Motivated by recent advances in deep domain adaptation, this paper introduces a deep architecture for estimating 3D keypoints when the training (source) and the test (target) images greatly differ in terms of visual appearance (domain shift). Our approach operates by promoting domain distribution alignment in the feature space adopting batch normalization-based techniques. Furthermore, we propose to collect statistics about 3D keypoints positions of the source training data and to use this prior information to constrain predictions on the target domain introducing a loss derived from Multidimensional Scaling. We conduct an extensive experimental evaluation considering three publicly available benchmarks and show that our approach out-performs state-of-the-art domain adaptation methods for 3D keypoints predictions

Structured Domain Adaptation for 3D Keypoint Estimation / Vasconcelos, Levi; Mancini, Massimiliano; Boscaini, Davide; Caputo, Barbara; Ricci, Elisa. - (2019), pp. 57-66. (Intervento presentato al convegno 2019 International Conference on 3D Vision (3DV) tenutosi a Québec City (Canada) nel 16-19 Sept. 2019) [10.1109/3DV.2019.00016].

Structured Domain Adaptation for 3D Keypoint Estimation

Caputo Barbara;
2019

Abstract

Motivated by recent advances in deep domain adaptation, this paper introduces a deep architecture for estimating 3D keypoints when the training (source) and the test (target) images greatly differ in terms of visual appearance (domain shift). Our approach operates by promoting domain distribution alignment in the feature space adopting batch normalization-based techniques. Furthermore, we propose to collect statistics about 3D keypoints positions of the source training data and to use this prior information to constrain predictions on the target domain introducing a loss derived from Multidimensional Scaling. We conduct an extensive experimental evaluation considering three publicly available benchmarks and show that our approach out-performs state-of-the-art domain adaptation methods for 3D keypoints predictions
File in questo prodotto:
File Dimensione Formato  
08885979.pdf

non disponibili

Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 812.78 kB
Formato Adobe PDF
812.78 kB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11583/2785962