Yang Yang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yang Yang has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Shunyi Zheng
School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, China
4 shared publications - Wei Ao
School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, China
3 shared publications - Zhao Liu
School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, China
2 shared publications - Chenxi Duan
Faculty of Geo-Information Science and Earth Observation (ITC), University of Twente, Enschede, The Netherlands
1 shared publication - Rui Li
School of Engineering, University of Warwick
1 shared publication Shunyi Zheng
1 shared publication
Latest Publications
- Open Access
- 20 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 19 (19391404) , 6328-6340
AMPUNet: Hierarchical Attention Map Pyramid for Semantic Segmentation of Remote Sensing Images
Accurate semantic segmentation of high-resolution remote sensing imagery is essential for applications ranging from urban planning to environmental monitoring. However, this task remains fundamentally challenging due to the complex spatial patterns, extreme scale variations, and fine-grained details inherent in geographical scenes. While attention mechanisms, particularly global and sparse attention, have shown promise in capturing long-range dependencies, existing approaches often suffer from three interconnected limitations: prohibitive computational complexity, misalignment when integrating multi-scale representations, and loss of semantic information during the decoder's upsampling stages. This paper introduces AMPUNet, a novel framework designed to overcome these limitations through the construction of a hierarchical, coarse-to-fine attention map pyramid. Our core innovation lies in explicitly propagating and refining attention maps across network layers rather than operating solely on feature maps. Specifically, we design: (1) a hybrid sparse attention framework combining a Block Attention Module and a Column Attention Module to model global context efficiently; (2) a Dimension Correspondence Module to achieve tensor-level granularity alignment for multi-scale attention maps; and (3) an Attention Map Merging Module with a Cross-layer Attention Weighting strategy, which directly transfers high-level semantic information from deep to shallow layers, mitigating information degradation. Extensive experiments on the ISPRS Vaihingen, Potsdam, and LoveDA benchmarks demonstrate that AMPUNet achieves superior performance, with mIoU scores of 75.43% on Vaihingen, 78.03% on Potsdam, and 50.94% on LoveDA, while maintaining competitive inference efficiency. Our findings confirm that structuring attention into a learnable pyramid is a highly effective paradigm for remote sensing semantic segmentation, successfully balancing precise detail preservation with robust global understanding. The source code is available at: https://github.com/interpretty/AMPUNet.
- 20 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 19 (19391404) , 6328-6340
Open AccessAMPUNet: Hierarchical Attention Map Pyramid for Semantic Segmentation of Remote Sensing Images
Accurate semantic segmentation of high-resolution remote sensing imagery is essential for applications ranging from urban planning to environmental monitoring. However, this task remains fundamentally challenging due to the complex spatial patterns, extreme scale variations, and fine-grained details inherent in geographical scenes. While attention mechanisms, particularly global and sparse attention, have shown promise in capturing long-range dependencies, existing approaches often suffer from three interconnected limitations: prohibitive computational complexity, misalignment when integrating multi-scale representations, and loss of semantic information during the decoder's upsampling stages. This paper introduces AMPUNet, a novel framework designed to overcome these limitations through the construction of a hierarchical, coarse-to-fine attention map pyramid. Our core innovation lies in explicitly propagating and refining attention maps across network layers rather than operating solely on feature maps. Specifically, we design: (1) a hybrid sparse attention framework combining a Block Attention Module and a Column Attention Module to model global context efficiently; (2) a Dimension Correspondence Module to achieve tensor-level granularity alignment for multi-scale attention maps; and (3) an Attention Map Merging Module with a Cross-layer Attention Weighting strategy, which directly transfers high-level semantic information from deep to shallow layers, mitigating information degradation. Extensive experiments on the ISPRS Vaihingen, Potsdam, and LoveDA benchmarks demonstrate that AMPUNet achieves superior performance, with mIoU scores of 75.43% on Vaihingen, 78.03% on Potsdam, and 50.94% on LoveDA, while maintaining competitive inference efficiency. Our findings confirm that structuring attention into a learnable pyramid is a highly effective paradigm for remote sensing semantic segmentation, successfully balancing precise detail preservation with robust global understanding. The source code is available at: https://github.com/interpretty/AMPUNet.
- 27 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 22 (1545598X) , 1-5
AMMUNet: Multiscale Attention Map Merging for Remote Sensing Image Segmentation
The advancement of deep learning has driven notable progress in remote sensing semantic segmentation. Multi-head self-attention mechanisms have been widely adopted in semantic segmentation tasks. Network architectures exemplified by vision transformers have implemented window-based operations in the spatial domain to reduce computational costs. However, this approach comes at the expense of weakened capacity to capture long-range dependencies, potentially limiting their efficacy in remote sensing image processing. In this letter, we propose AMMUNet, a UNet-based framework that employs multi-scale attention map merging, comprising two key innovations: the attention map merging mechanism (AMMM) module and the granular multi-head self-attention (GMSA). AMMM effectively combines multi-scale attention maps into a unified representation using a fixed mask template, enabling the modeling of global attention mechanism. By integrating precomputed attention maps in preceding layers, AMMM reduces computational cost while preserving global correlations. The proposed GMSA efficiently acquires global information while substantially mitigating computational costs in contrast to global multi-head self-attention mechanism. This is accomplished through the strategic alignment of granularity and the reduction of relative position bias parameters, thereby optimizing computational efficiency. Experimental evaluations highlight the superior performance of our approach, achieving remarkable mean intersection over union (mIoU) scores of 75.48% on the challenging Vaihingen dataset and an exceptional 77.90% on the Potsdam dataset, demonstrating the superiority of our method in precise remote sensing semantic segmentation. Codes are available at https://github.com/interpretty/AMMUNet.
- 27 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 22 (1545598X) , 1-5
AMMUNet: Multiscale Attention Map Merging for Remote Sensing Image Segmentation
The advancement of deep learning has driven notable progress in remote sensing semantic segmentation. Multi-head self-attention mechanisms have been widely adopted in semantic segmentation tasks. Network architectures exemplified by vision transformers have implemented window-based operations in the spatial domain to reduce computational costs. However, this approach comes at the expense of weakened capacity to capture long-range dependencies, potentially limiting their efficacy in remote sensing image processing. In this letter, we propose AMMUNet, a UNet-based framework that employs multi-scale attention map merging, comprising two key innovations: the attention map merging mechanism (AMMM) module and the granular multi-head self-attention (GMSA). AMMM effectively combines multi-scale attention maps into a unified representation using a fixed mask template, enabling the modeling of global attention mechanism. By integrating precomputed attention maps in preceding layers, AMMM reduces computational cost while preserving global correlations. The proposed GMSA efficiently acquires global information while substantially mitigating computational costs in contrast to global multi-head self-attention mechanism. This is accomplished through the strategic alignment of granularity and the reduction of relative position bias parameters, thereby optimizing computational efficiency. Experimental evaluations highlight the superior performance of our approach, achieving remarkable mean intersection over union (mIoU) scores of 75.48% on the challenging Vaihingen dataset and an exceptional 77.90% on the Potsdam dataset, demonstrating the superiority of our method in precise remote sensing semantic segmentation. Codes are available at https://github.com/interpretty/AMMUNet.
- Open Access
AMMUNet: Multi-Scale Attention Map Merging for Remote Sensing Image Segmentation
The advancement of deep learning has driven notable progress in remote sensing semantic segmentation. Attention mechanisms, while enabling global modeling and utilizing contextual information, face challenges of high computational costs and require window-based operations that weaken capturing long-range dependencies, hindering their effectiveness for remote sensing image processing. In this letter, we propose AMMUNet, a UNet-based framework that employs multi-scale attention map merging, comprising two key innovations: the granular multi-head self-attention (GMSA) module and the attention map merging mechanism (AMMM). GMSA efficiently acquires global information while substantially mitigating computational costs in contrast to global multi-head self-attention mechanism. This is accomplished through the strategic utilization of dimension correspondence to align granularity and the reduction of relative position bias parameters, thereby optimizing computational efficiency. The proposed AMMM effectively combines multi-scale attention maps into a unified representation using a fixed mask template, enabling the modeling of global attention mechanism. Experimental evaluations highlight the superior performance of our approach, achieving remarkable mean intersection over union (mIoU) scores of 75.48\% on the challenging Vaihingen dataset and an exceptional 77.90\% on the Potsdam dataset, demonstrating the superiority of our method in precise remote sensing semantic segmentation. Codes are available at https://github.com/interpretty/AMMUNet.
Open AccessAMMUNet: Multi-Scale Attention Map Merging for Remote Sensing Image Segmentation
The advancement of deep learning has driven notable progress in remote sensing semantic segmentation. Attention mechanisms, while enabling global modeling and utilizing contextual information, face challenges of high computational costs and require window-based operations that weaken capturing long-range dependencies, hindering their effectiveness for remote sensing image processing. In this letter, we propose AMMUNet, a UNet-based framework that employs multi-scale attention map merging, comprising two key innovations: the granular multi-head self-attention (GMSA) module and the attention map merging mechanism (AMMM). GMSA efficiently acquires global information while substantially mitigating computational costs in contrast to global multi-head self-attention mechanism. This is accomplished through the strategic utilization of dimension correspondence to align granularity and the reduction of relative position bias parameters, thereby optimizing computational efficiency. The proposed AMMM effectively combines multi-scale attention maps into a unified representation using a fixed mask template, enabling the modeling of global attention mechanism. Experimental evaluations highlight the superior performance of our approach, achieving remarkable mean intersection over union (mIoU) scores of 75.48\% on the challenging Vaihingen dataset and an exceptional 77.90\% on the Potsdam dataset, demonstrating the superiority of our method in precise remote sensing semantic segmentation. Codes are available at https://github.com/interpretty/AMMUNet.
- Open Access
- 17 February 2024
- Published by Springer Nature in Neural Processing Letters
- Vol. 56 (2) , 1-15
Few-Shot Semantic Segmentation via Mask Aggregation
Few-shot semantic segmentation aims to recognize novel classes with only very few labelled data. This challenging task requires mining of the correlation between the query image and the support images. Previous works have typically regarded it as a pixel-wise classification problem. Therefore, various models have been designed to explore the correlation of pixels between the query image and the support images. However, they focus only on pixel-wise correspondence and ignore the overall correlation of objects. In this paper, we introduce a mask-based classification method for addressing this problem. The mask aggregation network, which is a simple mask classification model, is proposed to simultaneously generate a fixed number of masks and their probabilities of being targets. Then, the final segmentation result is obtained by aggregating all the masks according to their locations. Experiments on both the PASCAL- $$5^i$$ and COCO- $$20^i$$ datasets show that our method performs comparably to the state-of-the-art pixel-based methods. This competitive performance demonstrates the potential of mask classification as an alternative baseline method for few-shot semantic segmentation.- 17 February 2024
- Published by Springer Nature in Neural Processing Letters
- Vol. 56 (2) , 1-15
Open AccessFew-Shot Semantic Segmentation via Mask Aggregation
Few-shot semantic segmentation aims to recognize novel classes with only very few labelled data. This challenging task requires mining of the correlation between the query image and the support images. Previous works have typically regarded it as a pixel-wise classification problem. Therefore, various models have been designed to explore the correlation of pixels between the query image and the support images. However, they focus only on pixel-wise correspondence and ignore the overall correlation of objects. In this paper, we introduce a mask-based classification method for addressing this problem. The mask aggregation network, which is a simple mask classification model, is proposed to simultaneously generate a fixed number of masks and their probabilities of being targets. Then, the final segmentation result is obtained by aggregating all the masks according to their locations. Experiments on both the PASCAL- $$5^i$$ and COCO- $$20^i$$ datasets show that our method performs comparably to the state-of-the-art pixel-based methods. This competitive performance demonstrates the potential of mask classification as an alternative baseline method for few-shot semantic segmentation. - Top Cited PapersOpen Access
- 10 February 2020
- Published by MDPI AG in Remote Sensing
- Vol. 12 (3) , 582
Classification of Hyperspectral Image Based on Double-Branch Dual-Attention Mechanism Network
In recent years, researchers have paid increasing attention on hyperspectral image (HSI) classification using deep learning methods. To improve the accuracy and reduce the training samples, we propose a double-branch dual-attention mechanism network (DBDA) for HSI classification in this paper. Two branches are designed in DBDA to capture plenty of spectral and spatial features contained in HSI. Furthermore, a channel attention block and a spatial attention block are applied to these two branches respectively, which enables DBDA to refine and optimize the extracted feature maps. A series of experiments on four hyperspectral datasets show that the proposed framework has superior performance to the state-of-the-art algorithm, especially when the training samples are signally lacking.
- 10 February 2020
- Published by MDPI AG in Remote Sensing
- Vol. 12 (3) , 582
Top Cited PapersOpen AccessClassification of Hyperspectral Image Based on Double-Branch Dual-Attention Mechanism Network
In recent years, researchers have paid increasing attention on hyperspectral image (HSI) classification using deep learning methods. To improve the accuracy and reduce the training samples, we propose a double-branch dual-attention mechanism network (DBDA) for HSI classification in this paper. Two branches are designed in DBDA to capture plenty of spectral and spatial features contained in HSI. Furthermore, a channel attention block and a spatial attention block are applied to these two branches respectively, which enables DBDA to refine and optimize the extracted feature maps. A series of experiments on four hyperspectral datasets show that the proposed framework has superior performance to the state-of-the-art algorithm, especially when the training samples are signally lacking.