% 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”.
@ARTICLE{Paul:1033893,
author = {Paul, Richard D. and Quercia, Alessio and Fortuin, Vincent
and Nöh, Katharina and Scharr, Hanno},
title = {{P}arameter-efficient {B}ayesian {N}eural {N}etworks for
{U}ncertainty-aware {D}epth {E}stimation},
publisher = {arXiv},
reportid = {FZJ-2024-06731},
year = {2024},
note = {Presented as an Extended Abstract at the 3rd Workshop on
Uncertainty Quantification for Computer Vision at the
ECCV'24.},
abstract = {State-of-the-art computer vision tasks, like monocular
depth estimation (MDE), rely heavily on large, modern
Transformer-based architectures. However, their application
in safety-critical domains demands reliable predictive
performance and uncertainty quantification. While Bayesian
neural networks provide a conceptually simple approach to
serve those requirements, they suffer from the high
dimensionality of the parameter space. Parameter-efficient
fine-tuning (PEFT) methods, in particular low-rank
adaptations (LoRA), have emerged as a popular strategy for
adapting large-scale models to down-stream tasks by
performing parameter inference on lower-dimensional
subspaces. In this work, we investigate the suitability of
PEFT methods for subspace Bayesian inference in large-scale
Transformer-based vision models. We show that, indeed,
combining BitFit, DiffFit, LoRA, and CoLoRA, a novel
LoRA-inspired PEFT method, with Bayesian inference enables
more robust and reliable predictive performance in MDE.},
keywords = {Computer Vision and Pattern Recognition (cs.CV) (Other) /
Machine Learning (stat.ML) (Other) / FOS: Computer and
information sciences (Other)},
cin = {IAS-8 / IBG-1},
cid = {I:(DE-Juel1)IAS-8-20210421 / I:(DE-Juel1)IBG-1-20101118},
pnm = {5112 - Cross-Domain Algorithms, Tools, Methods Labs (ATMLs)
and Research Groups (POF4-511)},
pid = {G:(DE-HGF)POF4-5112},
typ = {PUB:(DE-HGF)25},
doi = {10.48550/ARXIV.2409.17085},
url = {https://juser.fz-juelich.de/record/1033893},
}