It is a very well known fact in computer vision that classifiers trained on source datasets do not perform well when tested on other datasets acquired under different conditions. To this end, Unsupervised Domain adaptation (UDA) methods address the shift between the source and target domain by adapting the classifier to work well in the target domain despite having no access to the target labels. A handful of UDA methods bridge domain shift by aligning the source and target feature distributions through embedded domain alignment layers that are based on batch normalization (BN) or grouped whitening. Contrarily, in this work we propose to align feature distributions with domain specific full-feature whitening and domain agnostic colouring transforms, abbreviated as F2WCT . The proposed F2WCT optimally aligns the feature distributions by ensuring that the source and target features have identical covariance matrices. Our claim is also substantiated by the experimental results on Digits datasets for both single source and multi source unsupervised adaptation settings.

Unsupervised Domain Adaptation Using Full-Feature Whitening and Colouring

Roy, Subhankar;
2019

Abstract

It is a very well known fact in computer vision that classifiers trained on source datasets do not perform well when tested on other datasets acquired under different conditions. To this end, Unsupervised Domain adaptation (UDA) methods address the shift between the source and target domain by adapting the classifier to work well in the target domain despite having no access to the target labels. A handful of UDA methods bridge domain shift by aligning the source and target feature distributions through embedded domain alignment layers that are based on batch normalization (BN) or grouped whitening. Contrarily, in this work we propose to align feature distributions with domain specific full-feature whitening and domain agnostic colouring transforms, abbreviated as F2WCT . The proposed F2WCT optimally aligns the feature distributions by ensuring that the source and target features have identical covariance matrices. Our claim is also substantiated by the experimental results on Digits datasets for both single source and multi source unsupervised adaptation settings.
978-3-030-30644-1
978-3-030-30645-8
File in questo prodotto:
File Dimensione Formato  
RoySiaSeb_ICIAP_2019.pdf

non disponibili

Descrizione: Articolo principale
Licenza: NON PUBBLICO - Accesso privato/ristretto
Dimensione 530.69 kB
Formato Adobe PDF
530.69 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

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: http://hdl.handle.net/11582/320633
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
social impact