%0 Electronic Article
%A Paul, Richard D.
%A Quercia, Alessio
%A Fortuin, Vincent
%A Nöh, Katharina
%A Scharr, Hanno
%T Parameter-efficient Bayesian Neural Networks for Uncertainty-aware Depth Estimation
%I arXiv
%M FZJ-2024-06731
%D 2024
%Z Presented as an Extended Abstract at the 3rd Workshop on Uncertainty Quantification for Computer Vision at the ECCV'24.
%X 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.
%K Computer Vision and Pattern Recognition (cs.CV) (Other)
%K Machine Learning (stat.ML) (Other)
%K FOS: Computer and information sciences (Other)
%F PUB:(DE-HGF)25
%9 Preprint
%R 10.48550/ARXIV.2409.17085
%U https://juser.fz-juelich.de/record/1033893