The availability of large-scale data sets is an essential prerequisite for deep learning-based semantic segmentation schemes. Since obtaining pixel-level labels is extremely expensive, supervising deep semantic segmentation networks using low-cost weak annotations has been an attractive research problem in recent years. In this work, we explore the potential of Constrained Dominant Sets (CDS) for generating multi-labeled full mask predictions to train a fully convolutional network (FCN) for semantic segmentation. Our experimental results show that using CDS’s yields higher-quality mask predictions compared to methods that have been adopted in the literature for the same purpose.

Weakly Supervised Semantic Segmentation Using Constrained Dominant Sets

Aslan, Sinem
;
Pelillo, Marcello
2019

Abstract

The availability of large-scale data sets is an essential prerequisite for deep learning-based semantic segmentation schemes. Since obtaining pixel-level labels is extremely expensive, supervising deep semantic segmentation networks using low-cost weak annotations has been an attractive research problem in recent years. In this work, we explore the potential of Constrained Dominant Sets (CDS) for generating multi-labeled full mask predictions to train a fully convolutional network (FCN) for semantic segmentation. Our experimental results show that using CDS’s yields higher-quality mask predictions compared to methods that have been adopted in the literature for the same purpose.
20th International Conference on Image Analysis and Processing, ICIAP 2019 - Proceedings
File in questo prodotto:
File Dimensione Formato  
aslan2019_ICIAP.pdf

non disponibili

Tipologia: Versione dell'editore
Licenza: Accesso chiuso-personale
Dimensione 2.04 MB
Formato Adobe PDF
2.04 MB Adobe PDF   Visualizza/Apri

I documenti in ARCA sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10278/3732390
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? 0
social impact