Concentric Circle Pooling in Deep Convolutional Networks for Remote Sensing Scene Classification

Qi, Kunlun; Guan, Qingfeng; Yang, Chao; Peng, Fei; Shen, Shengyu; Wu, Huayi

doi:10.3390/rs10060934

Cited by 46 publications

(38 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…All models were trained until the training loss converged. At the same time, for a fair comparison, the same ratios were applied in the following experiments according to the experimental settings in works [23][24][25]27,28,30,35,[53][54][55][56][57][63][64][65][66][67][68]. For the UC Merced Land-Use dataset, the 80% and 50% training ratio were set separately.…”

Section: Implementation Detailsmentioning

confidence: 99%

Remote Sensing Image Scene Classification Using CNN-CapsNet

2019

View full text Add to dashboard Cite

Remote sensing image scene classification is one of the most challenging problems in understanding high-resolution remote sensing images. Deep learning techniques, especially the convolutional neural network (CNN), have improved the performance of remote sensing image scene classification due to the powerful perspective of feature learning and reasoning. However, several fully connected layers are always added to the end of CNN models, which is not efficient in capturing the hierarchical structure of the entities in the images and does not fully consider the spatial information that is important to classification. Fortunately, capsule network (CapsNet), which is a novel network architecture that uses a group of neurons as a capsule or vector to replace the neuron in the traditional neural network and can encode the properties and spatial information of features in an image to achieve equivariance, has become an active area in the classification field in the past two years. Motivated by this idea, this paper proposes an effective remote sensing image scene classification architecture named CNN-CapsNet to make full use of the merits of these two models: CNN and CapsNet. First, a CNN without fully connected layers is used as an initial feature maps extractor. In detail, a pretrained deep CNN model that was fully trained on the ImageNet dataset is selected as a feature extractor in this paper. Then, the initial feature maps are fed into a newly designed CapsNet to obtain the final classification result. The proposed architecture is extensively evaluated on three public challenging benchmark remote sensing image datasets: the UC Merced Land-Use dataset with 21 scene categories, AID dataset with 30 scene categories, and the NWPU-RESISC45 dataset with 45 challenging scene categories. The experimental results demonstrate that the proposed method can lead to a competitive classification performance compared with the state-of-the-art methods.

show abstract

Section: Implementation Detailsmentioning

confidence: 99%

Remote Sensing Image Scene Classification Using CNN-CapsNet

2019

View full text Add to dashboard Cite

show abstract

“…In Equation 3, i, j ∈ [7,7] and d is the feature dimension. The number of channels in y is still 512.…”

Section: Multiplicative Fusion Of Deep Features Derived From Cnn and Sftmentioning

confidence: 99%

“…As we all know, scene classification (that classifies scene images into diverse categories according to the semantic information they contain), has been widely applied to land-cover or land-use classification of HRRSI [3][4][5][6]. Nevertheless, it is difficult to classify the scene images effectively due to various land-cover objects and high intra-class diversity [7,8]. Therefore, features that are used to describe scene images are important for scene classification of HRRSI.…”

Section: Introductionmentioning

confidence: 99%

RETRACTED: Attention-Based Deep Feature Fusion for the Scene Classification of High-Resolution Remote Sensing Images

Zhu

Yan

et al. 2019

Remote Sensing

View full text Add to dashboard Cite

Scene classification of highresolution remote sensing images (HRRSI) is one of the most important means of landcover classification. Deep learning techniques, especially the convolutional neural network (CNN) have been widely applied to the scene classification of HRRSI due to the advancement of graphic processing units (GPU). However, they tend to extract features from the whole images rather than discriminative regions. The visual attention mechanism can force the CNN to focus on discriminative regions, but it may suffer from the influence of intraclass diversity and repeated texture. Motivated by these problems, we propose an attention-based deep feature fusion (ADFF) framework that constitutes three parts, namely attention maps generated by Gradientweighted Class Activation Mapping (GradCAM), a multiplicative fusion of deep features and the centerbased cross-entropy loss function. First of all, we propose to make attention maps generated by GradCAM as an explicit input in order to force the network to concentrate on discriminative regions. Then, deep features derived from original images and attention maps are proposed to be fused by multiplicative fusion in order to consider both improved abilities to distinguish scenes of repeated texture and the salient regions. Finally, the centerbased cross-entropy loss function that utilizes both the cross-entropy loss and center loss function is proposed to backpropagate fused features so as to reduce the effect of intraclass diversity on feature representations. The proposed ADFF architecture is tested on three benchmark datasets to show its performance in scene classification. The experiments confirm that the proposed method outperforms most competitive scene classification methods with an average overall accuracy of 94% under different training ratios.

show abstract

“…(iii) RSSC by extracting intermediate level features to prevent overfitting and performing the fusion by analyzing canonical correlation to obtain more powerful discriminative features [22,24]. (iv) RSSC by concentric circle pooling to avoid rotation invariant problem [25].…”

Section: Recent Research Work In Rssc[21-25]mentioning

confidence: 99%

Advances in Scene Classification of Remotely Sensed High Resolution Images and the Existing Datasets

G¹,

Gayathri²

2019

IJITEE

View full text Add to dashboard Cite

Research on Scene classification of remotely sensed images has shown a significant improvement in the recent years as it is used in various applications such as urban planning, urban mapping, management of natural resources, precision agriculture, detecting targets etc. The recent advancement of intelligent earth observation system has led to the generation of high resolution remote sensing images in terms of spatial, spectral and temporal resolutions which in turn helped the researchers to improve the performance of Land Use Land Class (LULC) Classification Techniques to a higher level. With the usage of different deep learning architecture and the availability of various high resolution image datasets, the field of Remote Sensing Scene Classification of high resolution (RSSCHR) images has shown tremendous improvement in the past decade. In this paper we present the different publicly available datasets , various scene classification methods and the future research scope of remotely sensed high resolution images.

show abstract

Concentric Circle Pooling in Deep Convolutional Networks for Remote Sensing Scene Classification

Cited by 46 publications

References 53 publications

Remote Sensing Image Scene Classification Using CNN-CapsNet

Remote Sensing Image Scene Classification Using CNN-CapsNet

RETRACTED: Attention-Based Deep Feature Fusion for the Scene Classification of High-Resolution Remote Sensing Images

Advances in Scene Classification of Remotely Sensed High Resolution Images and the Existing Datasets

Contact Info

Product

Resources

About