Fine-grained classification of ship targets is an important task in remote sensing, having numerous applications in military reconnaissance and sea surveillance. Due to the influence of various imaging factors, ship targets in remote sensing images have considerable inter-class similarity and intra-class difference, which brings significant challenges to fine-grained classification. In response, we developed a contrastive learning network based on causal attention (C2Net) to improve the model’s fine-grained identification ability from local details. The asynchronous feature learning mode of “decoupling + aggregation” is adopted to reduce the mutual influence between local features and improve the quality of local features. In the decoupling stage, the feature vectors of each part of the ship targets are de-correlated using a decoupling function to prevent feature adhesion. Considering the possibility of false associations between results and features, the decoupled part is designed based on the counterfactual causal attention network to enhance the model’s predictive logic. In the aggregation stage, the local attention weight learned in the decoupling stage is used to carry out feature fusion on the trunk feature weight. Then, the proposed feature re-association module is used to re-associate and integrate the target local information contained in the fusion feature to obtain the target feature vector. Finally, the aggregation function is used to complete the clustering process of the target feature vectors and fine-grained classification is realized. Using two large-scale datasets, the experimental results show that the proposed C2Net method had better fine-grained classification than other methods.

Remote sensing ship detection is a hotspot in computer vision, which is vital in both military and civilian fields. Nevertheless, the arbitrary orientation and dense arrangement of ship targets impose significant challenges in high-precision detection. Although research on this problem has progressed, high-precision detection is still limited by angular prediction accuracy. To tackle the issue, we start with angle prediction and propose a Dynamic Adjusting Labels (DAL) strategy based on Binary Coded Label (BCL). DAL strategy dynamically adjusts the ground-truth coded labels in the training process to guide angle coding for tendency learning. This strengthens the coupling between the angle coding bits and improves the performance of small granularity intervals. Due to the angle interval granularity difference, the learning difficulty of the coding layers and the convergence speed vary significantly. Aiming at this problem, we add a gradient truncation mechanism to each coding bit loss. The mechanism can effectively balance the coding layers’ learning strength and enhance the model’s training emphasis on coding bits corresponding to small granularity intervals, avoiding the effect of coding bits learning imbalance on angle prediction. Extensive experiments based on three public datasets demonstrate our method’s superiority in high-precision detection and state-of-the-art performance. Our code is available at https://github.com/lirunsheng2008/SDALS.

In the era of information explosion, the effective configuration of labels on maps is crucial for the rapid comprehension of information. The point-feature label placement problem, particularly in large-scale and high-density scenarios with spatial mutual-exclusion constraints, is a classic NP-hard discrete optimization challenge. Existing metaheuristic algorithms (e.g., Simulated Annealing and Genetic Algorithm) often struggle to achieve high-quality global layouts due to their propensity to become trapped in local optima, inefficient random point-selection processes, and inadequate modeling of the spatial mutual-exclusion and blocking constraints between labels. To address these limitations, this paper proposes a Progressive Reinforcement Learning (PRL) algorithm specifically tailored for the point-feature label placement problem. The algorithm models the label placement process as a sequential decision-making problem within the Reinforcement Learning framework, optimized through agent–environment interaction. Its core design comprises the following: (1) a staircase-like policy learning mechanism that shifts from “broad exploration in the early stage to precise exploitation in the later stage” to balance global search and local optimization; (2) a data mining-based Intelligent Action Screening (IAS) mechanism, which dynamically identifies and prioritizes “high-value action points” critical for improving layout quality by constructing the “Contribution Decline Degree” and “Contribution Support Degree” metrics. Experiments on large-scale real-world POI datasets (10,000, 20,000, and 32,312 points) demonstrate that the proposed algorithm significantly outperforms 13 state-of-the-art comparative algorithms, including Simulated Annealing, Genetic Algorithm, Differential Evolution, POPMUSIC, and DBSCAN, in terms of both placement quality and the number of successfully placed labels. It exhibits remarkable adaptability and competitiveness in handling high-density and complex scenarios.