2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) 2020
DOI: 10.1109/cvprw50498.2020.00314
|View full text |Cite
|
Sign up to set email alerts
|

iTASK - Intelligent Traffic Analysis Software Kit

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
5
0
2

Year Published

2020
2020
2023
2023

Publication Types

Select...
5
2

Relationship

0
7

Authors

Journals

citations
Cited by 15 publications
(8 citation statements)
references
References 23 publications
0
5
0
2
Order By: Relevance
“…More recently, the authors in [12] propose Ditto, where users collaborate to train a separate global model akin to [2], which is then used to steer the training of the local personalized model at each user via local model adaptation. Their approach embodies the intuition of pFedMe [13], which decouples personalized model optimization from the global model learning by introducing a penalizing term to regularize the clients local adaptation step. Despite resulting in a per-user personalized model, collaboration among users in Ditto and pFedMe is limited to updating the global model, while relying solely on the local data sets to train their personalized models, rather than leveraging collaboration among statistically similar learners to refine those models.…”
Section: Related Workmentioning
confidence: 99%
See 2 more Smart Citations
“…More recently, the authors in [12] propose Ditto, where users collaborate to train a separate global model akin to [2], which is then used to steer the training of the local personalized model at each user via local model adaptation. Their approach embodies the intuition of pFedMe [13], which decouples personalized model optimization from the global model learning by introducing a penalizing term to regularize the clients local adaptation step. Despite resulting in a per-user personalized model, collaboration among users in Ditto and pFedMe is limited to updating the global model, while relying solely on the local data sets to train their personalized models, rather than leveraging collaboration among statistically similar learners to refine those models.…”
Section: Related Workmentioning
confidence: 99%
“…The first set includes algorithms that achieve personalization by resulting multiple personalized models. Those include CFL [3], FedFomo [7], pFedMe [13] and Ditto [12]. The second set of baselines include algorithms that yield a single Federated model such as Fedprox 1 [10], SCAFFOLD [11].…”
Section: A Set-upmentioning
confidence: 99%
See 1 more Smart Citation
“…Tran vd. [4] çalışmalarında döner kavşak trafik akış koşullarını analiz etmek için deneysel verileri Sint-Truiden (Belçika) şehrinde elde etmişlerdir. Sonuçlar, UAV videolarının sağladığı esnekliğin ve kuş bakışı görünümünün değerini yansıtmaktadır.…”
Section: Introductionunclassified
“…İHA kullanımında önümüzdeki yıllarda beklenen önemli artışla birlikte, bu tür çalışmalar hem uygulayıcılar hem de gelecekteki araştırmacılar için faydalı bir kaynak olabilir. Gelecekteki araştırmalar, esas olarak İHA tabanlı trafik uygulamalarının daha fazla uzantılarına odaklanacaktır [4].…”
Section: Introductionunclassified