DLANet: A manifold-learning-based discriminative feature learning network for scene classification
文献类型：期刊论文
| 作者 | Feng Ziyong Z; Jin Lianwen; Tao Dapeng; Huang Shuangping |
| 刊名 | NEUROCOMPUTING
 |
| 出版日期 | 2015 |
| 英文摘要 | This paper presents Discriminative Locality Alignment Network (DLANet), a novel manifold-learning-based discriminative learnable feature, for wild scene classification. Based on a convolutional structure, DLANet learns the filters of multiple layers by applying DLA and exploits the block-wise histograms of the binary codes of feature maps to generate the local descriptors. A DLA layer maximizes the margin between the inter-class patches and minimizes the distance of the intra-class patches in the local region. In particular, we construct a two-layer DLANet by stacking two DLA layers and a feature layer. It is followed by a popular framework of scene classification, which combines Locality-constrained Linear Coding-Spatial Pyramid Matching (LLC-SPM) and linear Support Vector Machine (SVM). We evaluate DLANet on NYU Depth V1, Scene-15 and MIT Indoor-67. Experiments show that DLANet performs well on depth image. It outperforms the carefully tuned features, including SIFT and is also competitive to the other reported methods. (C) 2015 Elsevier B.V. All rights reserved |
| 收录类别 | SCI |
| 原文出处 | http://www.sciencedirect.com/science/article/pii/S0925231215000880 |
| 语种 | 英语 |
| 源URL | [http://ir.siat.ac.cn:8080/handle/172644/6681]  |
| 专题 | 深圳先进技术研究院_集成所 |
| 作者单位 | NEUROCOMPUTING |
| 推荐引用方式 GB/T 7714 | Feng Ziyong Z,Jin Lianwen,Tao Dapeng,et al. DLANet: A manifold-learning-based discriminative feature learning network for scene classification[J]. NEUROCOMPUTING,2015. |
| APA | Feng Ziyong Z,Jin Lianwen,Tao Dapeng,&Huang Shuangping.(2015).DLANet: A manifold-learning-based discriminative feature learning network for scene classification.NEUROCOMPUTING. |
| MLA | Feng Ziyong Z,et al."DLANet: A manifold-learning-based discriminative feature learning network for scene classification".NEUROCOMPUTING (2015). |
入库方式： OAI收割
来源：深圳先进技术研究院
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。