26 March 2025 in IEEE Transactions on Geoscience and Remote Sensing
Deep learning-based scene classification methods have long been a key research area in remote sensing imagery due to their wide-ranging applications. Recently, Transformer models have achieved significant progress in computer vision, making Vision Transformers (ViTs) a promising direction for scene classification. However, the spatial complexity of remote sensing imagery poses unique challenges for applying Transformers directly. Manually designing Transformers tailored for remote sensing scene classification is time-consuming under model parameter constraints and requires extensive domain expertise. To address this challenge, Neural Architecture Search (NAS) methods provide an effective solution to construct optimal Transformer architectures for remote sensing scene classification automatically. In this work, we propose SceneFormer, an automated Transformer architecture search framework tailored for scene classification tasks. In SceneFormer, we construct a dedicated search space to search for the optimal Transformer. Moreover, we design a supernet training strategy to train numerous candidate architectures within the search space simultaneously. Furthermore, SceneFormer employs the evolutionary search to find the optimal Transformer architecture under specific resource constraints. Experiments on three high-spatial-resolution (HSR) datasets demonstrate the effectiveness of SceneFormer.
19 February 2025 in IEEE Transactions on Geoscience and Remote Sensing
Recently, deep neural networks have been extensively explored in remote sensing image haze removal and achieved remarkable performance. However, most existing haze removal methods fail to effectively leverage the fusion of spatial and frequency information, which is crucial for learning more representative features. Moreover, the prevalent perceptual loss used in dehazing model training overlooks the diversity among perceptual channels, leading to performance degradation. To address these issues, we propose a Spatial-Frequency Residual-guided Dynamic Perceptual Network (SFRDP-Net) for remote sensing image haze removal. Specifically, we first propose a Residual-guided Spatial-Frequency Interaction (RSFI) module, which incorporates a Bidirectional Residual Complementary Mechanism (BRCM) and a Frequency Residual Enhanced Attention (FREA). Both BRCM and FREA exploit spatial-frequency complementarity to guide more effective fusion of spatial and frequency information, thus enhancing feature representation capability and improving haze removal performance. Furthermore, a Dynamic Channel Weighting Perceptual Loss (DCWP-Loss) is developed to impose constraints with varying strengths on different perceptual channels, advancing the reconstruction of high-quality haze-free images. Experiments on challenging benchmark datasets demonstrate our SFRDP-Net outperforms several state-of-the-art haze removal methods. The code is released publicly at https://github.com/789as-syl/SFRDP-Net.
1 March 2021 in IEEE Transactions on Geoscience and Remote Sensing
Endmember extraction (EE) plays a crucial part in the hyperspectral unmixing (HU) process. To obtain satisfactory EE results, the EE can be considered as the multiobjective optimization problem to optimize the volume maximization (VM) and root-mean-square error (RMSE) simultaneously. However, it is often quite challenging to balance the conflict of these objectives. In order to tackle the challenges of multiobjective EE, we present a ( μ + λ ) multiobjective differential evolution algorithm (( μ +λ )-MODE) based on ranking multiple mutations. In the ( μ + λ )-MODE algorithm, ranking multiple mutations are adopted to create the mutant vectors via the scaling factor pool to enhance the population diversity. Moreover, mutant vectors employ the binary crossover operator to generate the trial vectors through a crossover control parameter pool in ( μ + λ )-MODE to take advantage of the good information of the population. In addition, ( μ + λ )-MODE utilizes the fast nondominated sorting approach to sort the parent and trial vectors, and then selects the elitism offspring as the next population via the ( μ + λ ) selection strategy. Eventually, experimental comparative results in three real HSIs reveal that our proposed ( μ + λ )-MODE is superior to other EE methods.
8 January 2025 in IEEE Transactions on Geoscience and Remote Sensing
Recently, U-shaped neural networks (U-Net) and Full resolution convolutional neural networks (F-Net) have been extensively explored for remote sensing image haze removal, achieving excellent performance. However, downsampling in U-Net leads to significant loss of high-frequency information, while F-Net fails to satisfy the large receptive field demand of remote sensing images, resulting in suboptimal dehazing results for both architectures. Moreover, most existing haze removal methods neglect exploring the correlation between spatial and channel information in feature fusion, which is crucial for restoring image texture details and colors. To address these issues, we propose a Dynamic-Routing 3D-Fusion Network (DR3DF-Net), comprising a Dynamic Routing Features Framework (DRFF) and a 3D Perceptual Feature Fusion (3D-PFF) module. Specifically, the DRFF utilizes a Self-generated Constrained Feature Routing (SCFR) mechanism to learn the most representative features extracted from U-Net, F-Net, and their fused features to enhance clear image reconstruction. Furthermore, the 3D-PFF module enhances interaction between spatial and channel information of multiple features, assigning pixel-level weights for feature fusion, improving dehazed image texture details and colors. Experiments on challenging benchmark datasets demonstrate our DR3DF-Net outperforms several state-of-the-art haze removal methods. The source code is available at https://github.com/lslyttx/DR3DF-Net.
21 May 2024 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Recent advances in satellite remote sensing technology and computer technology have significantly impacted practical applications in remote sensing image segmentation. However, the prevalent hybrid segmentation models that combine Convolutional Neural Networks (CNNs) and Transformers, often overlook the critical exploration of local and global feature correlations across various scales. This exploration is essential for learning more representative features and strengthening context modeling capabilities. Additionally, the decoding layers of these models do not effectively exploit the pixel-level semantic relationships within cross-layer feature maps, thereby limiting the models' ability to discern small object features. To address these challenges, this paper introduces a Multi-directional and Multi-constraint Learning Network (MMLN) designed for semantic segmentation of remote sensing imagery. This network features a Multi-directional Dynamic Complement Decoder (MDCD), which enhances the interaction between local and global features in the feature space, and subsequently improves the feature discrimination within the segmentation network. Moreover, a Multi-constraint Saliency Boundary-adaptive Module (MSBM) is implemented to reinforce the spatial constraints on saliency at the edge regions and ensure semantic consistency along the mask boundaries. This, in turn, augments the segmentation model's capability to detect small objects. The evaluation on four datasets reveals that the MMLN outperforms the existing state-of-the-art methods in remote sensing imagery segmentation. The code is available at https://github.com/zhongyas/MMLN.
19 February 2026 in IEEE Transactions on Medical Imaging
Accurate segmentation of cervical structures in transvaginal ultrasound (TVS) is critical for assessing the risk of spontaneous preterm birth (PTB), yet the scarcity of labeled data limits the performance of supervised learning approaches. This paper introduces the Fetal Ultrasound Grand Challenge (FUGC), the first benchmark for semi-supervised learning in cervical segmentation, hosted at ISBI 2025. FUGC provides a dataset of 890 TVS images, including 500 training images, 90 validation images, and 300 test images. Methods were evaluated using the Dice Similarity Coefficient (DSC), Hausdorff Distance (HD), and runtime (RT), with a weighted combination of 0.4/0.4/0.2. The challenge attracted 10 teams with 82 participants submitting innovative solutions. The best-performing methods for each individual metric achieved 90.26% mDSC, 38.88 mHD, and 32.85 ms RT, respectively. FUGC establishes a standardized benchmark for cervical segmentation, demonstrates the efficacy of semi-supervised methods with limited labeled data, and provides a foundation for AI-assisted clinical PTB risk assessment.