关于使用锚定训练视觉模型的研究
On the Use of Anchoring for Training Vision Models
AI总结：
本文系统研究锚定训练视觉模型，发现其易导致学习不良捷径的问题，并提出引入简单正则化器的新锚定训练协议，显著提升了模型的泛化能力和安全性。
摘要：
锚定是一种最近的、与架构无关的训练深度神经网络的原理，已被证明能显著改善不确定性估计、校准和外推能力。在本文中，我们系统地探索了锚定作为训练视觉模型的通用协议，为其训练和推理过程及其对泛化和安全性的影响提供了基本见解。尽管锚定具有前景，但我们发现锚定训练中存在一个关键问题，该问题可能导致学习不良捷径的风险增加，从而限制其泛化能力。为了解决这个问题，我们引入了一种新的锚定训练协议，该协议采用简单的正则化器来缓解此问题并显著增强泛化能力。我们在不同规模和复杂性的数据集和架构上实证评估了我们提出的方法，证明与标准训练协议相比，在泛化和安全指标方面取得了显著的性能提升。
英文摘要：
Anchoring is a recent, architecture-agnostic principle for training deep neural networks that has been shown to significantly improve uncertainty estimation, calibration, and extrapolation capabilities. In this paper, we systematically explore anchoring as a general protocol for training vision models, providing fundamental insights into its training and inference processes and their implications for generalization and safety. Despite its promise, we identify a critical problem in anchored training that can lead to an increased risk of learning undesirable shortcuts, thereby limiting its generalization capabilities. To address this, we introduce a new anchored training protocol that employs a simple regularizer to mitigate this issue and significantly enhances generalization. We empirically evaluate our proposed approach across datasets and architectures of varying scales and complexities, demonstrating substantial performance gains in generalization and safety metrics compared to the standard training protocol.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
