Research on underwater image processing has increased significantly in the past decade due to the precious resources that exist underwater. However, it is still a challenging problem to restore degraded underwater images. Existing prior-based methods show limited performance in many cases due to their reliance on hand-crafted features. Therefore, in this paper, we propose an effective unsupervised generative adversarial network(GAN) for underwater image restoration. Specifically, we embed the idea of contrastive learning into the model. The method encourages two elements (corresponding patches) to map the similar points in the learned feature space relative to other elements (other patches) in the data set, and maximizes the mutual information between input and output through PatchNCE loss. We design a query attention (Que-Attn) module, which compares feature distances in the source domain, and gives an attention matrix and probability distribution for each row. We then select queries based on their importance measure calculated from the distribution. We also verify its generalization performance on several benchmark datasets. Experiments and comparison with the state-of-the-art methods show that our model outperforms others.

Low-visibility haze environments, marked by their inherent low contrast and high brightness, present a formidable challenge to the precision and robustness of conventional object detection algorithms. This paper introduces an enhanced object detection framework for YOLOv9s tailored for low-visibility haze conditions, capitalizing on the merits of contrastive learning for optimizing local feature details, as well as the benefits of multiscale attention mechanisms and dynamic focusing mechanisms for achieving real-time global quality optimization. Specifically, the framework incorporates Patchwise Contrastive Learning to fortify the correlation among positive samples within image patches, effectively reducing negative sample interference and enhancing the model’s capability to discern subtle local features of haze-impacted images. Additionally, the integration of Efficient Multi-Scale Attention and the Wise-IoU Dynamic Focusing Mechanism enhances the algorithm’s sensitivity to channel, spatial orientation, and locational information. Furthermore, the implementation of a nonmonotonic strategy for dynamically adjusting the loss function weights significantly boosts the model’s detection precision and training efficiency. Comprehensive experimental evaluations of the COCO2017 fog-augmented dataset indicate that the proposed algorithm surpasses current state-of-the-art techniques in various assessment metrics, including precision, recall, and mean average precision (mAP). Our source code is available at: https://github.com/PaTinLei/EOD.

Graph neural networks (GNN) have achieved remarkable success in various domains, yet incomplete node attribute data can significantly impair their performance. Graph completion learning (GCL) methods have been developed to address this issue, aiming to reconstruct missing node attributes based on existing structural relationships. However, the accuracy of these reconstructions is highly dependent on the quality of the initial graph structure, which often contains errors and inaccuracies. This paper proposes the evolving graph structure (EGS) framework for semi-supervised node classification with missing attributes. EGS dynamically reconstructs the attributes of the nodes and updates the graph structure through an alternating optimization approach. Specifically, we introduce a Dirichlet Energy function with dual constraints to formulate the objective function, which jointly optimizes node structure relationships and attribute reconstruction. Extensive experiments on five benchmark datasets, with different missing rates, and with seven GNN variants demonstrate the effectiveness of EGS, achieving state-of-the-art performance compared to existing GCL methods.

The complex and variable operating conditions of sucker-rod pumping wells pose a significant challenge for the timely and accurate identification of oil well operating conditions. Effective deep learning based on measured multi-source data obtained from the sucker-rod pumping well production site offers a promising solution to the challenge. However, existing deep learning-based operating condition recognition methods are constrained by several factors: the limitations of traditional operating condition recognition methods based on single-source and multi-source data, the need for large amounts of labeled data for training, and the high robustness requirement for recognizing complex and variable data. Therefore, we propose a semi-supervised class-incremental sucker-rod pumping well operating condition recognition method based on measured multi-source data distillation. Firstly, we select measured ground dynamometer cards and measured electrical power cards as information sources, and construct the graph neural network teacher models for data sources, and dynamically fuse the prediction probability of each teacher model through the Squeeze-and-Excitation attention mechanism. Then, we introduce a multi-source data distillation loss. It uses Kullback-Leibler (KL) divergence to measure the difference between the output logic of the teacher and student models. This helps reduce the forgetting of old operating condition category knowledge during class-incremental learning. Finally, we employ a multi-source semi-supervised graph classification method based on enhanced label propagation, which improves the label propagation method through a logistic regression classifier. This method can deeply explore the potential relationship between labeled and unlabeled samples, so as to further enhance the classification performance. Extensive experimental results show that the proposed method achieves superior recognition performance and enhanced engineering practicality in real-world class-incremental oil extraction production scenarios with complex and variable operating conditions.

To identify various oil well working conditions more accurately and practically from massive image data collected by multiple measured information sources of sucker-rod pumping wells, this paper proposes a working condition recognition method with three key aspects: curvelet pooling optimization technology, multi-source attention mechanism fusion feature extraction technology, and multi-source semi-supervised classification deep learning. Specifically: (a) Curvelet pooling optimization technology. We introduce the second-generation curvelet transform into the ResNet-50 pooling layer and adopt a collaborative learning pooling strategy of low-frequency and high-frequency information from the raw data decomposed via curvelet transform instead of max-pooling. This enhances the neural network’s capability to capture detailed features of complex image data. (b) Multi-source attention mechanism fusion feature extraction technology. We selected two information sources: measured ground dynamometer cards and measured electrical power cards. The multi-head self-attention mechanism enables interactive complementarity between curvelet-decomposed image data from each information source, while achieving dynamic weighted fusion of the interactive complementary data via the adaptive attention mechanism. This process yields optimal global feature representations of multi-source fused data. (c) Multi-source semi-supervised classification deep learning. By integrating multi-source fused feature data with a semi-supervised classification algorithm based on the dual strategy of dynamic adjustment of pseudo-label confidence and self-adaptive class fairness regularization, the method leverages abundant multi-source unlabeled samples to improve model classification performance and generalization ability under limited labeled training samples. This further enhances the accuracy and practicality of condition recognition. Experimental data were collected from a high-pressure, low-permeability, thin oil reservoir block in an oilfield in China. Extensive experiments demonstrate that the proposed method efficiently processes measured information source data in the sucker-rod pumping production system, improves the performance of traditional deep learning frameworks, explores the intrinsic correlations among multiple measured information source data of oil wells, and utilizes massive unlabeled working condition data to enhance the working condition recognition effect and engineering practicability with a minimal number of labeled samples. Code is available at https://github.com/Yoick/AMMFFECP .