Visual and Semantic Knowledge Transfer for Large Scale Semi-supervised Object Detection

Yuxing Tang 1 Josiah Wang 2 Xiaofang Wang 3, 4 Boyang Gao 4 Emmanuel Dellandréa 4 Robert Gaizauskas 2 Liming Chen 4
1 NIH - National Institutes of Health
2 University of Sheffield [Sheffield]
3 ECL - École Centrale de Lyon
4 imagine - Extraction de Caractéristiques et Identification
LIRIS - Laboratoire d'InfoRmatique en Image et Systèmes d'information
Abstract : Deep CNN-based object detection systems have achieved remarkable success on several large-scale object detection benchmarks. However, training such detectors requires a large number of labeled bounding boxes, which are more difficult to obtain than image-level annotations. Previous work addresses this issue by transforming image-level classifiers into object detectors. This is done by modeling the differences between the two on categories with both image-level and bounding box annotations, and transferring this information to convert classifiers to detectors for categories without bounding box annotations. We improve this previous work by incorporating knowledge about object similarities from visual and semantic domains during the transfer process. The intuition behind our proposed method is that visually and semantically similar categories should exhibit more common transferable properties than dissimilar categories, e.g. a better detector would result by transforming the differences between a dog classifier and a dog detector onto the cat class, than would by transforming from the violin class. Experimental results on the challenging ILSVRC2013 detection dataset demonstrate that each of our proposed object similarity based knowledge transfer methods outperforms the baseline methods. We found strong evidence that visual similarity and semantic relatedness are complementary for the task, and when combined notably improve detection, achieving state-of-the-art detection performance in a semi-supervised setting.
Keywords : convolutional neural networks weakly supervised object detection transfer learning object detection semi-supervised learning semantic similarity visual similarity
Type de document :
Article dans une revue
IEEE Transactions on Pattern Analysis and Machine Intelligence, Institute of Electrical and Electronics Engineers, 2017, pp.1 - 1. 〈10.1109/TPAMI.2017.2771779〉
Liste complète des métadonnées

Littérature citée [66 références]  Voir  Masquer  Télécharger
https://hal.archives-ouvertes.fr/hal-01678123
Contributeur : Yuxing Tang <>
Soumis le : jeudi 11 janvier 2018 - 16:17:11
Dernière modification le : jeudi 19 avril 2018 - 14:38:06
Document(s) archivé(s) le : jeudi 12 avril 2018 - 14:24:26

Fichier

TPAMI-R1-2017-03-0177.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

UNIV-LYON1 | EC-LYON | UNIV-LYON2 | LIRIS | INSA-LYON

Citation

Yuxing Tang, Josiah Wang, Xiaofang Wang, Boyang Gao, Emmanuel Dellandréa, et al.. Visual and Semantic Knowledge Transfer for Large Scale Semi-supervised Object Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, Institute of Electrical and Electronics Engineers, 2017, pp.1 - 1. 〈10.1109/TPAMI.2017.2771779〉. 〈hal-01678123〉

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

140

Téléchargements de fichiers

64

Contact

support.ccsd.cnrs.fr
hal.support@ccsd.cnrs.fr
Logo CCSD