基于混合高斯-拉普拉斯混合模型的Fisher矢量图像标注
Fisher Vectors Derived from Hybrid Gaussian-Laplacian Mixture Models for Image Annotation
摘要:
在传统的对象识别管道中,描述符在图像上被密集地采样,汇集成高维非线性表示,然后传递到分类器。近年来,Fisher Vectors已被经验证明是各种应用的领先表示。Fisher向量通常被视为描述符的对数似然相对于高斯混合模型(GMM)的参数的梯度。基于对不同数据集应用不同分布的假设,我们提出了另外两个混合模型,并推导了它们的期望最大化和Fisher向量表达式。第一种是基于拉普拉斯分布的拉普拉斯混合模型(LMM)。第二个混合模型是一个混合高斯-拉普拉斯混合模型(HGLMM),它是基于高斯和拉普拉斯分布的加权几何平均值。对于后者,期望最大化算法的一个有趣的特性是,在最大化步骤中,每个分量中的每个维度都被选择为高斯或拉普拉斯。最后,通过使用新的Fisher向量从HGLSTOM派生,我们实现了国家的最先进的结果,图像注释和图像搜索的一句话的任务。
英文摘要:
In the traditional object recognition pipeline, descriptors are densely sampled over an image, pooled into a high dimensional non-linear representation and then passed to a classifier. In recent years, Fisher Vectors have proven empirically to be the leading representation for a large variety of applications. The Fisher Vector is typically taken as the gradients of the log-likelihood of descriptors, with respect to the parameters of a Gaussian Mixture Model (GMM). Motivated by the assumption that different distributions should be applied for different datasets, we present two other Mixture Models and derive their Expectation-Maximization and Fisher Vector expressions. The first is a Laplacian Mixture Model (LMM), which is based on the Laplacian distribution. The second Mixture Model presented is a Hybrid Gaussian-Laplacian Mixture Model (HGLMM) which is based on a weighted geometric mean of the Gaussian and Laplacian distribution. An interesting property of the Expectation-Maximization algorithm for the latter is that in the maximization step, each dimension in each component is chosen to be either a Gaussian or a Laplacian. Finally, by using the new Fisher Vectors derived from HGLMMs, we achieve state-of-the-art results for both the image annotation and the image search by a sentence tasks.
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。