Improving Spatial Feature Representation from Aerial Scenes by Using Convolutional Networks

Nogueira, Keiller; Miranda, Waner O.; Santos, Jefersson A. dos

doi:10.1109/sibgrapi.2015.39

Cited by 43 publications

(29 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…PatreoNet, presented in [15], is a network capable of learning specific spatial features from remote sensing images, without any pre-processing step or descriptor evaluation. This network, which architecture can be seen in Figure 7a, has 3 convolutional layers, 3 pooling ones and 3 fully-connected ones (considering the softmax).…”

Section: Patreonetmentioning

confidence: 99%

“…Recently, deep learning has become the new state-of-the-art solution for visual recognition. Given its success, deep learning has been intensively used in several distinct tasks of different domains [12,13], including remote sensing [14,15,16]. In remote sensing, the use of deep learning is growing very quickly, since it has a natural ability to effectively encode spectral and spatial information based mainly on the data itself.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Towards better exploiting convolutional neural networks for remote sensing scene classification

Nogueira

Penatti²,

Santos

2017

Pattern Recognition

Self Cite

796

476

View full text Add to dashboard Cite

8We present an analysis of three possible strategies for exploiting the power of existing convolutional neural net-9 works (ConvNets or CNNs) in different scenarios from the ones they were trained: full training, fine tuning, and 10 using ConvNets as feature extractors. In many applications, especially including remote sensing, it is not feasible to 11 fully design and train a new ConvNet, as this usually requires a considerable amount of labeled data and demands 12 high computational costs. Therefore, it is important to understand how to better use existing ConvNets. We perform 13 experiments with six popular ConvNets using three remote sensing datasets. We also compare ConvNets in each 14 strategy with existing descriptors and with state-of-the-art baselines. Results point that fine tuning tends to be the best 15 performing strategy. In fact, using the features from the fine-tuned ConvNet with linear SVM obtains the best results. 16 We also achieved state-of-the-art results for the three datasets used.

show abstract

Section: Patreonetmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Towards better exploiting convolutional neural networks for remote sensing scene classification

Nogueira

Penatti²,

Santos

2017

Pattern Recognition

Self Cite

796

476

View full text Add to dashboard Cite

show abstract

“…It can be also noted that the proposed method outperforms other deep models, such as GoogLeNet [7] which obtains 97.10%, VGG-VD16-1 st -FC+Aug [23] which obtains 96.88%, SPP-net+MKL [29] which obtains 96.38%, and MCNN [21] which obtains 96.66%. For Brazilian Coffee Scene dataset, the proposed method also obtains 91.24% outperforms 88.46% which is obtained by LQPCANet [37], 85.36% by VGG16 [22], 89.79% by ConvNet [38], 90.94% by CaffeNet [7] and 91.13% by D-DSML-CaffeNet [9]. For Google dataset, the proposed method obtains 92.04% which is better than 82.81% by TF-CNN [39], 89.88% by RDSG-CNN [39], 87.68% by Fine-tuned CaffeNet.…”

Section: Comparisons With the Most Recent Methodsmentioning

confidence: 86%

Joint Learning of the Center Points and Deep Metrics for Land-Use Classification in Remote Sensing

Gong

Zhong

et al. 2019

Remote Sensing

View full text Add to dashboard Cite

Deep learning methods, especially convolutional neural networks (CNNs), have shown remarkable ability for remote sensing scene classification. However, the traditional training process of standard CNNs only takes the point-wise penalization of the training samples into consideration, which usually makes the learned CNNs sub-optimal especially for remote sensing scenes with large intra-class variance and low inter-class variance. To address this problem, deep metric learning, which incorporates the metric learning into the deep model, is used to maximize the inter-class variance and minimize the intra-class variance for better representation. This work introduces structured metric learning for remote sensing scene representation, a special deep metric learning which can take full advantage of the training batch. However, the deep metrics only consider the pairwise correlation between the training samples, and ignores the classwise correlation from the class view. To take the classwise penalization into consideration, this work defines the center points of the learned features of each class in the training process to represent the class. Through increasing the variance between different center points and decreasing the variance between the learned features from each class and the corresponding center point, the representational ability can be further improved. Therefore, this work develops a novel center-based structured metric learning to take advantage of both the deep metrics and the center points. Finally, joint supervision of the cross-entropy loss and the center-based structured metric learning is developed for the land-use classification in remote sensing. It can joint learn the center points and the deep metrics to take advantage of the point-wise, the pairwise, and the classwise correlation. Experiments are conducted over three real-world remote sensing scene datasets, namely UC Merced Land-Use dataset, Brazilian Coffee Scene dataset, and Google dataset. The classification performance can achieve 97.30%, 91.24%, and 92.04% with the proposed method over the three datasets which are better than other state-of-the-art methods under the same experimental setups. The results demonstrate that the proposed method can improve the representational ability for the remote sensing scenes.

show abstract

“…Methods from this area, commonly represented as multilayered neural networks, are able to learn both the features and the classifier in a unified manner, adjusting themselves to better represent the characteristics of the data and their labels. A specific deep learning method, called Convolutional (Neural) Networks (ConvNets) [9], is the most popular for learning visual features in computer vision applications, including remote sensing [10], [11]. This type of network relies on the natural stationary property of an image, i.e., the statistics of one part of the image are assumed to be the same as those of any other part.…”

Section: Introductionmentioning

confidence: 99%

Exploiting ConvNet Diversity for Flooding Identification

Nogueira

Fadel

Dourado

et al. 2018

IEEE Geosci. Remote Sensing Lett.

Self Cite

View full text Add to dashboard Cite

Flooding is the world's most costly type of natural disaster in terms of both economic losses and human causalities. A first and essential procedure towards flood monitoring is based on identifying the area most vulnerable to flooding, which gives authorities relevant regions to focus. In this work, we propose several methods to perform flooding identification in highresolution remote sensing images using deep learning. Specifically, some proposed techniques are based upon unique networks, such as dilated and deconvolutional ones, while other was conceived to exploit diversity of distinct networks in order to extract the maximum performance of each classifier. Evaluation of the proposed methods were conducted in a high-resolution remote sensing dataset. Results show that the proposed algorithms outperformed state-of-the-art baselines, providing improvements ranging from 1 to 4% in terms of the Jaccard Index.

show abstract

Improving Spatial Feature Representation from Aerial Scenes by Using Convolutional Networks

Cited by 43 publications

References 24 publications

Towards better exploiting convolutional neural networks for remote sensing scene classification

Towards better exploiting convolutional neural networks for remote sensing scene classification

Joint Learning of the Center Points and Deep Metrics for Land-Use Classification in Remote Sensing

Exploiting ConvNet Diversity for Flooding Identification

Contact Info

Product

Resources

About