Modality-Guided Subnetwork for Salient Object Detection - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Modality-Guided Subnetwork for Salient Object Detection

Résumé

Recent RGBD-based models for saliency detection have attracted research attention. The depth clues such as boundary clues, surface normal, shape attribute, etc., contribute to the identification of salient objects with complicated scenarios. However, most RGBD networks require multi-modalities from the input side and feed them separately through a two-stream design, which inevitably results in extra costs on depth sensors and computation. To tackle these inconveniences, we present in this paper a novel fusion design named modality-guided subnetwork (MGSnet). It has the following superior designs: 1) Our model works for both RGB and RGBD data, and dynamically estimating depth if not available. Taking the inner workings of depthprediction networks into account, we propose to estimate the pseudo-geometry maps from RGB input-essentially mimicking the multi-modality input. 2) Our MGSnet for RGB SOD results in real-time inference but achieves stateof-the-art performance compared to other RGB models. 3) The flexible and lightweight design of MGS facilitates the integration into RGBD two-streaming models. The introduced fusion design enables a cross-modality interaction to enable further progress but with a minimal cost.
Fichier principal
Vignette du fichier
3DV21.pdf (2.37 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03375042 , version 1 (12-10-2021)
hal-03375042 , version 2 (25-10-2021)

Identifiants

  • HAL Id : hal-03375042 , version 2

Citer

Zongwei Wu, Guillaume Allibert, Christophe Stolz, Chao Ma, Cédric Demonceaux. Modality-Guided Subnetwork for Salient Object Detection. 9th International Conference on 3D Vision, Dec 2021, Online, France. ⟨hal-03375042v2⟩
60 Consultations
57 Téléchargements

Partager

Gmail Facebook X LinkedIn More