Active Learning with Gaussian Processes for Object Categorization
Active Learning with Gaussian Processes for Object Categorization
复制标题
DOI：
10.1109/iccv.2007.4408844
复制
发表时间：
2007-12
期刊：
影响因子：
--
通讯作者：
Ashish Kapoor;K. Grauman;R. Urtasun;Trevor Darrell
中科院分区：
文献类型：
--
作者：
Ashish Kapoor;K. Grauman;R. Urtasun;Trevor Darrell
用于视觉对象类别识别的判别方法通常是非概率的，预测类别标签，但不直接提供不确定性的估计。高斯过程（GPs）是具有显式不确定性模型的强大回归技术;我们在这里展示了基于金字塔匹配核（PMK）定义协方差函数的高斯过程如何用于概率对象类别识别。GP提供的不确定性模型提供了测试点的置信度估计，并且自然允许主动学习范例，其中点被最佳地选择用于交互式标记。我们推导出一种新的主动类别学习方法的基础上，我们的概率回归模型，并表明分类性能的显着提高是可能的，特别是当一个类别的训练数据量最终是非常小的。
Discriminative methods for visual object category recognition are typically non-probabilistic, predicting class labels but not directly providing an estimate of uncertainty. Gaussian Processes (GPs) are powerful regression techniques with explicit uncertainty models; we show here how Gaussian Processes with covariance functions defined based on a Pyramid Match Kernel (PMK) can be used for probabilistic object category recognition. The uncertainty model provided by GPs offers confidence estimates at test points, and naturally allows for an active learning paradigm in which points are optimally selected for interactive labeling. We derive a novel active category learning method based on our probabilistic regression model, and show that a significant boost in classification performance is possible, especially when the amount of training data for a category is ultimately very small.