Graph-FCN for Image Semantic Segmentation

Lu, Yi; Chen, Yaran; Zhao, Dan; Chen, Jianxin

doi:10.1007/978-3-030-22796-8_11

Cited by 88 publications

(33 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To explore high-order relations between the lower-level local features from CIM and higher-level cues from CFM. We introduce the non-local [77], [78] operation under graph convolution domain [79] to implement our similarity aggregation module (SAM). As a result, SAM can inject detailed appearance features into high-level semantic features using global attention.…”

Section: E Similarity Aggregation Modulementioning

confidence: 99%

Polyp-PVT: Polyp Segmentation with Pyramid Vision Transformers

Dong¹,

Wang²,

Fan³

et al. 2021

Preprint

View full text Add to dashboard Cite

Most polyp segmentation methods use CNNs as their backbone, leading to two key issues when exchanging information between the encoder and decoder: 1) taking into account the differences in contribution between different-level features; and 2) designing effective mechanism for fusing these features. Different from existing CNN-based methods, we adopt a transformer encoder, which learns more powerful and robust representations. In addition, considering the image acquisition influence and elusive properties of polyps, we introduce three novel modules, including a cascaded fusion module (CFM), a camouflage identification module (CIM), a and similarity aggregation module (SAM). Among these, the CFM is used to collect the semantic and location information of polyps from high-level features, while the CIM is applied to capture polyp information disguised in low-level features. With the help of the SAM, we extend the pixel features of the polyp area with high-level semantic position information to the entire polyp area, thereby effectively fusing cross-level features. The proposed model, named Polyp-PVT, effectively suppresses noises in the features and significantly improves their expressive capabilities. Extensive experiments on five widely adopted datasets show that the proposed model is more robust to various challenging situations (e.g., appearance changes, small objects) than existing methods, and achieves the new state-of-the-art performance. The proposed model is available at https://github.com/DengPingFan/Polyp-PVT.

show abstract

Section: E Similarity Aggregation Modulementioning

confidence: 99%

Polyp-PVT: Polyp Segmentation with Pyramid Vision Transformers

Dong¹,

Wang²,

Fan³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…For example, approaches, such as References [29,30], tried to generalize convolution layers to the graphs. Other works, like References [31,32], attempted to learn knowledge graphs and use graphs for visual reasoning.…”

Section: Remote Sensing With Gnnmentioning

confidence: 99%

Knowledge and Spatial Pyramid Distance-Based Gated Graph Attention Network for Remote Sensing Semantic Segmentation

Cui

Meng

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

The pixel-based semantic segmentation methods take pixels as recognitions units, and are restricted by the limited range of receptive fields, so they cannot carry richer and higher-level semantics. These reduce the accuracy of remote sensing (RS) semantic segmentation to a certain extent. Comparing with the pixel-based methods, the graph neural networks (GNNs) usually use objects as input nodes, so they not only have relatively small computational complexity, but also can carry richer semantic information. However, the traditional GNNs are more rely on the context information of the individual samples and lack geographic prior knowledge that reflects the overall situation of the research area. Therefore, these methods may be disturbed by the confusion of “different objects with the same spectrum” or “violating the first law of geography” in some areas. To address the above problems, we propose a remote sensing semantic segmentation model called knowledge and spatial pyramid distance-based gated graph attention network (KSPGAT), which is based on prior knowledge, spatial pyramid distance and a graph attention network (GAT) with gating mechanism. The model first uses superpixels (geographical objects) to form the nodes of a graph neural network and then uses a novel spatial pyramid distance recognition algorithm to recognize the spatial relationships. Finally, based on the integration of feature similarity and the spatial relationships of geographic objects, a multi-source attention mechanism and gating mechanism are designed to control the process of node aggregation, as a result, the high-level semantics, spatial relationships and prior knowledge can be introduced into a remote sensing semantic segmentation network. The experimental results show that our model improves the overall accuracy by 4.43% compared with the U-Net Network, and 3.80% compared with the baseline GAT network.

show abstract

“…The recently proposed graph representation methods allow us to better understand the structures of these networks and promote the development of various disciplines. Interestingly, the early graph embedding methods were benefited from natural language processing [12], while now the graph neural networks (GNN) are used to successfully deal with visual semantic segmentation [13]. Furthermore, these graph embedding methods have made remarkable achievements in such areas as recommendation systems [14], [15], QA sites [16], [17], and even drug discovery [18], [19].…”

Section: Introductionmentioning

confidence: 99%

Sampling Subgraph Network With Application to Graph Classification

Wang

Chen

et al. 2021

IEEE Trans. Netw. Sci. Eng.

View full text Add to dashboard Cite

Graphs are naturally used to describe the structures of various real-world systems in biology, society, computer science etc., where subgraphs or motifs as basic blocks play an important role in function expression and information processing. However, existing research focuses on the basic statistics of certain motifs, largely ignoring the connection patterns among them. Recently, a subgraph network (SGN) model is proposed to study the potential structure among motifs, and it was found that the integration of SGN can enhance a series of graph classification methods. However, SGN model lacks diversity and is of quite high time complexity, making it difficult to widely apply in practice. In this paper, we introduce sampling strategies into SGN, and design a novel sampling subgraph network model, which is scale-controllable and of higher diversity. We also present a hierarchical feature fusion framework to integrate the structural features of diverse sampling SGNs, so as to improve the performance of graph classification. Extensive experiments demonstrate that, by comparing with the SGN model, our new model indeed has much lower time complexity (reduced by two orders of magnitude) and can better enhance a series of graph classification methods (doubling the performance enhancement).

show abstract

Graph-FCN for Image Semantic Segmentation

Cited by 88 publications

References 15 publications

Polyp-PVT: Polyp Segmentation with Pyramid Vision Transformers

Polyp-PVT: Polyp Segmentation with Pyramid Vision Transformers

Knowledge and Spatial Pyramid Distance-Based Gated Graph Attention Network for Remote Sensing Semantic Segmentation

Sampling Subgraph Network With Application to Graph Classification

Contact Info

Product

Resources

About