Federated learning enables a large number of clients (such as edge computing devices) to learn a model jointly without data sharing. However, the high amount of communication of the federated learning aggregation algorithm hinders the realisation of artificial intelligence in the last mile. Although FederatedAveraging (FedAvg) is the leading algorithm, its communication cost is still high. The method of communication delay and gradient sparse can reduce the communication cost, but there is no previous work to analyse the relationship and common effects of these two dimensions. Aiming at the problems that federated learning communication is expensive and it has become a training bottleneck, we improve the FedAvg algorithm and propose an adaptive communication frequency FederatedAveraging algorithm (AFedAvg). The gradient sparse operation in the algorithm reduces the quantity of parameters for a single communication, while the communication delay operation allows training to converge faster and obtain smaller losses. The number of sparse parameters is used to select the communication frequency of next round dynamically. Experimental results prove that, the AFedAvg algorithm is superior to the FedAvg and its variants in terms of communication cost. It achieves 2.4X–23.1X communication compression in different data distributions with minimal communication rounds required by the algorithm to converge.

Road extraction techniques based on remote sensing image have significantly advanced. Currently, fully supervised road segmentation neural networks based on remote sensing images require a significant number of densely labeled road samples, limiting their applicability in large-scale scenarios. Consequently, semi-supervised methods that utilize fewer labeled data have gained increasing attention. However, the imbalance between a small quantity of labeled data and a large volume of unlabeled data leads to local detail errors and overall cognitive mistakes in semi-supervised road extraction. To address this challenge, this paper proposes a novel consistency self-training semi-supervised method (CSSnet), which effectively learns from a limited number of labeled data samples and a large amount of unlabeled data. This method integrates self-training semi-supervised segmentation with semi-supervised classification. The semi-supervised segmentation component relies on an enhanced generative adversarial network for semantic segmentation, which significantly reduces local detail errors. The semi-supervised classification component relies on an upgraded mean-teacher network to handle overall cognitive errors. Our method exhibits excellent performance with a modest amount of labeled data. This study was validated on three separate road datasets comprising high-resolution remote sensing satellite images and UAV photographs. Experimental findings showed that our method consistently outperformed state-of-the-art semi-supervised methods and several classic fully supervised methods.

Remote sensing object detection is a difficult task because it often requires real-time feedback through numerous objects in complex environments. In object detection, Feature Pyramids Networks (FPN) have been widely used for better representations based on a multi-scale problem. However, the multiple level features cause detectors’ structures to be complex and makes redundant calculations that slow down the detector. This paper uses a single-layer feature to make the detection lightweight and accurate without relying on Feature Pyramid Structures. We proposed a method called the Cross Stage Partial Strengthen Matching Detector (StrMCsDet). The StrMCsDet generates a single-level feature map architecture in the backbone with a cross stage partial network. To provide an alternative way of replacing the traditional feature pyramid, a multi-scale encoder was designed to compensate the receptive field limitation. Additionally, a stronger matching strategy was proposed to make sure that various scale anchors may be equally matched. The StrMCsDet is different from the conventional full pyramid structure and fully exploits the feature map which deals with a multi-scale encoder. Methods achieved both comparable precision and speed for practical applications. Experiments conducted on the DIOR dataset and the NWPU-VHR-10 dataset achieved 65.6 and 73.5 mAP on 1080 Ti, respectively, which can match the performance of state-of-the-art works. Moreover, StrMCsDet requires less computation and achieved 38.5 FPS on the DIOR dataset.

Extracting roads from remote sensing images holds significant practical value across fields like urban planning, traffic management, and disaster monitoring. Current Convolutional Neural Network (CNN) methods, praised for their robust local feature learning enabled by inductive biases, deliver impressive results. However, they face challenges in capturing global context and accurately extracting the linear features of roads due to their localized receptive fields. To address these shortcomings of traditional methods, this paper proposes a novel parallel encoder architecture that integrates a CNN Encoder Module (CEM) with a Transformer Encoder Module (TEM). The integration combines the CEM’s strength in local feature extraction with the TEM’s ability to incorporate global context, achieving complementary advantages and overcoming limitations of both Transformers and CNNs. Furthermore, the architecture also includes a Linear Convolution Module (LCM), which uses linear convolutions tailored to the shape and distribution of roads. By capturing image features in four specific directions, the LCM significantly improves the model’s ability to detect and represent global and linear road features. Experimental results demonstrate that our proposed method achieves substantial improvements on the German-Street Dataset and the Massachusetts Roads Dataset, increasing the Intersection over Union (IoU) of road class by at least 3% and the overall F1 score by at least 2%.

The widely deployed devices in Internet of Things (IoT) have opened up a large amount of IoT data. Recently, federated learning emerges as a promising solution aiming to protect user privacy on IoT devices by training a globally shared model. However, the devices in the complex IoT environments pose great challenge to federate learning, which is vulnerable to gradient-based reconstruction attacks. In this paper, we discuss the relationships between the security of federated learning model and optimization technologies of decreasing communication overhead comprehensively. To promote the efficiency and security, we propose a defence strategy of federated learning which is suitable to resource-constrained IoT devices. The adaptive communication strategy is to adjust the frequency and parameter compression by analysing the training loss to ensure the security of the model. The experiments show the efficiency of our proposed method to decrease communication overhead, while preventing privacy data leakage.