001033882 001__ 1033882
001033882 005__ 20251024202101.0
001033882 037__ $$aFZJ-2024-06720
001033882 1001_ $$0P:(DE-Juel1)188471$$aQuercia, Alessio$$b0$$eCorresponding author$$ufzj
001033882 1112_ $$aIEEE/CVF Winter Conference on Applications of Computer Vision$$cTucson$$d2025-02-28 - 2025-03-04$$gWACV$$wUSA
001033882 245__ $$aEnhancing Monocular Depth Estimation with Multi-Source Auxiliary Tasks
001033882 260__ $$c2025
001033882 300__ $$a8
001033882 3367_ $$2ORCID$$aCONFERENCE_PAPER
001033882 3367_ $$033$$2EndNote$$aConference Paper
001033882 3367_ $$2BibTeX$$aINPROCEEDINGS
001033882 3367_ $$2DRIVER$$aconferenceObject
001033882 3367_ $$2DataCite$$aOutput Types/Conference Paper
001033882 3367_ $$0PUB:(DE-HGF)8$$2PUB:(DE-HGF)$$aContribution to a conference proceedings$$bcontrib$$mcontrib$$s1761306747_21804
001033882 520__ $$aMonocular depth estimation (MDE) is a challenging task in computer vision, often hindered by the cost and scarcity of high-quality labeled datasets. We tackle this challenge using auxiliary datasets from related vision tasks for an alternating training scheme with a shared decoder built on top of a pre-trained vision foundation model, while giving a higher weight to MDE. Through extensive experiments we demonstrate the benefits of incorporating various in-domain auxiliary datasets and tasks to improve MDE quality on average by ~11%. Our experimental analysis shows that auxiliary tasks have different impacts, confirming the importance of task selection, highlighting that quality gains are not achieved by merely adding data. Remarkably, our study reveals that using semantic segmentation datasets as Multi-Label Dense Classification (MLDC) often results in additional quality gains. Lastly, our method significantly improves the data efficiency for the considered MDE datasets, enhancing their quality while reducing their size by at least 80%. This paves the way for using auxiliary data from related tasks to improve MDE quality despite limited availability of high-quality labeled data. Code is available at https://jugit.fz-juelich.de/ias-8/mdeaux.
001033882 536__ $$0G:(DE-HGF)POF4-5112$$a5112 - Cross-Domain Algorithms, Tools, Methods Labs (ATMLs) and Research Groups (POF4-511)$$cPOF4-511$$fPOF IV$$x0
001033882 7001_ $$0P:(DE-Juel1)191034$$aYildiz, Erenus$$b1$$ufzj
001033882 7001_ $$0P:(DE-Juel1)199019$$aCao, Zhuo$$b2$$ufzj
001033882 7001_ $$0P:(DE-Juel1)129347$$aKrajsek, Kai$$b3$$ufzj
001033882 7001_ $$0P:(DE-Juel1)151166$$aMorrison, Abigail$$b4$$ufzj
001033882 7001_ $$0P:(DE-Juel1)188313$$aAssent, Ira$$b5$$ufzj
001033882 7001_ $$0P:(DE-Juel1)129394$$aScharr, Hanno$$b6$$ufzj
001033882 909CO $$ooai:juser.fz-juelich.de:1033882$$pVDB
001033882 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)188471$$aForschungszentrum Jülich$$b0$$kFZJ
001033882 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)191034$$aForschungszentrum Jülich$$b1$$kFZJ
001033882 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)199019$$aForschungszentrum Jülich$$b2$$kFZJ
001033882 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)129347$$aForschungszentrum Jülich$$b3$$kFZJ
001033882 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)151166$$aForschungszentrum Jülich$$b4$$kFZJ
001033882 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)188313$$aForschungszentrum Jülich$$b5$$kFZJ
001033882 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)129394$$aForschungszentrum Jülich$$b6$$kFZJ
001033882 9131_ $$0G:(DE-HGF)POF4-511$$1G:(DE-HGF)POF4-510$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-5112$$aDE-HGF$$bKey Technologies$$lEngineering Digital Futures – Supercomputing, Data Management and Information Security for Knowledge and Action$$vEnabling Computational- & Data-Intensive Science and Engineering$$x0
001033882 9141_ $$y2025
001033882 9201_ $$0I:(DE-Juel1)IAS-8-20210421$$kIAS-8$$lDatenanalyse und Maschinenlernen$$x0
001033882 9201_ $$0I:(DE-Juel1)IAS-6-20130828$$kIAS-6$$lComputational and Systems Neuroscience$$x1
001033882 980__ $$acontrib
001033882 980__ $$aVDB
001033882 980__ $$aI:(DE-Juel1)IAS-8-20210421
001033882 980__ $$aI:(DE-Juel1)IAS-6-20130828
001033882 980__ $$aUNRESTRICTED