Name
Abstract | ||
|---|---|---|
Objects in scenes are thought to be important for scene recognition. In this paper, we propose to utilize scene-specific objects represented by deep features for scene categorization. Our approach combines benefits of deep learning and Latent Support Vector Machine (LSVM) to train a set of scene-specific object models for each scene category. Specifically, we first use deep Convolutional Neural Networks (CNNs) pre-trained on the large-scale object-centric image database ImageNet to learn rich object features and a large number of general object concepts. Then, the pre-trained CNNs is adopted to extract features from images in the target dataset, and initialize the learning of scene-specific object models for each scene category. After initialization, the scene-specific object models are obtained by alternating between searching over the most representative and discriminative regions of images in the target dataset and training linear SVM classifiers based on obtained region features. As a result, for each scene category a set of object models that are representative and discriminative can be acquired. We use them to perform scene categorization. In addition, to utilize global structure information of scenes, we use another CNNs pre-trained on the large-scale scene-centric database Places to capture structure information of scene images. By combining objects and structure information for scene categorization, we show superior performances to state-of-the-art approaches on three public datasets, i.e. MIT-indoor, UIUC-sports and SUN. Experiment results demonstrated the effectiveness of the proposed method. |
Year | DOI | Venue |
|---|---|---|
2017 | 10.1142/S0218001417550138 | INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE |
Keywords | Field | DocType |
Scene categorization, scene-specific object, convolutional neural networks, latent support vector machine | Categorization,Pattern recognition,Convolutional neural network,Support vector machine,Artificial intelligence,Image database,Deep learning,Initialization,Discriminative model,Mathematics,Linear svm | Journal |
Volume | Issue | ISSN |
31 | 9 | 0218-0014 |
Citations | PageRank | References |
3 | 0.37 | 33 |
Authors | ||
1 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Shuang Bai | 1 | 45 | 8.01 |