Joint Learning of Salient Object Detection, Depth Estimation and Contour Extraction

Benefiting from color independence, illumination invariance and location discrimination attributed by the depth map, it can provide important supplemental information for extracting salient objects in complex environments. However, high-quality depth sensors are expensive and can not be widely appli...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - 31(2022) vom: 21., Seite 7350-7362
1. Verfasser: Zhao, Xiaoqi (VerfasserIn)
Weitere Verfasser: Pang, Youwei, Zhang, Lihe, Lu, Huchuan
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2022
Zugriff auf das übergeordnete Werk:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Schlagworte:Journal Article
LEADER 01000naa a22002652 4500
001 NLM349229945
003 DE-627
005 20231226042129.0
007 cr uuu---uuuuu
008 231226s2022 xx |||||o 00| ||eng c
024 7 |a 10.1109/TIP.2022.3222641  |2 doi 
028 5 2 |a pubmed24n1164.xml 
035 |a (DE-627)NLM349229945 
035 |a (NLM)36409818 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Zhao, Xiaoqi  |e verfasserin  |4 aut 
245 1 0 |a Joint Learning of Salient Object Detection, Depth Estimation and Contour Extraction 
264 1 |c 2022 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Revised 01.12.2022 
500 |a published: Print-Electronic 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a Benefiting from color independence, illumination invariance and location discrimination attributed by the depth map, it can provide important supplemental information for extracting salient objects in complex environments. However, high-quality depth sensors are expensive and can not be widely applied. While general depth sensors produce the noisy and sparse depth information, which brings the depth-based networks with irreversible interference. In this paper, we propose a novel multi-task and multi-modal filtered transformer (MMFT) network for RGB-D salient object detection (SOD). Specifically, we unify three complementary tasks: depth estimation, salient object detection and contour estimation. The multi-task mechanism promotes the model to learn the task-aware features from the auxiliary tasks. In this way, the depth information can be completed and purified. Moreover, we introduce a multi-modal filtered transformer (MFT) module, which equips with three modality-specific filters to generate the transformer-enhanced feature for each modality. The proposed model works in a depth-free style during the testing phase. Experiments show that it not only significantly surpasses the depth-based RGB-D SOD methods on multiple datasets, but also precisely predicts a high-quality depth map and salient contour at the same time. And, the resulted depth map can help existing RGB-D SOD methods obtain significant performance gain 
650 4 |a Journal Article 
700 1 |a Pang, Youwei  |e verfasserin  |4 aut 
700 1 |a Zhang, Lihe  |e verfasserin  |4 aut 
700 1 |a Lu, Huchuan  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on image processing : a publication of the IEEE Signal Processing Society  |d 1992  |g 31(2022) vom: 21., Seite 7350-7362  |w (DE-627)NLM09821456X  |x 1941-0042  |7 nnns 
773 1 8 |g volume:31  |g year:2022  |g day:21  |g pages:7350-7362 
856 4 0 |u http://dx.doi.org/10.1109/TIP.2022.3222641  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 31  |j 2022  |b 21  |h 7350-7362