Segment My Object: A pipeline to extract segmented objects in images based on labels or bounding boxes - Université Paris Cité Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Segment My Object: A pipeline to extract segmented objects in images based on labels or bounding boxes

Camille Kurtz
Philippe Dejean
  • Fonction : Auteur
  • PersonId : 1109823
Laurent Wendling
  • Fonction : Auteur
  • PersonId : 1109824

Résumé

We propose a pipeline (SegMyO - Segment my object) to automatically extract segmented objects in images based on given labels and / or bounding boxes. When providing the expected label, our system looks for the closest label in the list of outputs, using a measure of semantic similarity. And when providing the bounding box, it looks for the output object with the best coverage, based on several geometric criteria. Associated with a semantic segmentation model trained on a similar dataset, or a good region proposal algorithm, this pipeline provides a simple solution to segment efficiently a dataset without requiring specific training, but also to the problem of weakly-supervised segmentation. This is particularly useful to segment public datasets available with weak object annotations (e.g., bounding boxes and labels from a detection, labels from a caption) coming from an algorithm or from manual annotation. An experimental study conducted on the PASCAL VOC 2012 dataset shows that these simple criteria embedded in SegMyO allow to select the proposal with the best IoU score in most cases, and so to get the best of the pre-segmentation.
Fichier principal
Vignette du fichier
VISAPP21_RD_final.pdf (549.28 Ko) Télécharger le fichier
VISAPP21_RD_final.zip (503.27 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03409511 , version 1 (29-10-2021)

Licence

Paternité

Identifiants

Citer

Robin Deléarde, Camille Kurtz, Philippe Dejean, Laurent Wendling. Segment My Object: A pipeline to extract segmented objects in images based on labels or bounding boxes. 16th International Conference on Computer Vision Theory and Applications, Feb 2021, Online Streaming, Austria. pp.618-625, ⟨10.5220/0010324006180625⟩. ⟨hal-03409511⟩

Collections

LIPADE UP-SCIENCES
61 Consultations
208 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More