Context Prior for Scene Segmentation

Yu, Changqian; Wang, Jingbo; Gao, Changxin; Yu, Gang; Shen, Chunhua

doi:10.1109/cvpr42600.2020.01243

Cited by 268 publications

(148 citation statements)

References 1 publication

Supporting

Mentioning

148

Contrasting

Order By: Relevance

“…These methods tended to ignore the dependency of context information. The CPNet [31] proposed by Changqian Yu et al could aggregate spatial information and considered context information, and thus had better prediction performance in multiclass distributed pictures. They designed the Context Prior Layer in CPNet, which was used to aggregate the intracontext and intercontext for each pixel.…”

Section: Related Workmentioning

confidence: 99%

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

Huang

Weng

Chen

et al. 2021

IJGI

View full text Add to dashboard Cite

Analyzing land cover using remote sensing images has broad prospects, the precise segmentation of land cover is the key to the application of this technology. Nowadays, the Convolution Neural Network (CNN) is widely used in many image semantic segmentation tasks. However, existing CNN models often exhibit poor generalization ability and low segmentation accuracy when dealing with land cover segmentation tasks. To solve this problem, this paper proposes Dual Function Feature Aggregation Network (DFFAN). This method combines image context information, gathers image spatial information, and extracts and fuses features. DFFAN uses residual neural networks as backbone to obtain different dimensional feature information of remote sensing images through multiple downsamplings. This work designs Affinity Matrix Module (AMM) to obtain the context of each feature map and proposes Boundary Feature Fusion Module (BFF) to fuse the context information and spatial information of an image to determine the location distribution of each image’s category. Compared with existing methods, the proposed method is significantly improved in accuracy. Its mean intersection over union (MIoU) on the LandCover dataset reaches 84.81%.

show abstract

Section: Related Workmentioning

confidence: 99%

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

Huang

Weng

Chen

et al. 2021

IJGI

View full text Add to dashboard Cite

show abstract

“…PSPNet [ 22 ] adopted the pyramid pooling module to partition the feature map into different scale regions. Yu et al [ 23 ] developed a Context Prior to distinguish the intraclass and interclass context clearly. Lin et al proposed a multipath refinement network, which contains residual convolution unit, multiresolution fusion, and chained residual pooling.…”

Section: Related Workmentioning

confidence: 99%

SSCA-Net: Simultaneous Self- and Channel-Attention Neural Network for Multiscale Structure-Preserving Vessel Segmentation

Tong

et al. 2021

BioMed Research International

View full text Add to dashboard Cite

Vessel segmentation is a fundamental, yet not well-solved problem in medical image analysis, due to the complicated geometrical and topological structures of human vessels. Unlike existing rule- and conventional learning-based techniques, which hardly capture the location of tiny vessel structures and perceive their global spatial structures, we propose Simultaneous Self- and Channel-attention Neural Network (termed SSCA-Net) to solve the multiscale structure-preserving vessel segmentation (MSVS) problem. SSCA-Net differs from the conventional neural networks in modeling image global contexts, showing more power to understand the global semantic information by both self- and channel-attention (SCA) mechanism and offering high performance on segmenting vessels with multiscale structures (e.g., DSC: 96.21% and MIoU: 92.70% on the intracranial vessel dataset). Specifically, the SCA module is designed and embedded in the feature decoding stage to learn SCA features at different layers, in which the self-attention is used to obtain the position information of the feature itself, and the channel attention is designed to guide the shallow features to obtain global feature information. To evaluate the effectiveness of our SSCA-Net, we compare it with several state-of-the-art methods on three well-known vessel segmentation benchmark datasets. Qualitative and quantitative results demonstrate clear improvements of our method over the state-of-the-art in terms of preserving vessel details and global spatial structures.

show abstract

“…PSPNet [23] adopts the pyramid pooling module to partition the feature map into different scale regions. Yu et al [24] developed a Context Prior to distinguish the intra-class and interclass context clearly. Lin et al [17] proposed a multi-path refinement network, which contains residual convolution unit, multi-resolution fusion, and chained residual pooling.…”

Section: Context Aggregationmentioning

confidence: 99%

SSCA-Net: Simultaneous Self- and Channel-attention Neural Network for Multi-scale Structure-Preserving Vessel Segmentation

Tong

Wei

et al. 2020

Preprint

View full text Add to dashboard Cite

Background: Vessel segmentation is a fundamental, yet not well-solved problem in medical image analysis, due to complicated geometrical and topological structures of human vessels. Unlike existing rule- and conventional learning-based techniques, which hardly capture the location of tiny vessel structures and perceive their global spatial structures, Methods: we propose Simultaneous Self- and Channel-attention Neural Network (termed SSCA-Net) to solve the multi-scale structure-preserving vessel segmentation (MSVS) problem. SSCA-Net differs from the conventional neural networks in modeling image global contexts, showing more power to understand the global semantic information by both self- and channel-attention (SCA) mechanism, and offering high performance on segmenting vessels with multi-scale structures. Specifically, the SCA module is designed and embedded in the feature decoding stage to learn SCA features at different layers, which the self-attention is used to obtain the position information of the feature itself, and the channel attention is designed to guide the shallow features to obtain global feature information. Results: Three blood vessel data sets are train and validate the models. our SSCA-Net achieves 96.21% in Dic and 92.70% in Mean IoU on the intracranial vessel dataset and achieved 98.20 %, 83.52% and 96.14% in AUC, Sen and Acc respectively on retinal vessel dataset. The obtain model can segment the leg arteries and Dic score is 97.21% and the Mean IoU score is 94.42%. Conclusions: The results demonstrated that the proposed SSCA-Net clear improvements of our method over the state-of-the-arts in terms of preserving vessel details and global spatial structures.

show abstract

Context Prior for Scene Segmentation

Cited by 268 publications

References 1 publication

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

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

SSCA-Net: Simultaneous Self- and Channel-Attention Neural Network for Multiscale Structure-Preserving Vessel Segmentation

SSCA-Net: Simultaneous Self- and Channel-attention Neural Network for Multi-scale Structure-Preserving Vessel Segmentation

Contact Info

Product

Resources

About