Federated Learning for Face Recognition with Gradient Correction
- URL: http://arxiv.org/abs/2112.07246v1
- Date: Tue, 14 Dec 2021 09:19:29 GMT
- Title: Federated Learning for Face Recognition with Gradient Correction
- Authors: Yifan Niu, Weihong Deng
- Abstract summary: In this work, we introduce a framework, FedGC, to tackle federated learning for face recognition.
We show that FedGC constitutes a valid loss function similar to standard softmax.
- Score: 52.896286647898386
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: With increasing appealing to privacy issues in face recognition, federated
learning has emerged as one of the most prevalent approaches to study the
unconstrained face recognition problem with private decentralized data.
However, conventional decentralized federated algorithm sharing whole
parameters of networks among clients suffers from privacy leakage in face
recognition scene. In this work, we introduce a framework, FedGC, to tackle
federated learning for face recognition and guarantees higher privacy. We
explore a novel idea of correcting gradients from the perspective of backward
propagation and propose a softmax-based regularizer to correct gradients of
class embeddings by precisely injecting a cross-client gradient term.
Theoretically, we show that FedGC constitutes a valid loss function similar to
standard softmax. Extensive experiments have been conducted to validate the
superiority of FedGC which can match the performance of conventional
centralized methods utilizing full training dataset on several popular
benchmark datasets.
Related papers
- AdaFedFR: Federated Face Recognition with Adaptive Inter-Class Representation Learning [14.139432393751298]
We propose a simple yet effective federated face recognition framework called AdaFedFR.
Our work delicately utilizes feature representations of public identities as learnable negative knowledge to optimize the local objective.
Experimental results demonstrate that our method outperforms previous approaches on several prevalent face recognition benchmarks within less than 3 communication rounds.
arXiv Detail & Related papers (2024-05-22T09:19:25Z) - Cluster-level pseudo-labelling for source-free cross-domain facial
expression recognition [94.56304526014875]
We propose the first Source-Free Unsupervised Domain Adaptation (SFUDA) method for Facial Expression Recognition (FER)
Our method exploits self-supervised pretraining to learn good feature representations from the target data.
We validate the effectiveness of our method in four adaptation setups, proving that it consistently outperforms existing SFUDA methods when applied to FER.
arXiv Detail & Related papers (2022-10-11T08:24:50Z) - Escaping Data Scarcity for High-Resolution Heterogeneous Face
Hallucination [68.78903256687697]
In Heterogeneous Face Recognition (HFR), the objective is to match faces across two different domains such as visible and thermal.
Recent methods attempting to fill the gap via synthesis have achieved promising results, but their performance is still limited by the scarcity of paired training data.
In this paper, we propose a new face hallucination paradigm for HFR, which not only enables data-efficient synthesis but also allows to scale up model training without breaking any privacy policy.
arXiv Detail & Related papers (2022-03-30T20:44:33Z) - Improving Federated Learning Face Recognition via Privacy-Agnostic
Clusters [7.437386882362172]
This work proposes PrivacyFace, a framework to improve federated learning face recognition.
It consists of two components: First, a practical Differentially Private Local Clustering mechanism is proposed to distill sanitized clusters from local class centers.
Second, a consensus-aware recognition loss subsequently encourages global consensuses among clients, which ergo results in more discriminative features.
arXiv Detail & Related papers (2022-01-29T01:27:04Z) - Differentially Private Federated Learning on Heterogeneous Data [10.431137628048356]
Federated Learning (FL) is a paradigm for large-scale distributed learning.
It faces two key challenges: (i) efficient training from highly heterogeneous user data, and (ii) protecting the privacy of participating users.
We propose a novel FL approach to tackle these two challenges together by incorporating Differential Privacy (DP) constraints.
arXiv Detail & Related papers (2021-11-17T18:23:49Z) - SphereFace Revived: Unifying Hyperspherical Face Recognition [57.07058009281208]
We introduce a unified framework to understand large angular margin in hyperspherical face recognition.
Under this framework, we propose an improved variant with substantially better training stability -- SphereFace-R.
We show that SphereFace-R is consistently better than or competitive with state-of-the-art methods.
arXiv Detail & Related papers (2021-09-12T17:07:54Z) - Understanding Clipping for Federated Learning: Convergence and
Client-Level Differential Privacy [67.4471689755097]
This paper empirically demonstrates that the clipped FedAvg can perform surprisingly well even with substantial data heterogeneity.
We provide the convergence analysis of a differential private (DP) FedAvg algorithm and highlight the relationship between clipping bias and the distribution of the clients' updates.
arXiv Detail & Related papers (2021-06-25T14:47:19Z) - Federated Face Recognition [30.344709613627764]
Federated Learning is proposed to train a model cooperatively without sharing data between parties.
This paper proposes a framework named FedFace to innovate federated learning for face recognition.
arXiv Detail & Related papers (2021-05-06T08:07:25Z) - Hierarchical Deep CNN Feature Set-Based Representation Learning for
Robust Cross-Resolution Face Recognition [59.29808528182607]
Cross-resolution face recognition (CRFR) is important in intelligent surveillance and biometric forensics.
Existing shallow learning-based and deep learning-based methods focus on mapping the HR-LR face pairs into a joint feature space.
In this study, we desire to fully exploit the multi-level deep convolutional neural network (CNN) feature set for robust CRFR.
arXiv Detail & Related papers (2021-03-25T14:03:42Z) - BioMetricNet: deep unconstrained face verification through learning of
metrics regularized onto Gaussian distributions [25.00475462213752]
We present BioMetricNet, a novel framework for deep unconstrained face verification.
The proposed approach does not impose any specific metric on facial features.
It shapes the decision space by learning a latent representation in which matching and non-matching pairs are mapped onto clearly separated and well-behaved target distributions.
arXiv Detail & Related papers (2020-08-13T17:22:46Z)
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.