Multi-feature aggregation network for salient object detection

Huang, Hu; Liu, Ping; Wang, Yanzhao; Zhou, Tongchi; Qu, Boyang; Tao, Aimin; Zhang, Hao

doi:10.1007/s11760-022-02310-3

Cited by 4 publications

(1 citation statement)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For semantic category tasks, recent solutions are based on deep-learning-based methods, including convolutional neural networks (CNNs) [1][2][3][4][5][6], Transformers [7][8][9] and their hybrid models [10][11][12][13].…”

Section: Introductionmentioning

confidence: 99%

Improved Gated Recurrent Units together with Fusion for Semantic Segmentation of Remote Sensing Images based on Parallel Hybrid Network

Zhou,

He,

Wang

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

Transformer together with convolutional neural network (CNN) has achieved better performance than the pure module-based methods. However, the advantages of both coding styles are not well considered, and the designed fusion modules have not achieved good effect in the aspect of remote sensing image (RSI) semantic segmentation. In this paper, to exploit local and global pixel dependencies, improved Gated Recurrent Units combined with fusion, are proposed to harness the complementary advantages of Parallel Hybrid Network for semantic segmentation of RSIs. The proposed network core is feature selection and fusion module (FSFM), which is composed by both feature selection units (FSU) and feature fusion units (FFU), named FSFM-PHN. Concretely, to precisely incorporate local and global representations, the improved reset and update gates of ConvGRU are treated as FSU and is realized the feature selection of the advantageous segmentation task. To merge the outputs from ResNet, Swin Transformer and FSU, feature fusion units (FFU) based on stack and sequential convolutional block operations is constructed. On the public Vaihingen, Potsdam and BLU datasets, the experimental results show that FSFM is effective, which outperforms state-of-the-art methods in some famous remote image semantic segmentation tasks.

show abstract

Section: Introductionmentioning

confidence: 99%

Improved Gated Recurrent Units together with Fusion for Semantic Segmentation of Remote Sensing Images based on Parallel Hybrid Network

Zhou,

He,

Wang

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

Hybrid-CT: a novel hybrid 2D/3D CNN-Transformer based on transfer learning and attention mechanisms for small object classification

Bayoudh,

Mtibaa

2024

SIViP

View full text Add to dashboard Cite

CF‐Net: Cross fusion network for semantic segmentation

Wang,

Shen,

Dong

et al. 2024

IET Image Processing

View full text Add to dashboard Cite

Semantic segmentation is a fundamental computer vision task, and deep learning methods have been successfully applied to this field. However, target morphology continues to exhibit the incomplete prediction problem, which is attributable to the low feature utilisation and the insufficiency of spatial location information. This paper proposes a novel cross fusion network with unit attention mechanism (CF‐Net) for semantic segmentation. The two hallmarks of the framework are the usage of a multi‐scale fusion module and the unit attention mechanism. Multi‐scale fusion module can integrate multi‐branch outputs with different receptive fields, which obtain fine‐grained target details and visual contextual information. The cross fusion network is optimised with a unit attention mechanism to fuse intermediate features, which enables the acquisition of more accurate and effective spatial location information while maintaining consistency in feature space. The experimental results demonstrate that the proposed CF‐Net outperforms favourably comparable with other existing methods on the CamVid, Cityscapes, and PASCAL VOC 2012 databases, which also verifies the Effectiveness and reliability of our method.

show abstract

Multi-feature aggregation network for salient object detection

Cited by 4 publications

References 35 publications

Improved Gated Recurrent Units together with Fusion for Semantic Segmentation of Remote Sensing Images based on Parallel Hybrid Network

Improved Gated Recurrent Units together with Fusion for Semantic Segmentation of Remote Sensing Images based on Parallel Hybrid Network

Hybrid-CT: a novel hybrid 2D/3D CNN-Transformer based on transfer learning and attention mechanisms for small object classification

CF‐Net: Cross fusion network for semantic segmentation

Contact Info

Product

Resources

About