Parameter-efficient Bayesian Neural Networks for Uncertainty-aware Depth Estimation

Autor:	Paul, Richard D., Quercia, Alessio, Fortuin, Vincent, Nöh, Katharina, Scharr, Hanno
Rok vydání:	2024
Předmět:	Computer Science - Computer Vision and Pattern Recognition Statistics - Machine Learning
Druh dokumentu:	Working Paper
Popis:	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. Comment: Presented at UnCV Workshop at ECCV'24
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2409.17085 Zobrazit plný text záznamu View this record from Arxiv