Fisher kernels derived from stochastic probabilistic models such as restricted and deep Boltzmann machines have shown competitive visual classification results in comparison to widely popular deep discriminative models. This genre of Fisher kernels bridges the gap between shallow and deep learning paradigm by inducing the characteristics of deep architecture into Fisher kernel, further deployed for classification in discriminative classifiers. Despite their success, the memory and computational costs of Fisher vectors do not make them amenable for large-scale visual retrieval and classification tasks. This study introduces a novel feature selection technique inspired from the functional characteristics of neural architectures for learning discriminative feature representations to boost the performance of Fisher kernels against deep discriminative models. The proposed technique condenses the large dimensional Fisher features for kernel learning and shows improvement in its classification performance and storage cost on leading benchmark data sets. A comparison of the proposed method with other state-of-the-art feature selection techniques is made to demonstrate its performance supremacy as well as time complexity required to learn in reduced Fisher space.

中文翻译：

---

多样化的Fisher核：在Fisher特征中进行编码判别以竞争深度神经模型进行视觉分类任务

与广泛流行的深度判别模型相比，从随机概率模型（例如受限和深度Boltzmann机）获得的Fisher核显示出竞争性的视觉分类结果。Fisher核的这种类型弥合了浅 和 深通过将深度架构的特征引入Fisher核来学习范式，并进一步部署用于区分性分类器中的分类。尽管获得了成功，费舍尔向量的存储和计算成本仍无法满足大规模视觉检索和分类任务的需要。这项研究引入了一种新颖的特征选择技术，该技术受神经体系结构的功能特性启发，用于学习区分特征表示，以提高Fisher核针对深度区分模型的性能。所提出的技术浓缩了大尺寸费希尔功能用于内核学习，并显示其分类性能和领先基准数据集的存储成本得到了改善。将提出的方法与其他最新的特征选择技术进行了比较，以证明其性能优越性以及在缩减的Fisher空间中学习所需的时间复杂性。