协调统计和空间稀疏性以实现鲁棒图像和图像集分类
Reconciliation of Statistical and Spatial Sparsity For Robust Image and Image-Set Classification
摘要:
与经典的基于特征的方法相比,最近的图像分类算法通过从大规模数据集中学习深度特征,取得了显着更好的结果。然而,图像分类在实际应用中仍然存在各种挑战,如对噪声图像或图像集查询进行分类,以及在有限规模数据集上训练深度图像分类模型。代替应用通用深度特征,基于模型的方法对于鲁棒图像和图像集分类任务可以更有效和数据高效,因为各种图像先验被用于对集间和集内数据变化进行建模,同时防止过拟合。在这项工作中,我们提出了一种新的联合统计和空间稀疏表示,被称为\textit{J3S},建模的图像或图像集的数据进行分类,通过调和他们的局部补丁结构和全球高斯分布映射到黎曼流形。据我们所知,没有工作到目前为止,利用全球统计和本地补丁结构联合通过联合稀疏表示。我们提出了解决联合稀疏编码问题的J3 S模型的基础上,通过耦合的局部和全局图像表示使用联合稀疏。学习的J3 S模型用于鲁棒的图像和图像集分类。实验结果表明,基于J3 S的图像分类方法在FMD、UIUC、ETH-80和YTC数据库上的分类性能优于目前流行的或最先进的同类方法。
英文摘要:
Recent image classification algorithms, by learning deep features from large-scale datasets, have achieved significantly better results comparing to the classic feature-based approaches. However, there are still various challenges of image classifications in practice, such as classifying noisy image or image-set queries and training deep image classification models over the limited-scale dataset. Instead of applying generic deep features, the model-based approaches can be more effective and data-efficient for robust image and image-set classification tasks, as various image priors are exploited for modeling the inter- and intra-set data variations while preventing over-fitting. In this work, we propose a novel Joint Statistical and Spatial Sparse representation, dubbed \textit{J3S}, to model the image or image-set data for classification, by reconciling both their local patch structures and global Gaussian distribution mapped into Riemannian manifold. To the best of our knowledge, no work to date utilized both global statistics and local patch structures jointly via joint sparse representation. We propose to solve the joint sparse coding problem based on the J3S model, by coupling the local and global image representations using joint sparsity. The learned J3S models are used for robust image and image-set classification. Experiments show that the proposed J3S-based image classification scheme outperforms the popular or state-of-the-art competing methods over FMD, UIUC, ETH-80 and YTC databases.
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。