Providing fine-grained and accurate segmentation maps of indoor scenes is a challenging task with relevant applications in the fields of augmented reality, image retrieval, and personalized robotics. 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. With the goal of increasing the accuracy of semantic segmentation in indoor scenarios, we focus on the analysis of boundary-level objectives, which foster the generation of fine-grained boundaries between different semantic classes and which have never been explored in the case of indoor segmentation. In particular, we test and devise variants of both the Boundary and Active Boundary losses, two recent proposals which deal with the prediction of semantic boundaries. Through experiments on the NYUDv2 dataset, we quantify the role of such losses in terms of accuracy and quality of boundary prediction and demonstrate the accuracy gain of the proposed variants.

Assessing the Role of Boundary-level Objectives in Indoor Semantic Segmentation / Amoroso, Roberto; Baraldi, Lorenzo; Cucchiara, Rita. - 13052 LNCS:(2021), pp. 455-465. (Intervento presentato al convegno 19th International Conference on Computer Analysis of Images and Patterns (CAIP) tenutosi a Virtual nel 27 September - 01 October 2021) [10.1007/978-3-030-89128-2_44].

Assessing the Role of Boundary-level Objectives in Indoor Semantic Segmentation

Roberto Amoroso
;
Lorenzo Baraldi;Rita Cucchiara
2021

Abstract

Providing fine-grained and accurate segmentation maps of indoor scenes is a challenging task with relevant applications in the fields of augmented reality, image retrieval, and personalized robotics. 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. With the goal of increasing the accuracy of semantic segmentation in indoor scenarios, we focus on the analysis of boundary-level objectives, which foster the generation of fine-grained boundaries between different semantic classes and which have never been explored in the case of indoor segmentation. In particular, we test and devise variants of both the Boundary and Active Boundary losses, two recent proposals which deal with the prediction of semantic boundaries. Through experiments on the NYUDv2 dataset, we quantify the role of such losses in terms of accuracy and quality of boundary prediction and demonstrate the accuracy gain of the proposed variants.
2021
19th International Conference on Computer Analysis of Images and Patterns (CAIP)
Virtual
27 September - 01 October 2021
13052 LNCS
455
465
Amoroso, Roberto; Baraldi, Lorenzo; Cucchiara, Rita
Assessing the Role of Boundary-level Objectives in Indoor Semantic Segmentation / Amoroso, Roberto; Baraldi, Lorenzo; Cucchiara, Rita. - 13052 LNCS:(2021), pp. 455-465. (Intervento presentato al convegno 19th International Conference on Computer Analysis of Images and Patterns (CAIP) tenutosi a Virtual nel 27 September - 01 October 2021) [10.1007/978-3-030-89128-2_44].
File in questo prodotto:
File Dimensione Formato  
CAIP_2021_05_05_Assessing_the_Role_of_Boundary_level_Objectives_in_Indoor_Semantic_Segmentation.pdf

Open access

Descrizione: Articolo principale
Tipologia: Versione dell'autore revisionata e accettata per la pubblicazione
Dimensione 1.69 MB
Formato Adobe PDF
1.69 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/11380/1249347
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? 1
social impact