Bin Wu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Bin Wu has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Wei Wang
Beijing Jiaotong University, Beijing, China
3 shared publications - Siyuan Hao
School of Software Engineering, Beijing Jiaotong University, Beijing, China
2 shared publications - Chi Zhang
Beijing Jiaotong University
1 shared publication - Kun Zhao
School of Information and Control Engineering, Qingdao University of Technology, Qingdao, China
1 shared publication - Siyuan Hao
School of Information and Control Engineering, Qingdao University of Technology, Qingdao 266525, China
1 shared publication Wei Wang
Institute of Information Science, Beijing Jiaotong University, Beijing, China
1 shared publication
Latest Publications
- 12 September 2026
- Published by Springer Nature
- p. 445-462
Beyond the Boundary: RL-Driven Solution Space Exploration for Blind Face Restoration
- 12 September 2026
- Published by Springer Nature
- p. 445-462
Beyond the Boundary: RL-Driven Solution Space Exploration for Blind Face Restoration
- 27 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 22 (1545598X) , 1-5
Semantic-Aware Guidance for Blind Super-Resolution of Remote Sensing Images
Unlike traditional super-resolution (SR) methods that rely on fixed degradation models, blind super-resolution (BSR) methods can capture the complex processes introduced by factors such as sensor noise and platform motion in real-world remote sensing imagery. While most BSR methods effectively remove degradation from low-resolution (LR) images, they often struggle to preserve high-frequency details, leading to reduced reconstruction accuracy. To address this issue, we propose the Semantic Guidance Blind Super-Resolution (SGBSR) network, which leverages semantic information to guide the entire restoration process, enabling more accurate reconstruction. Specifically, we design a semantic extractor that utilizes powerful pre-trained visual models to capture rich semantic information from LR images, which is then integrated into the SR network. To further enhance the network’s ability to handle complex degradations, we introduce an implicit estimation method. Subsequently, the semantic information and degradation representations are respectively incorporated into the SR network through the Semantic-aware Block (SaB) and the Degradation-aware Block (DaB). Experiments on both synthetic and real-world LR images demonstrate that our method achieves superior reconstruction accuracy.
- 27 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 22 (1545598X) , 1-5
Semantic-Aware Guidance for Blind Super-Resolution of Remote Sensing Images
Unlike traditional super-resolution (SR) methods that rely on fixed degradation models, blind super-resolution (BSR) methods can capture the complex processes introduced by factors such as sensor noise and platform motion in real-world remote sensing imagery. While most BSR methods effectively remove degradation from low-resolution (LR) images, they often struggle to preserve high-frequency details, leading to reduced reconstruction accuracy. To address this issue, we propose the Semantic Guidance Blind Super-Resolution (SGBSR) network, which leverages semantic information to guide the entire restoration process, enabling more accurate reconstruction. Specifically, we design a semantic extractor that utilizes powerful pre-trained visual models to capture rich semantic information from LR images, which is then integrated into the SR network. To further enhance the network’s ability to handle complex degradations, we introduce an implicit estimation method. Subsequently, the semantic information and degradation representations are respectively incorporated into the SR network through the Semantic-aware Block (SaB) and the Degradation-aware Block (DaB). Experiments on both synthetic and real-world LR images demonstrate that our method achieves superior reconstruction accuracy.
- Open Access
- 15 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 17 (19391404) , 2173-2188
Class-Aware Self-Distillation for Remote Sensing Image Scene Classification
Currently, Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) are widely adopted as the predominant neural network architectures for remote sensing image scene classification. Although CNNs have lower computational complexity, ViTs have a higher performance ceiling, making both suitable as backbone networks for remote sensing scene classification tasks. However, remote sensing imagery has high intra-class variation and inter-class similarity, which poses a challenge for existing methods. To address this issue, we propose the Class-aware Self-distillation (CASD) Framework. This framework uses an end-to-end distillation mechanism to mine class-aware knowledge, effectively reducing the impact of significant intra-class variation and inter-class similarity in remote sensing imagery. Specifically, our approach involves constructing pairs of images: similar pairs consisting of images belonging to the same class, and dissimilar pairs consisting of images from different classes. We then apply a distillation loss that we designed, which distills the corresponding probability distributions to ensure that the distributions of similar pairs become more consistent, and those of dissimilar pairs become more distinct. Additionally, the enforced learnable α added to the distillation loss further amplifies the network's ability to comprehend class-aware knowledge. The experiment section demonstrates that our method CASD outperforms other methods on four publicly available datasets. And the ablation experiments demonstrate the effectiveness of the method.
- 15 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 17 (19391404) , 2173-2188
Open AccessClass-Aware Self-Distillation for Remote Sensing Image Scene Classification
Currently, Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) are widely adopted as the predominant neural network architectures for remote sensing image scene classification. Although CNNs have lower computational complexity, ViTs have a higher performance ceiling, making both suitable as backbone networks for remote sensing scene classification tasks. However, remote sensing imagery has high intra-class variation and inter-class similarity, which poses a challenge for existing methods. To address this issue, we propose the Class-aware Self-distillation (CASD) Framework. This framework uses an end-to-end distillation mechanism to mine class-aware knowledge, effectively reducing the impact of significant intra-class variation and inter-class similarity in remote sensing imagery. Specifically, our approach involves constructing pairs of images: similar pairs consisting of images belonging to the same class, and dissimilar pairs consisting of images from different classes. We then apply a distillation loss that we designed, which distills the corresponding probability distributions to ensure that the distributions of similar pairs become more consistent, and those of dissimilar pairs become more distinct. Additionally, the enforced learnable α added to the distillation loss further amplifies the network's ability to comprehend class-aware knowledge. The experiment section demonstrates that our method CASD outperforms other methods on four publicly available datasets. And the ablation experiments demonstrate the effectiveness of the method.
- Open Access
- 20 March 2022
- Published by MDPI AG in Remote Sensing
- Vol. 14 (6) , 1507
Two-Stream Swin Transformer with Differentiable Sobel Operator for Remote Sensing Image Classification
Remote sensing (RS) image classification has attracted much attention recently and is widely used in various fields. Different to natural images, the RS image scenes consist of complex backgrounds and various stochastically arranged objects, thus making it difficult for networks to focus on the target objects in the scene. However, conventional classification methods do not have any special treatment for remote sensing images. In this paper, we propose a two-stream swin transformer network (TSTNet) to address these issues. TSTNet consists of two streams (i.e., original stream and edge stream) which use both the deep features of the original images and the ones from the edges to make predictions. The swin transformer is used as the backbone of each stream given its good performance. In addition, a differentiable edge Sobel operator module (DESOM) is included in the edge stream which can learn the parameters of Sobel operator adaptively and provide more robust edge information that can suppress background noise. Experimental results on three publicly available remote sensing datasets show that our TSTNet achieves superior performance over the state-of-the-art (SOTA) methods.
- 20 March 2022
- Published by MDPI AG in Remote Sensing
- Vol. 14 (6) , 1507
Open AccessTwo-Stream Swin Transformer with Differentiable Sobel Operator for Remote Sensing Image Classification
Remote sensing (RS) image classification has attracted much attention recently and is widely used in various fields. Different to natural images, the RS image scenes consist of complex backgrounds and various stochastically arranged objects, thus making it difficult for networks to focus on the target objects in the scene. However, conventional classification methods do not have any special treatment for remote sensing images. In this paper, we propose a two-stream swin transformer network (TSTNet) to address these issues. TSTNet consists of two streams (i.e., original stream and edge stream) which use both the deep features of the original images and the ones from the edges to make predictions. The swin transformer is used as the backbone of each stream given its good performance. In addition, a differentiable edge Sobel operator module (DESOM) is included in the edge stream which can learn the parameters of Sobel operator adaptively and provide more robust edge information that can suppress background noise. Experimental results on three publicly available remote sensing datasets show that our TSTNet achieves superior performance over the state-of-the-art (SOTA) methods.