While most of the recent literature on semantic segmentation has focused on outdoor scenarios, the generation of accurate indoor segmentation maps has been partially under-investigated, although being a relevant task with applications in augmented reality, image retrieval, and personalized robotics. With the goal of increasing the accuracy of semantic segmentation in indoor scenarios, we develop and propose two novel boundary-level training objectives, which foster the generation of accurate boundaries between different semantic classes. In particular, we take inspiration from the Boundary and Active Boundary losses, two recent proposals which deal with the prediction of semantic boundaries, and propose modified geometric distance functions that improve predictions at the boundary level. Through experiments on the NYUDv2 dataset, we assess the appropriateness of our proposal in terms of accuracy and quality of boundary prediction and demonstrate its accuracy gain.

Improving Indoor Semantic Segmentation with Boundary-level Objectives / Amoroso, Roberto; Baraldi, Lorenzo; Cucchiara, Rita. - 12862:(2021), pp. 318-329. (Intervento presentato al convegno 16th International Work-Conference on Artificial Neural Networks, IWANN 2021 tenutosi a Online nel June 16-18, 2021) [10.1007/978-3-030-85099-9_26].

Improving Indoor Semantic Segmentation with Boundary-level Objectives

Amoroso, Roberto
;
Baraldi, Lorenzo;Cucchiara, Rita
2021

Abstract

While most of the recent literature on semantic segmentation has focused on outdoor scenarios, the generation of accurate indoor segmentation maps has been partially under-investigated, although being a relevant task with applications in augmented reality, image retrieval, and personalized robotics. With the goal of increasing the accuracy of semantic segmentation in indoor scenarios, we develop and propose two novel boundary-level training objectives, which foster the generation of accurate boundaries between different semantic classes. In particular, we take inspiration from the Boundary and Active Boundary losses, two recent proposals which deal with the prediction of semantic boundaries, and propose modified geometric distance functions that improve predictions at the boundary level. Through experiments on the NYUDv2 dataset, we assess the appropriateness of our proposal in terms of accuracy and quality of boundary prediction and demonstrate its accuracy gain.
2021
16th International Work-Conference on Artificial Neural Networks, IWANN 2021
Online
June 16-18, 2021
12862
318
329
Amoroso, Roberto; Baraldi, Lorenzo; Cucchiara, Rita
Improving Indoor Semantic Segmentation with Boundary-level Objectives / Amoroso, Roberto; Baraldi, Lorenzo; Cucchiara, Rita. - 12862:(2021), pp. 318-329. (Intervento presentato al convegno 16th International Work-Conference on Artificial Neural Networks, IWANN 2021 tenutosi a Online nel June 16-18, 2021) [10.1007/978-3-030-85099-9_26].
File in questo prodotto:
File Dimensione Formato  
IWANN_2021_05_10_Improving_Indoor_Semantic_Segmentation_with_Boundary_level_Objectives.pdf

Open access

Descrizione: Articolo principale
Tipologia: Versione originale dell'autore proposta per la pubblicazione
Dimensione 3.29 MB
Formato Adobe PDF
3.29 MB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

Licenza Creative Commons
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11380/1246075
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? 1
social impact