Centre de documentation
scientifique

Bayesian transfer learning for object detection in optical remote sensing images / Changsheng Zhou in IEEE Transactions on geoscience and remote sensing, vol 58 n° 11 (November 2020)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 58 n° 11 (November 2020) . - pp 7705 - 7719 Titre : Bayesian transfer learning for object detection in optical remote sensing images Type de document : Article/Communication Auteurs : Changsheng Zhou, Auteur ; Jiangshe Zhang, Auteur ; Junmin Liu, Auteur ; et al., Auteur Année de publication : 2020 Article en page(s) : pp 7705 - 7719 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] apprentissage profond [Termes IGN] chaîne de traitement [Termes IGN] détection d'objet [Termes IGN] distribution de Fisher [Termes IGN] jeu de données localisées [Termes IGN] théorème de Bayes Résumé : (auteur) In the literature of object detection in optical remote sensing images, a popular pipeline is first modifying an off-the-shelf deep neural network, then initializing the modified network by pretrained weights on a source data set, and finally fine-tuning the network on a target data set. The procedure works well in practice but might not make full use of underlying knowledge implied by pretrained weights. In this article, we propose a novel method, referred to as Fisher regularization, for efficient knowledge transferring. Based on Bayes’ theorem, the method stores underlying knowledge into a Fisher information matrix and fine-tunes parameters based on the knowledge. The proposed method would not introduce extra parameters and is less sensitive to hyperparameters than classical weight decay. Experiments on NWPUVHR-10 and DOTA data sets show that the proposed method is effective and works well with different object detectors. Numéro de notice : A2020-679 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2020.2983201 Date de publication en ligne : 14/04/2020 En ligne : https://doi.org/10.1109/TGRS.2020.2983201 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96182 [article]