期刊
IEEE TRANSACTIONS ON IMAGE PROCESSING
卷 25, 期 7, 页码 3372-3383出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIP.2016.2567076
关键词
Scene classification; convolutional neural networks; indoor object dataset; feature representations; dictionary learning; sparse coding
资金
- University of Western Australia
- Australian Research Council [DE120102960, DP110102166, DP150100294]
Indoor scene recognition is a multi-faceted and challenging problem due to the diverse intra-class variations and the confusing inter-class similarities that characterize such scenes. This paper presents a novel approach that exploits rich mid-level convolutional features to categorize indoor scenes. Traditional convolutional features retain the global spatial structure, which is a desirable property for general object recognition. We, however, argue that the structure-preserving property of the convolutional neural network activations is not of substantial help in the presence of large variations in scene layouts, e.g., in indoor scenes. We propose to transform the structured convolutional activations to another highly discriminative feature space. The representation in the transformed space not only incorporates the discriminative aspects of the target data set but also encodes the features in terms of the general object categories that are present in indoor scenes. To this end, we introduce a new large-scale data set of 1300 object categories that are commonly present in indoor scenes. Our proposed approach achieves a significant performance boost over the previous state-of-the-art approaches on five major scene classification data sets.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据