Filter-based deep-compression with global average pooling for convolutional networks

Hsiao, Ting-Yun; Chang, Yung-Chang; Chou, Hsin-Hung; Chiu, Ching-Te

doi:10.1016/j.sysarc.2019.02.008

Cited by 89 publications

(40 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then, the outputs of the three modules were added and fused. The fused features are mapped by rectified linear unit (ReLU) activation functions and then global average pooling (GAP) were applied [ 31 ]. The final feature vectors were generated by inputting the features to fully-connected layers.…”

Section: Methodsmentioning

confidence: 99%

Fusion of Hyperspectral CASI and Airborne LiDAR Data for Ground Object Classification through Residual Network

Chang

Zhang

et al. 2020

Sensors

View full text Add to dashboard Cite

Modern satellite and aerial imagery outcomes exhibit increasingly complex types of ground objects with continuous developments and changes in land resources. Single remote-sensing modality is not sufficient for the accurate and satisfactory extraction and classification of ground objects. Hyperspectral imaging has been widely used in the classification of ground objects because of its high resolution, multiple bands, and abundant spatial and spectral information. Moreover, the airborne light detection and ranging (LiDAR) point-cloud data contains unique high-precision three-dimensional (3D) spatial information, which can enrich ground object classifiers with height features that hyperspectral images do not have. Therefore, the fusion of hyperspectral image data with airborne LiDAR point-cloud data is an effective approach for ground object classification. In this paper, the effectiveness of such a fusion scheme is investigated and confirmed on an observation area in the middle parts of the Heihe River in China. By combining the characteristics of hyperspectral compact airborne spectrographic imager (CASI) data and airborne LiDAR data, we extracted a variety of features for data fusion and ground object classification. Firstly, we used the minimum noise fraction transform to reduce the dimensionality of hyperspectral CASI images. Then, spatio-spectral and textural features of these images were extracted based on the normalized vegetation index and the gray-level co-occurrence matrices. Further, canopy height features were extracted from airborne LiDAR data. Finally, a hierarchical fusion scheme was applied to the hyperspectral CASI and airborne LiDAR features, and the fused features were used to train a residual network for high-accuracy ground object classification. The experimental results showed that the overall classification accuracy was based on the proposed hierarchical-fusion multiscale dilated residual network (M-DRN), which reached an accuracy of 97.89%. This result was found to be 10.13% and 5.68% higher than those of the convolutional neural network (CNN) and the dilated residual network (DRN), respectively. Spatio-spectral and textural features of hyperspectral CASI images can complement the canopy height features of airborne LiDAR data. These complementary features can provide richer and more accurate information than individual features for ground object classification and can thus outperform features based on a single remote-sensing modality.

show abstract

Section: Methodsmentioning

confidence: 99%

Fusion of Hyperspectral CASI and Airborne LiDAR Data for Ground Object Classification through Residual Network

Chang

Zhang

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…Given the input feature map X ∈ R H×W ×C , where H,W , and C refer to the height, width, and the number of channels of feature maps, respectively. The SE module operates as follows: First, global average pooling [39], [40] is performed on each feature map to obtain the output C − dimensional column vector z:…”

Section: Sea-land Boundary Feature Enhancementmentioning

confidence: 99%

SANet: A Sea–Land Segmentation Network Via Adaptive Multiscale Feature Learning

Cui

Wei

Ling

et al. 2021

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

View full text Add to dashboard Cite

Sea-land segmentation of remote sensing images is of great significance to the dynamic monitoring of coastlines. However, the types of objects in the coastal zone are complex, and their spectra, textures, shapes, and distribution features are different. Therefore, sea-land segmentation for various types of coastlines is still a challenging task. In this paper, a scale-adaptive semantic segmentation network, called SANet, is proposed for sea-land segmentation of remote sensing images. SANet has made two innovations on the basis of the classic encoder-decoder structure. First, to integrate the spectral, textural and semantic features of ground objects at different scales, we designed an adaptive multi-scale feature learning module (AML) to replace the conventional serial convolution operation. The AML module mainly contains a multi-scale feature extraction unit and an adaptive feature fusion unit. The former can capture the multiscale detailed information and contextual semantic information of objects from an early stage, while the latter can adaptively fuse feature maps of different scales. Second, we adopted the squeezeand-excitation module to bridge the corresponding layers of the codec so that SANet can selectively emphasize the features of the weak sea-land boundaries. Experiments on a set of Gaofen-1 remote sensing images demonstrated that SANet achieved more accurate segmentation results and obtained sharper boundaries than other methods for various natural and artificial coastlines.

show abstract

“…The squeeze-excitation module includes both a squeeze operation, F squeeze , and an excitation operation, F excitation . As illustrated in Figure 3, the given feature maps X, X ∈ R H×W×C , where H, W, and C refer to the height, width, and number of channels of the feature maps, respectively, first pass through a squeeze operation (global average pooling [32,33]), which generates z ∈ R C , where z k is the k-th element of z, and X k is the k-th feature map of X:…”

Section: Squeeze-excitation Modulementioning

confidence: 99%

Extracting Raft Aquaculture Areas from Remote Sensing Images via an Improved U-Net with a PSE Structure

et al. 2019

View full text Add to dashboard Cite

Remote sensing has become a primary technology for monitoring raft aquaculture products. However, due to the complexity of the marine aquaculture environment, the boundaries of the raft aquaculture areas in remote sensing images are often blurred, which will result in 'adhesion' phenomenon in the raft aquaculture areas extraction. The fully convolutional network (FCN) based methods have made great progress in the field of remote sensing in recent years. In this paper, we proposed an FCN-based end-to-end raft aquaculture areas extraction model (which is called UPS-Net) to overcome the 'adhesion' phenomenon. The UPS-Net contains an improved U-Net and a PSE structure. The improved U-Net can simultaneously capture boundary and contextual information of raft aquaculture areas from remote sensing images. The PSE structure can adaptively fuse the boundary and contextual information to reduce the 'adhesion' phenomenon. We selected laver raft aquaculture areas in eastern Lianyungang in China as the research region to verify the effectiveness of our model. The experimental results show that compared with several state-of-the-art models, the proposed UPS-Net model performs better at extracting raft aquaculture areas and can significantly reduce the 'adhesion' phenomenon.

show abstract

Filter-based deep-compression with global average pooling for convolutional networks

Cited by 89 publications

References 5 publications

Fusion of Hyperspectral CASI and Airborne LiDAR Data for Ground Object Classification through Residual Network

Fusion of Hyperspectral CASI and Airborne LiDAR Data for Ground Object Classification through Residual Network

SANet: A Sea–Land Segmentation Network Via Adaptive Multiscale Feature Learning

Extracting Raft Aquaculture Areas from Remote Sensing Images via an Improved U-Net with a PSE Structure

Contact Info

Product

Resources

About