine

  • Xiang AnXuhan Zhu Ying Fu
  • Computer Science
    2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)
  • 2021
This work theoretically analyze the upper limit of model parallelism in face recognition and proposes a load-balanced sparse distributed classification training method, Partial FC, which is capable of using a machine with only 8 Nvidia Tesla V100 GPUs to implement training on a face recognition data set with up to 29 million IDs.

Simple Triplet Loss Based on Intra/Inter-Class Metric Learning for Face Verification

Experimental evaluations on the most widely used benchmarks LFW and YTF show that the model with the proposed class-wise simple triplet loss can reach the state-of-the-art performance.

Cross-Pose LFW : A Database for Studying Cross-Pose Face Recognition in Unconstrained Environments

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.

FaceNet: A unified embedding for face recognition and clustering

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.

Deep Learning Face Representation by Joint Identification-Verification

This paper shows that the face identification-verification task can be well solved with deep learning and using both face identification and verification signals as supervision, and the error rate has been significantly reduced.