Scene classification of remote sensing image based on deep network and multi-scale features fusion

Yang, Zhou; Mu, Xiaodong; Zhao, Feng’an

doi:10.1016/j.ijleo.2018.06.024

Cited by 36 publications

(11 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep learning is widely used in environmental remote sensing, such as land use extraction, land cover change analysis [5,6], remote sensing image classification [7,8], and object detection [9][10][11]. The deep-learning models commonly used in road extraction are convolutional neural networks (CNNs) [12], whose network structure is often used for various computer-vision tasks, and semantic segmentation technology [13][14][15][16][17][18] is another area of great research interest in image interpretation.…”

Section: Introductionmentioning

confidence: 99%

Road Extraction from Very-High-Resolution Remote Sensing Images via a Nested SE-Deeplab Model

Lin

Wang

et al. 2020

Remote Sensing

View full text Add to dashboard Cite

Automatic road extraction from very-high-resolution remote sensing images has become a popular topic in a wide range of fields. Convolutional neural networks are often used for this purpose. However, many network models do not achieve satisfactory extraction results because of the elongated nature and varying sizes of roads in images. To improve the accuracy of road extraction, this paper proposes a deep learning model based on the structure of Deeplab v3. It incorporates squeeze-and-excitation (SE) module to apply weights to different feature channels, and performs multi-scale upsampling to preserve and fuse shallow and deep information. To solve the problems associated with unbalanced road samples in images, different loss functions and backbone network modules are tested in the model’s training process. Compared with cross entropy, dice loss can improve the performance of the model during training and prediction. The SE module is superior to ResNext and ResNet in improving the integrity of the extracted roads. Experimental results obtained using the Massachusetts Roads Dataset show that the proposed model (Nested SE-Deeplab) improves F1-Score by 2.4% and Intersection over Union by 2.0% compared with FC-DenseNet. The proposed model also achieves better segmentation accuracy in road extraction compared with other mainstream deep-learning models including Deeplab v3, SegNet, and UNet.

show abstract

Section: Introductionmentioning

confidence: 99%

Road Extraction from Very-High-Resolution Remote Sensing Images via a Nested SE-Deeplab Model

Lin

Wang

et al. 2020

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…In the above scene classification methods, only the local multi-scale is used, but the multi-scale features of images and the depth of networks are not fully utilized. Therefore, Zhou et al proposed a new remote sensing scene classification method based on multiscale feature fusion (MSFF) [27]. MSFF combines multi-scale features and multi-scale input images for the first time, and the hierarchical features extracted from different levels are fused for classification.…”

Section: A Methods For Remote Sensing Scene Classificationmentioning

confidence: 99%

SEMSDNet: A Multiscale Dense Network With Attention for Remote Sensing Scene Classification

Tian

Chen

Zhou

2021

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

“…ARCNet-VGG16 [11] 99.12 ± 0.40 96.81 ± 0.14 VGG16+MSCP [39] 98.36 ± 0.58 -Siamese ResNet50+RD [40] 94.50 91.71 OverfeatL+IFK [41] 98.91 -Triplet networks [13] 97.99 ± 0.53 -MCNN [23] 96.66 ± 0.90 GoogLeNet+SVM [35] 94.31 ± 0.89 92.70 ± 0.60 AlexNet [42] 95.00 ± 1.74 -VGG16+IFK [25] 98.57 ± 0.34 D-DSML-CaffeNet [24] 95.76 ± 1.70 ResNet [42] 97.19 ± 0.57 Fusion by addition [30] 97.42 ± 1.79 VGG16+EMR [28] 98.14 Fine-tuning VGG16 [5] 97.14 ± 0.48 96.57 ± 0.38 GBNet [5] 96.90 ± 0.23 95.71 ± 0.19 GBNet+global feature [5] 98.57 ± 0.48 97.05 ± 0.19 Fine-tuning GoogLeNet [6] 97. Table 10.…”

Section: % Train 50% Trainmentioning

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

Scene classification of remote sensing image based on deep network and multi-scale features fusion

Cited by 36 publications

References 17 publications

Road Extraction from Very-High-Resolution Remote Sensing Images via a Nested SE-Deeplab Model

Road Extraction from Very-High-Resolution Remote Sensing Images via a Nested SE-Deeplab Model

SEMSDNet: A Multiscale Dense Network With Attention for Remote Sensing Scene Classification

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

Contact Info

Product

Resources

About