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.
| Origine | Fichiers produits par l'(les) auteur(s) |
|---|---|
| Licence |
Copyright (Tous droits réservés)
|