Diversity-Promoting Deep Structural Metric Learning for Remote Sensing Scene Classification

Gong, Zhiqiang; Zhong, Ping; Yu, Yang; Hu, Weidong

doi:10.1109/tgrs.2017.2748120

Cited by 87 publications

(58 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Liu and Huang (Liu and Huang 2018) proposed a framework based on triplet networks to achieve high accuracy in classifying high resolution satellite imagery. Gong et. al.…”

Section: Introductionmentioning

confidence: 99%

DeepSat V2: feature augmented convolutional neural nets for satellite image classification

Basu

Ganguly

et al. 2019

Remote Sensing Letters

View full text Add to dashboard Cite

Satellite image classification is a challenging problem that lies at the crossroads of remote sensing, computer vision, and machine learning. Due to the high variability inherent in satellite data, most of the current object classification approaches are not suitable for handling satellite datasets. The progress of satellite image analytics has also been inhibited by the lack of a single labeled high-resolution dataset with multiple class labels.In a preliminary version of this work, we introduced two new high resolution satellite imagery datasets (SAT-4 and SAT-6) and proposed DeepSat framework for classification based on "handcrafted" features and a deep belief network (DBN). The present paper is an extended version, we present an end-to-end framework leveraging an improved architecture that augments a convolutional neural network (CNN) with handcrafted features (instead of using DBN-based architecture) for classification.Our framework, having access to fused spatial information obtained from handcrafted features as well as CNN feature maps, have achieved accuracies of 99.90% and 99.84% respectively, on SAT-4 and SAT-6, surpassing all the other state-ofthe-art results. A statistical analysis based on Distribution Separability Criterion substantiates the robustness of our approach in learning better representations for satellite imagery.

show abstract

“…Liu and Huang (Liu and Huang 2018) proposed a framework based on triplet networks to achieve high accuracy in classifying high resolution satellite imagery. Gong et. al.…”

Section: Introductionmentioning

confidence: 99%

DeepSat V2: feature augmented convolutional neural nets for satellite image classification

Basu

Ganguly

et al. 2019

Remote Sensing Letters

View full text Add to dashboard Cite

show abstract

“…Accuracy(%) SIFT [9] 82.83 BIC [8] 87.03 ± 1.07 BOVW [8] 80.50 OverFeat L +OverFeat S [8] 83.04 ± 2.00 CNN-1 [19] 86.00 MARTA GANs (without data augmentation) [1], [18] 87.69 UCFFN [1] 87.83 Proposed Method 87.74 ± 1.59…”

Section: Methodsmentioning

confidence: 99%

“…Deep learning-based method, such as Convolutional Neural Network (CNN), Deep Belief Network (DBN), have shown their impressive performance for remote sensing scene representation [8]. Among these methods, CNNs which can extract both the local and global features from the scenes have been widely used in the literature of remote sensing [8], [9]. As Fig.…”

Section: A General Convolutional Neural Network (Cnn)mentioning

confidence: 99%

An End-to-End Joint Unsupervised Learning of Deep Model and Pseudo-Classes for Remote Sensing Scene Representation

Gong

Zhong

et al. 2019

2019 International Joint Conference on Neural Networks (IJCNN)

Self Cite

View full text Add to dashboard Cite

This work develops a novel end-to-end deep unsupervised learning method based on convolutional neural network (CNN) with pseudo-classes for remote sensing scene representation. First, we introduce center points as the centers of the pseudo classes and the training samples can be allocated with pseudo labels based on the center points. Therefore, the CNN model, which is used to extract features from the scenes, can be trained supervised with the pseudo labels. Moreover, a pseudo-center loss is developed to decrease the variance between the samples and the corresponding pseudo center point. The pseudo-center loss is important since it can update both the center points with the training samples and the CNN model with the center points in the training process simultaneously. Finally, joint learning of the pseudo-center loss and the pseudo softmax loss which is formulated with the samples and the pseudo labels is developed for unsupervised remote sensing scene representation to obtain discriminative representations from the scenes. Experiments are conducted over two commonly used remote sensing scene datasets to validate the effectiveness of the proposed method and the experimental results show the superiority of the proposed method when compared with other state-of-the-art methods.

show abstract

“…Other group of works embedded a metric learning regularizer for better representation of remote sensing images [7,24]. Cheng at el.…”

Section: Related Workmentioning

confidence: 99%

“…This term maps image pairs that belong to the same class to be as close as possible, while images of different classes are mapped to be as farther as possible. In [24], the authors considered the contextual information between different pairs during training and proposed a diversity regularization method to reduce the redundancy of learned parameters.…”

Section: Related Workmentioning

confidence: 99%

Simple Yet Effective Fine-Tuning of Deep CNNs Using an Auxiliary Classification Loss for Remote Sensing Scene Classification

et al. 2019

View full text Add to dashboard Cite

The current literature of remote sensing (RS) scene classification shows that state-of-the-art results are achieved using feature extraction methods, where convolutional neural networks (CNNs) (mostly VGG16 with 138.36 M parameters) are used as feature extractors and then simple to complex handcrafted modules are added for additional feature learning and classification, thus coming back to feature engineering. In this paper, we revisit the fine-tuning approach for deeper networks (GoogLeNet and Beyond) and show that it has not been well exploited due to the negative effect of the vanishing gradient problem encountered when transferring knowledge to small datasets. The aim of this work is two-fold. Firstly, we provide best practices for fine-tuning pre-trained CNNs using the root-mean-square propagation (RMSprop) method. Secondly, we propose a simple yet effective solution for tackling the vanishing gradient problem by injecting gradients at an earlier layer of the network using an auxiliary classification loss function. Then, we fine-tune the resulting regularized network by optimizing both the primary and auxiliary losses. As for pre-trained CNNs, we consider in this work inception-based networks and EfficientNets with small weights: GoogLeNet (7 M) and EfficientNet-B0 (5.3 M) and their deeper versions Inception-v3 (23.83 M) and EfficientNet-B3 (12 M), respectively. The former networks have been used previously in the context of RS and yielded low accuracies compared to VGG16, while the latter are new state-of-the-art models. Extensive experimental results on several benchmark datasets reveal clearly that if fine-tuning is done in an appropriate way, it can settle new state-of-the-art results with low computational cost.

show abstract

Diversity-Promoting Deep Structural Metric Learning for Remote Sensing Scene Classification

Cited by 87 publications

References 47 publications

DeepSat V2: feature augmented convolutional neural nets for satellite image classification

DeepSat V2: feature augmented convolutional neural nets for satellite image classification

An End-to-End Joint Unsupervised Learning of Deep Model and Pseudo-Classes for Remote Sensing Scene Representation

Simple Yet Effective Fine-Tuning of Deep CNNs Using an Auxiliary Classification Loss for Remote Sensing Scene Classification

Contact Info

Product

Resources

About