HARF: Hierarchy-Associated Rich Features for Salient Object Detection

Abstract : The state-of-the-art salient object detection models are able to perform well for relatively simple scenes, yet for more complex ones, they still have difficulties in highlighting salient objects completely from background, largely due to the lack of sufficiently robust features for saliency prediction. To address such an issue, this paper proposes a novel hierarchy-associated feature construction framework for salient object detection, which is based on integrating elementary features from multi-level regions in a hierarchy. Furthermore, multi-layered deep learning features are introduced and incorporated as elementary features into this framework through a compact integration scheme. This leads to a rich feature representation, which is able to represent the context of the whole object/background and is much more discriminative as well as robust for salient object detection. Extensive experiments on the most widely used and challenging benchmark datasets demonstrate that the proposed approach substantially outperforms the state-of-the-art on salient object detection.
Type de document :
Communication dans un congrès
2015 IEEE International Conference on Computer Vision (ICCV), Dec 2015, Santiago, France. IEEE, 2016, 〈10.1109/ICCV.2015.54〉
Liste complète des métadonnées

https://hal-enpc.archives-ouvertes.fr/hal-01832512
Contributeur : Nikos Komodakis <>
Soumis le : samedi 7 juillet 2018 - 21:58:19
Dernière modification le : lundi 3 septembre 2018 - 16:36:35

Identifiants

Citation

Wenbin Zou, Nikos Komodakis. HARF: Hierarchy-Associated Rich Features for Salient Object Detection. 2015 IEEE International Conference on Computer Vision (ICCV), Dec 2015, Santiago, France. IEEE, 2016, 〈10.1109/ICCV.2015.54〉. 〈hal-01832512〉

Partager

Métriques

Consultations de la notice

98