Salient object detection has been long studied to identify the most visually attractive objects in images/videos. Recently, a growing amount of approaches have been proposed, all of which rely on the contour/edge information to improve detection performance. The edge labels are either put into the loss directly or used as extra supervision. The edge and body can also be learned separately and then fused afterward. Both methods either lead to high prediction errors near the edge or cannot be trained in an end-to-end manner. Another problem is that existing methods may fail to detect objects of various sizes due to the lack of efficient and effective feature fusion mechanisms. In this work, we propose to decompose the saliency detection task into two cascaded sub-tasks, i.e., detail modeling and body filling. Specifically, detail modeling focuses on capturing the object edges by supervision of explicitly decomposed detail label that consists of the pixels that are nested on the edge and near the edge. Then the body filling learns the body part that will be filled into the detail map to generate more accurate saliency map. To effectively fuse the features and handle objects at different scales, we have also proposed two novel multi-scale detail attention and body attention blocks for precise detail and body modeling. Experimental results show that our method achieves state-of-the-art performances on six public datasets.

Disentangle Saliency Detection into Cascaded Detail Modeling and Body Filling / Song, Y.; Tang, H.; Sebe, N.; Wang, W.. - In: ACM TRANSACTIONS ON MULTIMEDIA COMPUTING, COMMUNICATIONS AND APPLICATIONS. - ISSN 1551-6857. - 19:1(2023), pp. 701-715. [10.1145/3513134]

Disentangle Saliency Detection into Cascaded Detail Modeling and Body Filling

Song Y.;Tang H.;Sebe N.;Wang W.
2023-01-01

Abstract

Salient object detection has been long studied to identify the most visually attractive objects in images/videos. Recently, a growing amount of approaches have been proposed, all of which rely on the contour/edge information to improve detection performance. The edge labels are either put into the loss directly or used as extra supervision. The edge and body can also be learned separately and then fused afterward. Both methods either lead to high prediction errors near the edge or cannot be trained in an end-to-end manner. Another problem is that existing methods may fail to detect objects of various sizes due to the lack of efficient and effective feature fusion mechanisms. In this work, we propose to decompose the saliency detection task into two cascaded sub-tasks, i.e., detail modeling and body filling. Specifically, detail modeling focuses on capturing the object edges by supervision of explicitly decomposed detail label that consists of the pixels that are nested on the edge and near the edge. Then the body filling learns the body part that will be filled into the detail map to generate more accurate saliency map. To effectively fuse the features and handle objects at different scales, we have also proposed two novel multi-scale detail attention and body attention blocks for precise detail and body modeling. Experimental results show that our method achieves state-of-the-art performances on six public datasets.
2023
1
Song, Y.; Tang, H.; Sebe, N.; Wang, W.
Disentangle Saliency Detection into Cascaded Detail Modeling and Body Filling / Song, Y.; Tang, H.; Sebe, N.; Wang, W.. - In: ACM TRANSACTIONS ON MULTIMEDIA COMPUTING, COMMUNICATIONS AND APPLICATIONS. - ISSN 1551-6857. - 19:1(2023), pp. 701-715. [10.1145/3513134]
File in questo prodotto:
File Dimensione Formato  
YueTOMM23.pdf

accesso aperto

Tipologia: Post-print referato (Refereed author’s manuscript)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 2.78 MB
Formato Adobe PDF
2.78 MB Adobe PDF Visualizza/Apri
3513134.pdf

Solo gestori archivio

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 5.32 MB
Formato Adobe PDF
5.32 MB Adobe PDF   Visualizza/Apri

I documenti in IRIS 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/11572/377275
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? 1
social impact