Multiple instance learning on deep features for weakly supervised object detection with extreme domain shifts - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2024

Multiple instance learning on deep features for weakly supervised object detection with extreme domain shifts

Résumé

Weakly supervised object detection (WSOD) using only image-level annotations has attracted a growing attention over the past few years. Whereas such task is typically addressed with a domain-specific solution focused on natural images, we show that a simple multiple instance approach applied on pre-trained deep features yields excellent performances on non-photographic datasets, possibly including new classes. The approach does not include any fine-tuning or cross-domain learning and is therefore efficient and possibly applicable to arbitrary datasets and classes. We investigate several flavors of the proposed approach, some including multi-layers perceptron and polyhedral classifiers. Despite its simplicity, our method shows competitive results on a range of publicly available datasets, including paintings (People-Art, IconArt), watercolors, cliparts and comics and allows to quickly learn unseen visual categories.
Fichier principal
Vignette du fichier
S1077314221001430.pdf (1.74 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03210265 , version 1 (05-01-2024)

Licence

Paternité - Pas d'utilisation commerciale

Identifiants

Citer

Nicolas Gonthier, Saïd Ladjal, Yann Gousseau. Multiple instance learning on deep features for weakly supervised object detection with extreme domain shifts. 2024. ⟨hal-03210265⟩
68 Consultations
11 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More