An Attribute-Based High-Level Image Representation for Scene Classification

被引:2
作者
Liu, Wenhua [1 ]
Li, Yidong [1 ]
Wu, Qi [2 ]
机构
[1] Beijing Jiaotong Univ, Beijing 100044, Peoples R China
[2] Univ Adelaide, Adelaide, SA 5005, Australia
来源
IEEE ACCESS | 2019年 / 7卷
基金
美国国家科学基金会;
关键词
Scene classification; attribute representation; convolutional neural network; high-level image representation; OBJECT; MODEL; ALGORITHMS; FEATURES; SHAPE; TREE;
D O I
10.1109/ACCESS.2018.2886597
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Scene classification is increasingly popular due to its extensive usage in many real-world applications such as object detection, image retrieval, and so on. Traditionally, the low-level hand-crafted image representations are adopted to describe the scene images. However, they usually fail to detect semantic features of visual concepts, especially in handling complex scenes. In this paper, we propose a novel high-level image representation which utilizes image attributes as features for scene classification. More specifically, the attributes of each image are firstly extracted by a deep convolution neural network (CNN), which is trained to be a multi-label classifier by minimizing an element-wise logistic loss function. The process of generating attributes can reduce the "semantic gap" between the low-level feature representation and the high level scene meaning. Based on the attributes, we then build a system to discover semantically meaningful descriptions of the scene classes. Extensive experiments on four large-scale scene classification datasets show that our proposed algorithm considerably outperforms other state-of-the-art methods.
引用
收藏
页码:4629 / 4640
页数:12
相关论文
共 66 条
[1]   Comparison of classification algorithms to predict outcomes of feedlot cattle identified and treated for bovine respiratory disease [J].
Amrine, David E. ;
White, Brad J. ;
Larson, Robert L. .
COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2014, 105 :9-19
[2]  
[Anonymous], P 3 INT C LEARNING R
[3]  
[Anonymous], 2015, CVPR, DOI DOI 10.48550/ARXIV.1411.4952
[4]   Shape matching and object recognition using shape contexts [J].
Belongie, S ;
Malik, J ;
Puzicha, J .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2002, 24 (04) :509-522
[5]  
Bo L., 2011, Neural Information Processing Systems, P2115
[6]   Poselets: Body Part Detectors Trained Using 3D Human Pose Annotations [J].
Bourdev, Lubomir ;
Malik, Jitendra .
2009 IEEE 12TH INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2009, :1365-1372
[7]   Remote Sensing Image Classification Using Attribute Filters Defined Over the Tree of Shapes [J].
Cavallaro, Gabriele ;
Dalla Mura, Mauro ;
Benediktsson, Jon Atli ;
Plaza, Antonio .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2016, 54 (07) :3899-3911
[8]   Unsupervised Feature Learning for Aerial Scene Classification [J].
Cheriyadat, Anil M. .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2014, 52 (01) :439-451
[9]   Histograms of oriented gradients for human detection [J].
Dalal, N ;
Triggs, B .
2005 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOL 1, PROCEEDINGS, 2005, :886-893
[10]   Large-scale multi-task image labeling with adaptive relevance discovery and feature hashing [J].
Deng, Cheng ;
Liu, Xianglong ;
Mu, Yadong ;
Li, Jie .
SIGNAL PROCESSING, 2015, 112 :137-145