Parameter-efficient Bayesian Neural Networks for Uncertainty-aware Depth Estimation
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Bayesian InferenceDepth EstimationMonocular Depth Estimationparameter-efficient fine-tuningUncertainty QuantificationSimilar Papers 제목 키워드 기반
Bayesian inversion of GPR waveforms for sub-surface material characterization: an uncertainty-aware retrieval of soil moisture and overlaying biomass properties
Accurate estimation of sub-surface properties such as moisture content and depth of soil and vegetation layers is crucial for applications spanning sub-surface condition monitoring, precision agriculture, and effective w…
Decision MakingGPRparameter estimationBayesian Deep Basis Fitting for Depth Completion with Uncertainty
In this work we investigate the problem of uncertainty estimation for image-guided depth completion. We extend Deep Basis Fitting (DBF) for depth completion within a Bayesian evidence framework to provide calibrated per-…
Depth CompletionDepth EstimationDepth PredictionUM-Depth : Uncertainty Masked Self-Supervised Monocular Depth Estimation with Visual Odometry
Monocular depth estimation has been increasingly adopted in robotics and autonomous driving for its ability to infer scene geometry from a single camera. In self-supervised monocular depth estimation frameworks, the netw…
Monocular Depth EstimationAutonomous DrivingPose EstimationVisual OdometryEvidMTL: Evidential Multi-Task Learning for Uncertainty-Aware Semantic Surface Mapping from Monocular RGB Images
For scene understanding in unstructured environments, an accurate and uncertainty-aware metric-semantic mapping is required to enable informed action selection by autonomous systems. Existing mapping methods often suffer…
Depth EstimationDepth PredictionMulti-Task LearningScene Understanding+2Beyond Feature Fusion: Contextual Bayesian PEFT for Multimodal Uncertainty Estimation
We introduce CoCo-LoRA, a multimodal, uncertainty-aware parameter-efficient fine-tuning method for text prediction tasks accompanied by audio context. Existing PEFT approaches such as LoRA are efficient but typically det…
parameter-efficient fine-tuning