Multiple instance learning on deep features for weakly supervised object detection with extreme domain shifts - Equipe Image, Modélisation, Analyse, GEométrie, Synthèse Access content directly
Journal Articles Computer Vision and Image Understanding Year : 2022

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

Abstract

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
Origin : Files produced by the author(s)

Dates and versions

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

Licence

Attribution - NonCommercial

Identifiers

Cite

Nicolas Gonthier, Saïd Ladjal, Yann Gousseau. Multiple instance learning on deep features for weakly supervised object detection with extreme domain shifts. Computer Vision and Image Understanding, 2022, 214, ⟨10.1016/j.cviu.2021.103299⟩. ⟨hal-03210265⟩
75 View
15 Download

Altmetric

Share

Gmail Facebook X LinkedIn More