In recent years, Neural Architecture Search (NAS) has garnered widespread attention in the field of deep learning due to its significant potential in automating the construction of deep models. However, existing NAS methods primarily focus on optimizing network architecture, utilizing search strategies to find a high-performing network architecture within the search space as effectively as possible. And this process often requires repetitive and continuous searching and evaluation. With the significant advancements in Artificial Intelligence Generated Content (AIGC), an increasing number of researchers are utilizing deep generative models to create graph data. Neural network architecture can be viewed as Directed Acyclic Graphs(DAG) with labeled nodes. Therefore, we propose a graph generation model based on Graph Convolutional Network (GCN) and Generative Adversarial Network(GAN) to generate network architecture. With the aim of avoiding the repetitive and continuous searching and evaluation process in NAS. The CNN architecture generated by our algorithm in this paper achieves an accuracy of 94.37% on the CIFAR-10 dataset. While it may not outperform many other CNN models in terms of performance, it doesn’t require any expert knowledge and is generated automatically by the model, avoiding the need for repetitive searching and evaluation.

Deep learning-based object detection has seen substantial advancements, however, its practical deployment is often constrained by the need for large-scale labeled datasets. This limitation becomes even more critical in remote sensing imagery, where objects are densely distributed and exhibit significant scale variations. To address these challenges, we introduce RemoteDPL, a novel semi-supervised object detection (SSOD) framework that leverages dense pseudo-labeling (DPL) and multi-scale learning. RemoteDPL offers three key contributions. First, a fusion module is designed to dynamically integrate spatial and channel features across scales, improving detection across varied object sizes. Second, an instance density prediction branch is introduced to support pseudo-label mining, enhancing detection performance in densely populated regions. Lastly, we propose a two-stage pseudo-label filtering strategy that first selects "pending" class predictions and then refines them using a joint confidence score based on both classification and density information. Extensive experiments on the DOTA-v1.0 and NWPU datasets confirm the effectiveness of RemoteDPL, demonstrating its clear advantage over existing state-of-the-art (SOTA) semi-supervised object detection methods. On the NWPU dataset, RemoteDPL outperforms the SOTA baseline by +3.44%, +1.10%, and +1.62% under the settings of data labelled with 30%, 40%, and 50%, respectively, highlighting its strong capability in low-label remote sensing scenarios.

Apart from the applications of navigation, positioning, and timing, the Global Navigation Satellite System (GNSS) plays an important role in improving the quality and reliability of numerical weather prediction (NWP) models. However, the difference and contribution of assimilating GNSS-derived Zenith Total Delay (ZTD) and Precipitable Water Vapor (PWV) to forecast result are less investigated, which becomes the focus of this study. A unified method of assimilating GNSS-derived ZTD/PWV is first proposed, and their difference and contribution to the forecasting performance of Weather Research and Forecasting (WRF) model are quantitatively evaluated by focusing on the multiple meteorological parameters, such as precipitation, relative humidity, temperature, and pressure. In addition, the effects of magnitude and seasonal characteristics of GNSS-derived ZTD/PWV on the WRF model are further analyzed during a case of severe convective weather. Central and eastern China is selected as the study area, and 287 meteorological stations, 452 GNSS/Met stations, and 11 radiosonde stations are selected over the whole year of 2018. Results indicate that the assimilation of GNSS-derived ZTD/PWV, particularly ZTD, enhances the forecast accuracy of different meteorological parameters, and the positive contribution degree increases as the magnitude of GNSS-derived ZTD/PWV increases. Compared with the traditional method, the root mean square error reductions of precipitation, relative humidity, temperature, and pressure generated by a unified method of assimilating GNSS-derived ZTD/PWV are 31.9%/22.7%, 54.6%/44.0%, 44.7%/35.7%, and 37.1%/24.2%, respectively. These results show the feasibility and effectiveness of the proposed data assimilation method and verify the positive contribution of GNSS-derived tropospheric products in improving the performance of WRF model, especially for severe convective event nowcasting.

Deep-learning-based object detection has recently played an increasingly important role in analyzing geographic spatial information. However, object detection performance is strongly correlated with the quality and quantity of manually labeled data. Furthermore, object detection in Remote Sensing differs from natural scenes and faces two challenges: 1) Dense instance distribution and 2) Significant scale variations. These issues also contribute to the difficulty of manual annotation. To this end, based on a dense pseudo-labeling framework and multi-scale learning, this paper proposes a novel semi-supervised object detection (SSOD) framework for remote sensing, namely RemoteDPL. Firstly, a fusion module is proposed to adaptively integrate spatial and channel features of images at different scales, improving the detection of objects at various scales. Second, a specialized branch predicts instance density and aids in pseudo-label mining to enhance detection in dense scenarios. Finally, a two-stage filtering strategy is devised for pseudo-label mining, which first filters to obtain the "pending" class prediction boxes and then further filters this portion of prediction boxes to obtain the pseudo-labels according to the joint confidence based on the classification and density scores. Extensive experiments on DOTA-v1.0 have demonstrated that our proposed RemoteDPL surpasses the current state-of-the-art SSOD methods in various semi-supervised settings.

Anomaly detection in computer vision aims to detect outliers from input image data. Examples include texture defect detection and semantic discrepancy detection. However, existing methods are limited in detecting both types of anomalies, especially for the latter. In this work, we propose a novel semantics-aware normalizing flow model to address the above challenges. First, we employ the semantic features extracted from a backbone network as the initial input of the normalizing flow model, which learns the mapping from the normal data to a normal distribution according to semantic attributes, thus enhances the discrimination of semantic anomaly detection. Second, we design a new feature fusion module in the normalizing flow model to integrate texture features and semantic features, which can substantially improve the fitting of the distribution function with input data, thus achieving improved performance for the detection of both types of anomalies. Extensive experiments on five well-known datasets for semantic anomaly detection show that the proposed method outperforms the state-of-the-art baselines. The codes will be available at https://github.com/SYLan2019/SANF-AD.