DP-NET: LEARNING DISCRIMINATIVE PARTS FOR IMAGE RECOGNITION - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

DP-NET: LEARNING DISCRIMINATIVE PARTS FOR IMAGE RECOGNITION

Résumé

This paper presents Discriminative Part Network (DP-Net), a deep architecture with strong interpretation capabilities, which exploits a pretrained Convolutional Neural Network (CNN) combined with a part-based recognition module. This system learns and detects parts in the images that are discriminative among categories, without the need for fine-tuning the CNN, making it more scalable than other part-based models. While part-based approaches naturally offer interpretable representations, we propose explanations at image and category levels and introduce specific constraints on the part learning process to make them more discrimative.
Fichier principal
Vignette du fichier
ICIP2023 (3).pdf (3 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence
Copyright (Tous droits réservés)

Dates et versions

hal-04533061 , version 1 (05-04-2024)

Licence

Copyright (Tous droits réservés)

Identifiants

Citer

R. Sicre, H. Zhang, J. Dejasmin, C. Daaloul, S. Ayache, et al.. DP-NET: LEARNING DISCRIMINATIVE PARTS FOR IMAGE RECOGNITION. ICIP 2023, Oct 2023, Kuala lumpur, Malaysia. pp.1230-1234, ⟨10.1109/ICIP49359.2023.10222053⟩. ⟨hal-04533061⟩
3 Consultations
6 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More