% IMPORTANT: The following is UTF-8 encoded.  This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.

@INPROCEEDINGS{Quercia:1034963,
      author       = {Quercia, Alessio and Yildiz, Erenus and Cao, Zhuo and
                      Morrison, Abigail and Krajsek, Kai and Assent, Ira and
                      Scharr, Hanno},
      title        = {{M}ulti-{S}ource {A}uxiliary {T}asks supported {M}onocular
                      {D}epth {E}stimation},
      reportid     = {FZJ-2025-00071},
      year         = {2024},
      note         = {The original abstract contains figures that cannot be shown
                      here.},
      abstract     = {Monocular 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 joint
                      training of a shared decoder on top of a pre-trained vision
                      foundation model, while giving a higher weight to MDE.In
                      particular, we leverage a frozen DINOv2 ViT Giant model as a
                      feature extractor, bypassing the need for fine-tuning, and
                      jointly train a shared DPT decoder with auxiliary datasets
                      from related tasks to improve MDE. We illustrate the
                      qualitative and quantitative improvements of our method over
                      the DINOv2 MDE baseline in Figures 1 and 2,
                      respectively.Notably, compared to the recent Depth Anything,
                      which reports no improvements using a jointly fine-tuned
                      DINOv2 ViT Large and task-specific decoders, our method
                      successfully leverages auxiliary tasks.Through extensive
                      experiments we demonstrate the benefits of incorporating
                      various auxiliary datasets and tasks to improve MDE quality
                      on average by $~11\%$ for related datasets. 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
                      often results in additional quality gains.},
      month         = {Jun},
      date          = {2024-06-12},
      organization  = {Helmholtz AI Conference, Düsseldorf
                       (Germany), 12 Jun 2024 - 14 Jun 2024},
      subtyp        = {After Call},
      cin          = {IAS-8 / IAS-6 / JSC},
      cid          = {I:(DE-Juel1)IAS-8-20210421 / I:(DE-Juel1)IAS-6-20130828 /
                      I:(DE-Juel1)JSC-20090406},
      pnm          = {5111 - Domain-Specific Simulation $\&$ Data Life Cycle Labs
                      (SDLs) and Research Groups (POF4-511) / 5112 - Cross-Domain
                      Algorithms, Tools, Methods Labs (ATMLs) and Research Groups
                      (POF4-511) / SLNS - SimLab Neuroscience (Helmholtz-SLNS)},
      pid          = {G:(DE-HGF)POF4-5111 / G:(DE-HGF)POF4-5112 /
                      G:(DE-Juel1)Helmholtz-SLNS},
      typ          = {PUB:(DE-HGF)6},
      url          = {https://juser.fz-juelich.de/record/1034963},
}