Junxiao Wang
Research Subjects
Junxiao Wang has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Shuyuan Yang
Xidian University
3 shared publications - Chen Yang
School of Artificial Intelligence, Xidian University, Xian, China
2 shared publications - Zhixi Feng
Xidian University
2 shared publications - Huixiao Meng
School of Artificial Intelligence, Xidian University, Xian, China
1 shared publication Jie Sun
1 shared publicationShuai Xiong
1 shared publication
Latest Publications
- 7 November 2025
- Published by Elsevier in Pattern Recognition
- Vol. 172
A consistency regularization training method for automatic modulation classification under incomplete information
- 7 November 2025
- Published by Elsevier in Pattern Recognition
- Vol. 172
A consistency regularization training method for automatic modulation classification under incomplete information
- 10 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 35 (1) , 657-669
Negative Class Guided Spatial Consistency Network for Sparsely Supervised Semantic Segmentation of Remote Sensing Images
Deep neural networks (DNNs) have been successfully applied in the remote sensing semantic segmentation. However, training DNNs requires a large number of densely labeled samples, which is laborious and time-consuming. Sparsely supervised semantic segmentation (SSSS) can train deep segmentation networks using only sparse annotations. In this paper, we propose a negative class guided spatial consistency network (NCG-SCNet) for semantic segmentation with sparse annotations. Specifically, we introduce a spatial consistency enhancement module (SCEM) to enhance network features by non-linearly combining spatially similar features. Thus, it could provide better representations of the boundaries and the shape of the target. Additionally, a channel compression module (CCM) is proposed to reduce channel redundancy while preserving the network’s feature extraction capability. A negative class guided loss function (NCG Loss) is constructed to provide extra supervisory information, where the negative classes are defined as the classes with lower probability in the prediction. Extensive experiments on two widely used remote sensing datasets show that the proposed NCG-SCNet outperforms the comparison methods.
- 10 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 35 (1) , 657-669
Negative Class Guided Spatial Consistency Network for Sparsely Supervised Semantic Segmentation of Remote Sensing Images
Deep neural networks (DNNs) have been successfully applied in the remote sensing semantic segmentation. However, training DNNs requires a large number of densely labeled samples, which is laborious and time-consuming. Sparsely supervised semantic segmentation (SSSS) can train deep segmentation networks using only sparse annotations. In this paper, we propose a negative class guided spatial consistency network (NCG-SCNet) for semantic segmentation with sparse annotations. Specifically, we introduce a spatial consistency enhancement module (SCEM) to enhance network features by non-linearly combining spatially similar features. Thus, it could provide better representations of the boundaries and the shape of the target. Additionally, a channel compression module (CCM) is proposed to reduce channel redundancy while preserving the network’s feature extraction capability. A negative class guided loss function (NCG Loss) is constructed to provide extra supervisory information, where the negative classes are defined as the classes with lower probability in the prediction. Extensive experiments on two widely used remote sensing datasets show that the proposed NCG-SCNet outperforms the comparison methods.
- Open Access
- 6 December 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 2924-2930
Sparse Tensor Auto-Encoder for Saliency Detection
In this paper a new Sparse Tensor Auto-Encoder (STAE) model is proposed to learn a latent and discriminative feature representations for saliency detection. By formulating the background patches as holistic high-dimensional tensors and learning multi-dimensional dictionary to code image patches, the coding error can precisely reveal the difference between salient object and background. Then a saliency map can be derived by a subsequent refinement of the representation errors of patches via image segmentation. Several benchmark datasets are used to verify the effectiveness of the proposed method. The results show that the proposed STAE can accurately locate saliency region and outperform its counterparts.
- 6 December 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 2924-2930
Open AccessSparse Tensor Auto-Encoder for Saliency Detection
In this paper a new Sparse Tensor Auto-Encoder (STAE) model is proposed to learn a latent and discriminative feature representations for saliency detection. By formulating the background patches as holistic high-dimensional tensors and learning multi-dimensional dictionary to code image patches, the coding error can precisely reveal the difference between salient object and background. Then a saliency map can be derived by a subsequent refinement of the representation errors of patches via image segmentation. Several benchmark datasets are used to verify the effectiveness of the proposed method. The results show that the proposed STAE can accurately locate saliency region and outperform its counterparts.