Federated learning (FL) has been widely used in medical image processing to protect data privacy, but it has issues with data heterogeneity. Personalized federated learning have emerged to tackle these issues but often focuses too much on personalized models at the expense of global models. To address these problem, we propose a personalized federated learning method CoGAP, using collaborative optimization to enhance both personalized and global model performance. On the client side, it employs adaptive weight aggregation to initialize personalized models and uses a training strategy based on L2regularization. On the server side, it implements a gradient accumulation-based aggregation method. These modules facilitate a collaborative optimization process where the global model guides the personalized models, and the personalized models provide positive feedback to the global model, ultimately leading to mutual improvement for both. We conducted extensive comparative experiments on the OCT2017 dataset, as well as the BloodMnist and PathMnist (subsets from MedMnist), to evaluate both global and personalized models. Results show that CoGAP own a unique strength which not only outperforms other personalized federated learning methods in personalization capability while also remarkably achieving satisfying global generalization. Code is available at https://github.com/lcyCQUPT/CoGAP.

Federated Learning (FL) is an advanced technology that tackles the challenge of blocked data arising from privacy concerns, enabling the training of deep learning models without the need for data sharing. However, FL faces difficulties with heterogeneous data and limited annotations in medical image segmentation. Motivated by this discovery, this study proposes a novel hybrid-supervised federated learning method (FedSLAG) that explores various types of annotations in medical imaging. To focus more on weakly-supervised and unsupervised scenarios within hybrid-supervised learning, a federated Gaussian enhancement module was proposed for heterogeneous sparse annotations (points and scribbles). The feature extraction module combines the features of multiple weakly-supervised clients and establishes the correlation of similar pixels, thus making up for the deficiency of scarce annotations and the insufficient feature extraction capability of a single machine. Then, a two-stage broadcast mechanism based on supervision sparsity was proposed to alleviate optimization deviation in local models. Experiments on breast tumor and skin lesion segmentation tasks demonstrate significant efficiency gains as well as highly competitive segmentation accuracy in many hybrid-supervised situations. Our codes are available at: https://github.com/TrivenDev/FedSLAG.

Low-light vision remains a fundamental challenge in computer vision due to severe illumination degradation, which significantly affects the performance of downstream tasks such as detection and segmentation. While recent state-of-the-art methods have improved performance through invariant feature learning modules, they still fall short due to incomplete modeling of low-light conditions. Therefore, we revisit low-light image formation and extend the classical Lambertian model to better characterize low-light conditions. By shifting our analysis to the frequency domain, we theoretically prove that the frequency-domain channel ratio can be leveraged to extract illumination-invariant features via a structured filtering process. We then propose a novel and end-to-end trainable module named \textbf{F}requency-domain \textbf{R}adial \textbf{B}asis \textbf{Net}work (\textbf{FRBNet}), which integrates the frequency-domain channel ratio operation with a learnable frequency domain filter for the overall illumination-invariant feature enhancement. As a plug-and-play module, FRBNet can be integrated into existing networks for low-light downstream tasks without modifying loss functions. Extensive experiments across various downstream tasks demonstrate that FRBNet achieves superior performance, including +2.2 mAP for dark object detection and +2.9 mIoU for nighttime segmentation. Code is available at: \url{https://github.com/Sing-Forevet/FRBNet}.

Cloud-free image reconstruction is of great significance for improving the quality of optical satellite images that are vulnerable to bad weather. When cloud cover makes it impossible to obtain information under the cloud, auxiliary data is indispensable to guide the reconstruction of the cloud-contaminated area. Additionally, the areas that require continuous observation are mostly regions with complex features, which puts higher demands on the restoration of texture, color, and other details in data reconstruction. In this paper, we propose a Transformer-based generative adversarial network for cloud-free multispectral image reconstruction via multi-sensor data fusion in satellite images (TransGAN-CFR). Synthetic Aperture Radar (SAR) images that are not affected by clouds are used as auxiliary data and paired with cloudy optical images into the GAN generator. To take advantage of the deep-shallow features and global-local geographical proximity in remote sensing images, the proposed generator employs a hierarchical Encoder-Decoder structure, in which the Transformer blocks adopt a non-overlapping window multi-head self-attention (WMSA) mechanism and a modified feed-forward network though depth-wise convolutions and the gating mechanism. Besides, we introduce a Triplet loss function specifically designed for cloud removal tasks to provide the generated cloud-less image with greater proximity to the ground truth. Compared with seven state-of-the-art deep learning-based cloud removal models, our network can yield more natural cloud-free images with better visual performance and more accurate results in quantitative evaluation on the SEN12MS-CR dataset.

Due to the impact of climate change, the frequency of flood events has increased in recent years, which puts forward an urgent need for timely and accurate flood mapping for emergency response. As the synthetic aperture radar (SAR) enables all-time monitoring regardless of bad weather conditions, it fits far better than passive optical sensors to delineate submerged areas during flood events. However, the universal, rapid, and accurate detection of flood extent remains a challenge. Drawing inspiration from the analysis of time-series variation in representative ground objects caused by flood events, as observed in a dual-polarized SAR time series over a hydrological year, we construct a novel window-based variation model. This model can be used to capture both long-term trends and short-term fluctuations of flood features across different polarization modes. Subsequently, we introduce an unsupervised flood mapping framework that integrates spatiotemporal flood features extracted by fuzzy-based methods. Given the distinct backscatter value of short vegetation, a flooded short vegetation activation model is designed and performed to enhance flood mapping accuracy in complex regions. The proposed method, tested on the 2020 East Dongting Lake flood in China, surpasses three unsupervised flood mapping methods and two deep learning methods in terms of quantitative evaluation and visual performance. The uncertainty of our proposed framework is tested through parameter sensitivity analyses, comparisons with flood mapping results from other sensor images, and extensive experiments on floods at different locations and times, thereby demonstrating its effectiveness, stability, and universality.

Hyperspectral image classification has been a constant hot topic in remote sensing field, and achieved significant progress recently. Until now, most of the existing works are based on high-quality noise-free datasets, whereas in real applications, the images are often degraded by different types of noise, which makes the noise sensitivity become one of the key issues for classification assessment. In this paper, we study the noise effects on hyperspectral image classification including Guassian, salt-and-pepper, and stripe noise. The experimental results shows that noise has varying degrees of negative effects on different hyperspectral classification methods, which provides instructional information for method design and selection under noise environment in actual classification applications.

Fusion of hyperspectral images (HSIs) and multispectral images (MSIs) with different resolutions is an active research topic in the field of remote sensing. However, HSI-MSI fusion assessments in existing researches are basically conducted on simulated data gone through spectral or spatial downsampling, which cannot reflect the actual performances of fusion methods in application scenarios. To conquer this problem, a new remote sensing dataset- Hunan UAV-borne HSIs and MSIs fusion(HNU-HMiF) dataset is provided in this paper. The proposed dataset contains fine registered hyperspectral and multispectral image pairs captured by unmanned aerial vehicle (UAV) covering different ground objects, and can be used to evaluate, select, and even develop fusion methods for users or researchers. Successful applications including method evaluation and comparison confirm the validity and reliability of the proposed dataset.