Rethinking Interactive Image Segmentation: Feature Space Annotation - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Pattern Recognition Année : 2022

Rethinking Interactive Image Segmentation: Feature Space Annotation

Jordão Bragantini
  • Fonction : Auteur
  • PersonId : 1088169
Alexandre X Falcão
  • Fonction : Auteur
  • PersonId : 932800

Résumé

Despite the progress of interactive image segmentation methods, high-quality pixel-level annotation is still time-consuming and laborious — a bottleneck for several deep learning applications. We take a step back to propose interactive and simultaneous segment annotation from multiple images guided by feature space projection. This strategy is in stark contrast to existing interactive segmentation methodologies, which perform annotation in the image domain. We show that feature space annotation achieves competitive results with state-of-the-art methods in foreground segmentation datasets: iCoSeg, DAVIS, and Rooftop. Moreover, in the semantic segmentation context, it achieves 91.5% accuracy in the Cityscapes dataset, being 74.75 times faster than the original annotation procedure. Further, our contribution sheds light on a novel direction for interactive image annotation that can be integrated with existing methodologies. The supplementary material presents video demonstrations. Code available at https://github.com/LIDS-UNICAMP/rethinking-interactive-image-segmentation.
Fichier principal
Vignette du fichier
main.pdf (5.6 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03105751 , version 1 (11-01-2021)
hal-03105751 , version 2 (01-12-2021)
hal-03105751 , version 3 (10-07-2022)

Identifiants

Citer

Jordão Bragantini, Alexandre X Falcão, Laurent Najman. Rethinking Interactive Image Segmentation: Feature Space Annotation. Pattern Recognition, 2022, 131, pp.108882. ⟨10.1016/j.patcog.2022.108882⟩. ⟨hal-03105751v3⟩
166 Consultations
126 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More