Zero-Shot Semantic Segmentation - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

Zero-Shot Semantic Segmentation

Maxime Bucher
  • Fonction : Auteur
  • PersonId : 1048199
Tuan-Hung Vu
  • Fonction : Auteur
Matthieu Cord
Patrick Pérez
  • Fonction : Auteur
  • PersonId : 1022281

Résumé

Semantic segmentation models are limited in their ability to scale to large numbers of object classes. In this paper, we introduce the new task of zero-shot semantic segmentation: learning pixel-wise classifiers for never-seen object categories with zero training examples. To this end, we present a novel architecture, ZS3Net, combining a deep visual segmentation model with an approach to generate visual representations from semantic word embeddings. By this way, ZS3Net addresses pixel classification tasks where both seen and unseen categories are faced at test time (so called "generalized" zero-shot classification). Performance is further improved by a self-training step that relies on automatic pseudo-labeling of pixels from unseen classes. On the two standard segmentation datasets, Pascal-VOC and Pascal-Context, we propose zero-shot benchmarks and set competitive baselines. For complex scenes as ones in the Pascal-Context dataset, we extend our approach by using a graph-context encoding to fully leverage spatial context priors coming from class-wise segmentation maps. Code and models are available at: https://github.com/valeoai/zero_shot_semantic_segmentation
Fichier principal
Vignette du fichier
1-paper.pdf (5.48 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02146433 , version 1 (03-06-2019)
hal-02146433 , version 2 (29-10-2019)

Identifiants

  • HAL Id : hal-02146433 , version 2

Citer

Maxime Bucher, Tuan-Hung Vu, Matthieu Cord, Patrick Pérez. Zero-Shot Semantic Segmentation. NeurIPS, Dec 2019, vancouver, Canada. ⟨hal-02146433v2⟩
114 Consultations
224 Téléchargements

Partager

Gmail Facebook X LinkedIn More