智能多视图测试时增强
Intelligent Multi-View Test Time Augmentation
AI总结：
提出一种基于预测不确定性的两阶段智能多视图 TTA 算法，为各类别选择增强并判断是否应用，在多数据集和架构上较单视图方法平均提升准确率 1.73%。
摘要：
在本研究中，我们提出了一种智能测试时增强（Test Time Augmentation，TTA）算法，旨在提高图像分类模型面对视角变化时的鲁棒性和准确率。与不加区分地应用增强的传统 TTA 方法不同，我们的方法基于预测不确定性指标智能选择最优增强。该选择通过两阶段过程实现：第一阶段通过评估不确定性水平，确定每个类别的最优增强；第二阶段采用不确定性阈值来判断何时应用 TTA 会更有利。这一方法进展确保增强对分类的贡献比在整个数据集上统一应用更加有效。在多个数据集和神经网络架构上的实验验证了我们的方法，与使用单视图图像的方法相比，准确率平均提升 1.73%。本研究强调了自适应、具备不确定性感知能力的 TTA 在视角变化存在时提升图像分类鲁棒性方面的潜力，并为进一步探索智能增强策略铺平了道路。
英文摘要：
In this study, we introduce an intelligent Test Time Augmentation (TTA) algorithm designed to enhance the robustness and accuracy of image classification models against viewpoint variations. Unlike traditional TTA methods that indiscriminately apply augmentations, our approach intelligently selects optimal augmentations based on predictive uncertainty metrics. This selection is achieved via a two-stage process: the first stage identifies the optimal augmentation for each class by evaluating uncertainty levels, while the second stage implements an uncertainty threshold to determine when applying TTA would be advantageous. This methodological advancement ensures that augmentations contribute to classification more effectively than a uniform application across the dataset. Experimental validation across several datasets and neural network architectures validates our approach, yielding an average accuracy improvement of 1.73% over methods that use single-view images. This research underscores the potential of adaptive, uncertainty-aware TTA in improving the robustness of image classification in the presence of viewpoint variations, paving the way for further exploration into intelligent augmentation strategies.
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。
