Modern saliency detection models are based on the encoder-decoder framework and they use different strategies to fuse the multi-level features between the encoder and decoder to boost representation power. Motivated by recent work in implicit modelling, we propose to introduce an implicit function to simulate the equilibrium state of the feature pyramid at infinite depths. We question the existence of the ideal equilibrium and thus propose a quasi-equilibrium model by taking the first-order derivative into the black-box root solver using Taylor expansion. It models more realistic convergence states and significantly improves the network performance. We also propose a differentiable edge extractor that directly extracts edges from the saliency masks. By optimizing the extracted edges, the generated saliency masks are naturally optimized on contour constraints and the non-deterministic predictions are removed. We evaluate the proposed methodology on five public datasets and extensive experiments show that our method achieves new state-of-the-art performances on six metrics across datasets.

Quasi-equilibrium Feature Pyramid Network for Salient Object Detection / Song, Y.; Tang, H.; Zhao, M.; Sebe, N.; Wang, W.. - In: IEEE TRANSACTIONS ON IMAGE PROCESSING. - ISSN 1057-7149. - 31:(2022), pp. 7144-7153. [10.1109/TIP.2022.3220058]

Quasi-equilibrium Feature Pyramid Network for Salient Object Detection

Song Y.;Tang H.;Sebe N.;Wang W.
2022-01-01

Abstract

Modern saliency detection models are based on the encoder-decoder framework and they use different strategies to fuse the multi-level features between the encoder and decoder to boost representation power. Motivated by recent work in implicit modelling, we propose to introduce an implicit function to simulate the equilibrium state of the feature pyramid at infinite depths. We question the existence of the ideal equilibrium and thus propose a quasi-equilibrium model by taking the first-order derivative into the black-box root solver using Taylor expansion. It models more realistic convergence states and significantly improves the network performance. We also propose a differentiable edge extractor that directly extracts edges from the saliency masks. By optimizing the extracted edges, the generated saliency masks are naturally optimized on contour constraints and the non-deterministic predictions are removed. We evaluate the proposed methodology on five public datasets and extensive experiments show that our method achieves new state-of-the-art performances on six metrics across datasets.
2022
Song, Y.; Tang, H.; Zhao, M.; Sebe, N.; Wang, W.
Quasi-equilibrium Feature Pyramid Network for Salient Object Detection / Song, Y.; Tang, H.; Zhao, M.; Sebe, N.; Wang, W.. - In: IEEE TRANSACTIONS ON IMAGE PROCESSING. - ISSN 1057-7149. - 31:(2022), pp. 7144-7153. [10.1109/TIP.2022.3220058]
File in questo prodotto:
File Dimensione Formato  
Yue-Tip22.pdf

accesso aperto

Tipologia: Post-print referato (Refereed author’s manuscript)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 8.33 MB
Formato Adobe PDF
8.33 MB Adobe PDF Visualizza/Apri
Quasi-Equilibrium_Feature_Pyramid_Network_for_Salient_Object_Detection.pdf

Solo gestori archivio

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 2.48 MB
Formato Adobe PDF
2.48 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/11572/361267
Citazioni
  • ???jsp.display-item.citation.pmc??? 0
  • Scopus 3
  • ???jsp.display-item.citation.isi??? 3
social impact