Visual words assignment via information-theoretic manifold embedding.
IEEE T. Cybernetics(2014)
摘要
Codebook-based learning provides a flexible way to extract the contents of an image in a data-driven manner for visual recognition. One central task in such frameworks is codeword assignment, which allocates local image descriptors to the most similar codewords in the dictionary to generate histogram for categorization. Nevertheless, existing assignment approaches, e.g., nearest neighbors strategy (hard assignment) and Gaussian similarity (soft assignment), suffer from two problems: 1) too strong Euclidean assumption and 2) neglecting the label information of the local descriptors. To address the aforementioned two challenges, we propose a graph assignment method with maximal mutual information (GAMI) regularization. GAMI takes the power of manifold structure to better reveal the relationship of massive number of local features by nonlinear graph metric. Meanwhile, the mutual information of descriptor-label pairs is ultimately optimized in the embedding space for the sake of enhancing the discriminant property of the selected codewords. According to such objective, two optimization models, i.e., inexact-GAMI and exact-GAMI, are respectively proposed in this paper. The inexact model can be efficiently solved with a closed-from solution. The stricter exact-GAMI nonparametrically estimates the entropy of descriptor-label pairs in the embedding space and thus leads to a relatively complicated but still trackable optimization. The effectiveness of GAMI models are verified on both the public and our own datasets.
更多查看译文
关键词
inexact-gami model,scene categorization,codeword assignment,nearest neighbors strategy,gaussian similarity,graph assignment method with maximal mutual information,gami regularization,learning (artificial intelligence),codebook-based learning,image descriptors,euclidean assumption,image recognition,information-theoretic manifold embedding,descriptor-label pairs,closed-from solution,feature extraction,nonlinear graph metric,exact-gami model,image contents extraction,computer vision,manifold embedding,graph theory,mutual information,visual words assignment,embedding space,visual recognition,image categorization
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络