用参数高效方法提升视觉大模型的不确定性估计能力
Parameter-efficient Bayesian Neural Networks for Uncertainty-aware Depth Estimation
- 将低秩适配等参数高效技术与贝叶斯推理结合
- 在单目深度估计任务中实现更鲁棒的预测性能
- 适合关注安全关键场景可靠性的研究者
当前最先进的计算机视觉任务，如单目深度估计（MDE），严重依赖大规模基于Transformer的架构。然而，在安全关键领域应用时，需要可靠的预测表现和不确定性量化。虽然贝叶斯神经网络在理论上可满足这些需求，但其高维参数空间带来了挑战。参数高效微调（PEFT）方法，尤其是低秩适配（LoRA），通过在低维子空间中进行参数推断，已成为适应大规模模型到下游任务的流行策略。本文研究了PEFT方法在大规模Transformer视觉模型中用于子空间贝叶斯推断的适用性。结果表明，将BitFit、DiffFit、LoRA以及一种新型的受LoRA启发的CoLoRA方法与贝叶斯推断结合，可在单目深度估计任务中实现更稳健、更可靠的预测性能。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。