Despite impressive progress in object detection over the last years, it is still an open challenge to reliably detect objects across visual domains. All current approaches access a sizable amount of target data at training time. This is a heavy assumption, as often it is not possible to anticipate the domain where a detector will be used, nor to access it in advance for data acquisition. Consider for instance the task of monitoring image feeds from social media: as every image is uploaded by a different user it belongs to a different target domain that is impossible to foresee during training. Our work addresses this setting, presenting an object detection algorithm able to perform unsupervised adaptation across domains by using only one target sample, seen at test time. We introduce a multi-task architecture that one-shot adapts to any incoming sample by iteratively solving a self-supervised task on it. We further enhance this auxiliary adaptation with cross-task pseudo-labeling. A thorough benchmark analysis against the most recent cross-domain detection methods and a detailed ablation study show the advantage of our approach.
One-Shot Unsupervised Cross-Domain Detection / D'Innocente, A.; Borlino, F. C.; Bucci, S.; Caputo, B.; Tommasi, T.. - 12361:(2020), pp. 732-748. (Intervento presentato al convegno 16th European Conference on Computer Vision, ECCV 2020 tenutosi a Glasgow) [10.1007/978-3-030-58517-4_43].
One-Shot Unsupervised Cross-Domain Detection
D'Innocente A.
Primo
Methodology
;Tommasi T.Ultimo
2020
Abstract
Despite impressive progress in object detection over the last years, it is still an open challenge to reliably detect objects across visual domains. All current approaches access a sizable amount of target data at training time. This is a heavy assumption, as often it is not possible to anticipate the domain where a detector will be used, nor to access it in advance for data acquisition. Consider for instance the task of monitoring image feeds from social media: as every image is uploaded by a different user it belongs to a different target domain that is impossible to foresee during training. Our work addresses this setting, presenting an object detection algorithm able to perform unsupervised adaptation across domains by using only one target sample, seen at test time. We introduce a multi-task architecture that one-shot adapts to any incoming sample by iteratively solving a self-supervised task on it. We further enhance this auxiliary adaptation with cross-task pseudo-labeling. A thorough benchmark analysis against the most recent cross-domain detection methods and a detailed ablation study show the advantage of our approach.File | Dimensione | Formato | |
---|---|---|---|
DInnocente_preprint_One-Shot_2020.pdf
accesso aperto
Tipologia:
Documento in Pre-print (manoscritto inviato all'editore, precedente alla peer review)
Licenza:
Creative commons
Dimensione
9.29 MB
Formato
Adobe PDF
|
9.29 MB | Adobe PDF | |
DInnocente_One-Shot_2020.pdf
solo gestori archivio
Tipologia:
Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
2.21 MB
Formato
Adobe PDF
|
2.21 MB | Adobe PDF | Contatta l'autore |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.