4.7 Article

OTFace: Hard Samples Guided Optimal Transport Loss for Deep Face Representation

Related references

Note: Only part of the references are listed.
Article Computer Science, Artificial Intelligence

BuresNet: Conditional Bures Metric for Transferable Representation Learning

Chuan-Xian Ren et al.

Summary: Transfer learning is a fundamental approach for learning and cognition. It aims to transfer knowledge from the training environment to the test environment to improve model performance. Previous methods often ignore the discrepancy between conditional distributions, leading to reduced discriminability in test environments. This article introduces the Conditional Kernel Bures (CKB) metric, which provides an interpretable approach to measure and reduce the gap between conditional distributions. The proposed method, BuresNet, integrates CKB into deep networks and can extract conditional invariant features for unsupervised domain adaptation and few-shot learning tasks.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2023)

Article Automation & Control Systems

Joint Optimal Transport With Convex Regularization for Robust Image Classification

Jianjun Qian et al.

Summary: This paper proposes a novel robust regression scheme by integrating Optimal Transport (OT) with convex regularization to handle structure noises in high-dimensional visual data. Experimental results demonstrate the superior performance of our method in biometric image classification compared to several state-of-the-art regression-based classification methods.

IEEE TRANSACTIONS ON CYBERNETICS (2022)

Article Engineering, Electrical & Electronic

Simultaneous Face Completion and Frontalization via Mask Guided Two-Stage GAN

Qingyan Duan et al.

Summary: This study proposes a novel mask guided two-stage generative adversarial network (TSGAN) for the synthesis and recognition of profile but occluded facial images. By utilizing occlusion masks and employing a two-stage architecture, this method achieves impressive results in face restoration and frontalization.

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY (2022)

Article Engineering, Electrical & Electronic

Context-Aware Feature Learning for Noise Robust Person Search

Cairong Zhao et al.

Summary: This work focuses on the noise in person search, categorizing it into scene-inherent noise and human-introduced noise. The proposed methods include a context contrastive loss to utilize contextual information and a noise-discovery and noise-suppression training process. Experimental results show the effectiveness of the proposed context-aware noise-robust person search.

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY (2022)

Proceedings Paper Computer Science, Artificial Intelligence

DeepFace-EMD: Re-ranking Using Patch-wise Earth Mover's Distance Improves Out-Of-Distribution Face Identification

Hai Phan et al.

Summary: Face identification methods often struggle with out-of-distribution perturbations and occlusions. We propose a re-ranking approach that compares deep spatial features of images to address this issue.

2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022) (2022)

Proceedings Paper Computer Science, Artificial Intelligence

Enhancing Face Recognition with Self-Supervised 3D Reconstruction

Mingjie He et al.

Summary: This paper proposes a method to enhance face recognition by using self-supervised 3D reconstruction. By introducing auxiliary networks and physical parameters, the face recognition network is improved to better understand the 3D view of faces. Experimental results show that this method outperforms state-of-the-art ones and the learned features also perform well on other face-related tasks.

2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022) (2022)

Article Computer Science, Information Systems

Dynamic Training Data Dropout for Robust Deep Face Recognition

Yaoyao Zhong et al.

Summary: This research addresses the problem of learning with noise in deep face recognition. They propose a dynamic training data dropout (DTDD) method to filter noise and gradually form a stable database for robust training. The proposed method demonstrates its effectiveness in training deep face recognition models in the presence of label noise and low quality images.

IEEE TRANSACTIONS ON MULTIMEDIA (2022)

Article Computer Science, Artificial Intelligence

Look More Into Occlusion: Realistic Face Frontalization and Recognition With BoostGAN

Qingyan Duan et al.

Summary: This article discusses the challenges of face synthesis and recognition under poses and occlusions, proposing a new GAN model BoostGAN that effectively addresses occlusion but profile face recognition and synthesis.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2021)

Article Automation & Control Systems

AdvKin: Adversarial Convolutional Network for Kinship Verification

Lei Zhang et al.

Summary: This article proposes an AdvKin method based on family ID for discriminative kin features in both small-scale and large-scale kinship verification, with the advantages of self-adversarial mechanism, pairwise contrastive loss, family ID-based softmax loss, two-stream network architecture with residual connections, and ensemble of patch-wise AdvKin networks. Extensive experiments show the superiority of the proposed AdvKin model over other state-of-the-art approaches on multiple datasets.

IEEE TRANSACTIONS ON CYBERNETICS (2021)

Proceedings Paper Computer Science, Artificial Intelligence

Towards Interpretable Deep Metric Learning with Structural Matching

Wenliang Zhao et al.

Summary: The study introduces a deep interpretable metric learning (DIML) method that uses a structural matching strategy to align spatial embeddings of images. This method allows deep models to learn image similarity in a way that is more understandable to humans and has shown substantial improvements in deep metric learning benchmark tests.

2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021) (2021)

Proceedings Paper Computer Science, Artificial Intelligence

MagFace: A Universal Representation for Face Recognition and Quality Assessment

Qiang Meng et al.

Summary: MagFace is a new type of loss function that learns a universal feature embedding to measure the quality of a given face. It introduces an adaptive mechanism to learn well-structured within-class feature distributions, improving the accuracy of face recognition.

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021 (2021)

Article Computer Science, Artificial Intelligence

Incremental Generative Occlusion Adversarial Suppression Network for Person ReID

Cairong Zhao et al.

Summary: In this study, a novel Incremental Generative Occlusion Adversarial Suppression (IGOAS) network is proposed to address the occlusion problem in person re-identification. The network gradually learns occlusion difficulty instead of directly learning the hardest occlusion, improving the network's robustness. Experimental results show the competitive performance of IGOAS on occluded dataset, achieving decent Rank-1 accuracy and mAP.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2021)

Article Computer Science, Information Systems

Deep Fusion Feature Representation Learning With Hard Mining Center-Triplet Loss for Person Re-Identification

Cairong Zhao et al.

IEEE TRANSACTIONS ON MULTIMEDIA (2020)

Article Computer Science, Information Systems

An Equalized Margin Loss for Face Recognition

Jingna Sun et al.

IEEE TRANSACTIONS ON MULTIMEDIA (2020)

Article Computer Science, Artificial Intelligence

Compressive Binary Patterns: Designing a Robust Binary Face Descriptor with Random-Field Eigenfilters

Weihong Deng et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2019)

Article Computer Science, Artificial Intelligence

Reliable Crowdsourcing and Deep Locality-Preserving Learning for Unconstrained Facial Expression Recognition

Shan Li et al.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2019)

Proceedings Paper Computer Science, Artificial Intelligence

Probabilistic Face Embeddings

Yichun Shi et al.

2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019) (2019)

Proceedings Paper Computer Science, Artificial Intelligence

AdaptiveFace: Adaptive Margin and Sampling for Face Recognition

Hao Liu et al.

2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) (2019)

Article Engineering, Electrical & Electronic

Additive Margin Softmax for Face Verification

Feng Wang et al.

IEEE SIGNAL PROCESSING LETTERS (2018)

Article Computer Science, Artificial Intelligence

Wasserstein discriminant analysis

Remi Flamary et al.

MACHINE LEARNING (2018)

Proceedings Paper Computer Science, Information Systems

IARPA Janus Benchmark - C: Face Dataset and Protocol

Brianna Maze et al.

2018 INTERNATIONAL CONFERENCE ON BIOMETRICS (ICB) (2018)

Article Computer Science, Artificial Intelligence

Nuclear Norm Based Matrix Regression with Applications to Face Recognition with Occlusion and Illumination Changes

Jian Yang et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2017)

Article Computer Science, Artificial Intelligence

Optimal Transport for Domain Adaptation

Nicolas Courty et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2017)

Proceedings Paper Computer Science, Artificial Intelligence

IARPA Janus Benchmark-B Face Dataset

Cameron Whitelam et al.

2017 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW) (2017)

Proceedings Paper Computer Science, Artificial Intelligence

AgeDB: the first manually collected, in-the-wild age database

Stylianos Moschoglou et al.

2017 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW) (2017)

Proceedings Paper Computer Science, Artificial Intelligence

Marginal Loss for Deep Face Recognition

Jiankang Deng et al.

2017 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW) (2017)

Proceedings Paper Computer Science, Artificial Intelligence

SphereFace: Deep Hypersphere Embedding for Face Recognition

Weiyang Liu et al.

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017) (2017)

Proceedings Paper Computer Science, Artificial Intelligence

Noisy Softmax: Improving the Generalization Ability of DCNN via Postponing the Early Softmax Saturation

Binghui Chen et al.

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017) (2017)

Article Computer Science, Hardware & Architecture

ImageNet Classification with Deep Convolutional Neural Networks

Alex Krizhevsky et al.

COMMUNICATIONS OF THE ACM (2017)

Proceedings Paper Computer Science, Artificial Intelligence

The MegaFace Benchmark: 1 Million Faces for Recognition at Scale

Ira Kemelmacher-Shlizerman et al.

2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) (2016)

Article Computer Science, Artificial Intelligence

Learning Compact Binary Face Descriptor for Face Recognition

Jiwen Lu et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2015)

Article Computer Science, Artificial Intelligence

Learning Discriminant Face Descriptor

Zhen Lei et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2014)

Article Computer Science, Artificial Intelligence

Sparse Representation Classifier Steered Discriminative Projection With Applications to Face Recognition

Jian Yang et al.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2013)

Article Computer Science, Hardware & Architecture

Robust Principal Component Analysis?

Emmanuel J. Candes et al.

JOURNAL OF THE ACM (2011)

Article Computer Science, Artificial Intelligence

Fusing Local Patterns of Gabor Magnitude and Phase for Face Recognition

Shufu Xie et al.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2010)

Article Computer Science, Artificial Intelligence

Robust Face Recognition via Sparse Representation

John Wright et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2009)

Article Computer Science, Artificial Intelligence

Globally maximizing, locally minimizing: Unsupervised discriminant projection with applications to face and palm biometrics

Jian Yang et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2007)

Article Computer Science, Artificial Intelligence

Face description with local binary patterns:: Application to face recognition

Timo Ahonen et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2006)