DFFAN: Dual Function Feature Aggregation Network for Semantic Segmentation of Land Cover

Huang, Junqing; Weng, Liguo; Chen, Bingyu; Xia, Min

doi:10.3390/ijgi10030125

Cited by 17 publications

(13 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The neural network DANet [26], PSPNet [27], FCN [18], and deeplabv3+ [32] are using pre-trained ResNet-50 as their backbone, DenseA-SPP [57] takes DenseNet [58] as its and all of them are implemented with the PyTorch framework. In addition, our method was compared with other published research on the same dataset recently, such as DFFAN [59] and MFANet [60]. As the results of Table 4 show, our DGFNet outperforms other methods in terms of the MIoU, FWIoU, MPA, and PA.…”

Section: Model Analysis 431 Influence Of Different Modules On Classificationmentioning

confidence: 77%

DGFNet: Dual Gate Fusion Network for Land Cover Classification in Very High-Resolution Images

et al. 2021

View full text Add to dashboard Cite

Deep convolutional neural networks (DCNNs) have been used to achieve state-of-the-art performance on land cover classification thanks to their outstanding nonlinear feature extraction ability. DCNNs are usually designed as an encoder–decoder architecture for the land cover classification in very high-resolution (VHR) remote sensing images. The encoder captures semantic representation by stacking convolution layers and shrinking image spatial resolution, while the decoder restores the spatial information by an upsampling operation and combines it with different level features through a summation or skip connection. However, there is still a semantic gap between different-level features; a simple summation or skip connection will reduce the performance of land-cover classification. To overcome this problem, we propose a novel end-to-end network named Dual Gate Fusion Network (DGFNet) to restrain the impact of the semantic gap. In detail, the key of DGFNet consists of two main components: Feature Enhancement Module (FEM) and Dual Gate Fusion Module (DGFM). Firstly, the FEM combines local information with global contents and strengthens the feature representation in the encoder. Secondly, the DGFM is proposed to reduce the semantic gap between different level features, effectively fusing low-level spatial information and high-level semantic information in the decoder. Extensive experiments conducted on the LandCover dataset and the ISPRS Potsdam dataset proved the effectiveness of the proposed network. The DGFNet achieves state-of-art performance 88.87% MIoU on the LandCover dataset and 72.25% MIoU on the ISPRS Potsdam dataset.

show abstract

Section: Model Analysis 431 Influence Of Different Modules On Classificationmentioning

confidence: 77%

DGFNet: Dual Gate Fusion Network for Land Cover Classification in Very High-Resolution Images

et al. 2021

View full text Add to dashboard Cite

show abstract

“…A dense fusion classmate network 28 incorporates mid-level information using an auxiliary road dataset in addition to the DeepGlobe dataset 29 for land cover classification. Huang et al 30 designed dual function feature aggregation network (DFFAN), a system for combining background information, collecting spatial information, and extracting and fusing features from an image. Wei et al 31 proposed a pyramid partial decoder based on an improved parallel partial decoder for more thoroughly fusing the multi-level features of the encoder.…”

Section: Semantic Segmentation For Land Cover Classificationmentioning

confidence: 99%

“…For all cases, ResNet50 with pre-trained weights as the backbone was implemented using the same device, and the PyTorch framework was also applied. In addition, we compared our results with those of other recently published methods for the LandCover.ai dataset, including MFANet, 40 DGFNet, 42 DFFAN, 30 and DEANet. 31 The results in Table 4 show that AMFFNet achieves optimal results for the two evaluation metrics.…”

Section: Comparison Of Landcoverai Datasetmentioning

confidence: 99%

AMFFNet: attention-guided multi-level feature fusion network for land cover classification of remote sensing images

Tang

Tuerxun

et al. 2022

J. Appl. Rem. Sens.

View full text Add to dashboard Cite

In the field of remote sensing, the classification of land cover is a pivotal and challenging issue. Standard models fail to capture global and semantic information in remote sensing images despite the fact that a convolutional neural network provides robust support for semantic segmentation. In addition, owing to disparities in semantic levels and spatial resolution, the simple fusion of low-level and high-level features may diminish the efficiency. To address these deficiencies, an attention-guided multi-level feature fusion network (AMFFNet) is proposed in this study. The proposed AMFFNet approach is designed as an encoder-decoder network with the inclusion of a multi-level feature fusion module (MFF) and a dual attention map module (DAM). A DAM models the semantic association of features from a spatial and channel perspective, and an MFF bridges the semantic and resolution gaps between high-level and low-level features. Furthermore, we propose a residual-based boundary refinement upsample module to further optimize the object boundaries. The experimental results indicate that the proposed strategy can considerably enhance the accuracy of land cover classification, achieving a mean intersection over union of 90.39% on the LandCover.ai dataset and 63.14% on the Gaofen Image Dataset with 15 categories (GID-15).

show abstract

“…Ample CNN variants have been studied to solve the task of land cover classification by taking high-resolution remote sensing images as input, such as these serial networks of Sherrah et al [27] , Maggiori et al [28] , Luo et al [29] , Huang et al [30] etc. However, there are still several issues remained to be addressed, one of them is fragmented segmentation caused by scale variance of objects in high-resolution remote sensing images as Fig.…”

Section: Introductionmentioning

confidence: 99%

Multiscale Feature Reconstruction and Interclass Attention Weighting for Land Cover Classification

Zhan,

Xiong,

Huang

et al. 2024

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

View full text Add to dashboard Cite

Land cover classification has the goal to attribute each pixel of high-resolution remote sensing image with planimetric category labels (such as vegetation, building, water etc.). In recent years, many serial deep learning architectures (features are delivered through a single path such as in ResNet, MobileNet, Segformer etc.) based on Convolutional Neural Networks (CNN) and attention mechanisms have been widely explored in land cover classification. However, high-resolution remote sensing images typically have abundant textual details, variable scales in objects, large intra-class variance and similar inter-class correlation, which bring challenges to land cover classification. In this work, we present two pluggable modules to further boost serial learning architecture: first, to cope with ambiguous boundaries caused by lost details and fragmented segmentation stemmed from scale variances, a combination of spatial attention and channel attention is proposed for Multi-Scale Feature Reconstruction (MSFR); Second, to mitigate the classification error caused by intra-class variance and inter-class correlation, we explore an Inter-Class Attention Weighting (ICAW) module, which builds feature vectors for each category, and applies a multi-head attention model to capture self-attention dependence among different categories. The experimental results demonstrate that the proposed modules are feasible to existing serial learning architectures and can improve OA (Overall Accuracy) by 5.64% on the ISPRS Vaihingen 2D dataset (using ResNet50 as backbone), in particular, the OA values are 80.68% and 86.32% before and after using the proposed modules, respectively. In addition, compared to other state-of-art models, our method can achieve similar or even better classification results, yet offer superior inference performance. Code is available at: https://github.com/StraySparks/MSFR-and-ICAW.

show abstract

DFFAN: Dual Function Feature Aggregation Network for Semantic Segmentation of Land Cover

Cited by 17 publications

References 35 publications

DGFNet: Dual Gate Fusion Network for Land Cover Classification in Very High-Resolution Images

DGFNet: Dual Gate Fusion Network for Land Cover Classification in Very High-Resolution Images

AMFFNet: attention-guided multi-level feature fusion network for land cover classification of remote sensing images

Multiscale Feature Reconstruction and Interclass Attention Weighting for Land Cover Classification

Contact Info

Product

Resources

About