Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
×
May 16, 2020 · In this paper, we propose an unexplored direction -- the joint optimization of CNNs to provide a compressed model that is adapted to perform well for a given ...
In this paper, we focus on DL models for unsupervised domain adaptation (UDA) to allow adapting CNN embed- dings based on unlabeled data. The main body of ...
Implementation of the paper "Joint Progressive Knowledge Distillation and Unsupervised Domain Adaptation" by Le Thanh Nguyen-Meidine, Eric Granger, ...
May 16, 2020 · The proposed approach performs unsupervised knowledge distillation (KD) from a complex teacher model to a compact student model, by leveraging both source and ...
People also ask
In this paper, we propose a progressive KD approach for unsupervised single-target DA (STDA) and multi-target DA (MTDA) of CNNs.
In this paper, we proposed a three-step Progressive Cross-domain Knowledge Distillation (PCdKD) paradigm for efficient unsupervised adaptive object detection.
Dec 7, 2020 · Joint progressive knowledge distillation and unsupervised domain adaptation ; Compte rendu de conférence · Professeur. Granger, Éric. Dolz, José.
Joint progressive knowledge distillation and unsupervised domain adaptation. In 2020 International Joint Conference on Neural Networks (IJCNN), pages 1–8.
Joint progressive knowledge distillation and unsupervised domain adaptation. LT Nguyen-Meidine, E Granger, M Kiran, J Dolz, LA Blais-Morin. 2020 International ...
In this paper, we propose a progressive KD approach for unsupervised single-target DA (STDA) and multi-target DA (MTDA) of CNNs. Our method for KD-STDA adapts a ...