Nothing Special   »   [go: up one dir, main page]

×
Please click here if you are not redirected within a few seconds.
Apr 9, 2022 · FedFR jointly optimizes clustering-based domain adaptation and federated learning to elevate performance on the target domain. Specifically, for ...
Extensive experiments on a newly constructed benchmark demonstrate that FedFR outperforms the baseline and classic methods on the target domain by 3% to 14% on ...
FedFR jointly optimizes clustering-based domain adaptation and federated learning to elevate performance on the target domain. Specif-ically, for unlabeled data ...
We propose federated unsupervised domain adaptation for face recognition, FedFR. FedFR jointly optimizes clustering-based domain adaptation and federated ...
Their experiments show the FedFR's performance on verification accuracy in face recognition is 3%-14% higher than baseline and other classic frameworks. ...
May 17, 2021 · We propose a novel unsupervised federated face recognition approach (FedFR). FedFR improves the performance in the target domain by iteratively aggregating ...
We propose an unsupervised domain adaptation method for video face recognition using large-scale unlabeled videos and labeled still images. To help bridge the ...
Missing: Federated | Show results with:Federated
People also ask
May 17, 2021 · This work proposes a novel unsupervised federated face recognition approach (FedFR), which improves the performance in the target domain by ...
We present FedUReID, a federated unsupervised person ReID system to learn person ReID models without any labels while preserving privacy. Federated Learning ...
In comparison with Unsupervised Domain Adaptation for Face Recognition (UDA-FR), UDAL-FR additionally constrains the number of samples from the target ...