Spatial modeling via feature co-pooling and SG grafting

• Published in: Neurocomputing (Amsterdam) Vol. 139; pp. 415 - 422
• Main Authors: Liu, Feng, Huang, Yongzhen, Wang, Liang, Yang, Wankou, Sun, Changyin
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier B.V 02.09.2014; Elsevier
• Subjects: Algorithms; Applied sciences; Artificial intelligence; Computer science; control theory; systems; Data processing. List processing. Character string processing; Exact sciences and technology; Feature selection; Grafting; Memory organisation. Data processing; Object classification; Pattern recognition. Digital image processing. Computational geometry; Representations; Software; Spatial modeling; Visual; Volatile organic compounds; Object classification; Feature selection; Spatial modeling; Dimensionality; Spatial cognition; Modeling; Experimental result; Sport; Visual stimulus; Spatial distribution; Visual cue; Classification; Greedy algorithm; Selection criterion; Sparse representation; Localization; Cooccurrence analysis; Field study
• ISSN: 0925-2312; 1872-8286
• DOI: 10.1016/j.neucom.2014.02.015

Spatial information is an important cue for visual object analysis. Various studies in this field have been conducted. However, they are either too rigid or too fragile to efficiently utilize such information. In this paper, we propose to model the distribution of objects׳ local appearance patterns by using their co-occurrence at different spatial locations. In order to represent such a distribution, we propose a flexible framework called spatial feature co-pooling, with which the relations between patterns are discovered. As the final representation resulted from our framework is of high dimensionality, we propose a semi-greedy (SG) grafting algorithm to select the most discriminative features. Experimental results on the CIFAR 10, UIUC Sports and VOC 2007 datasets show that our method is effective and comparable with the state-of-art algorithms.