To address the challenges of morphological similarity and the resulting difficulty in classifying vehicle damage images uploaded by clients for auto insurance claims, a model named ResAWDNet was proposed for vehicle damage classification. Firstly, to effectively augment the model’s capacity for extracting damage features, the traditional down sampling operation was replaced with weighted dynamic convolution. This approach dynamically adjusted the weights of convolutional kernels based on the input features, thereby enhancing the model’s adaptability to features of varying scales and orientations. As a result, it enabled more precise capture of the subtle differences in vehicle damage. Secondly, to ensure that the model could concentrate on the salient discriminative regions and feature channels within the images, a dual attention mechanism was embedded after the convolutional layers of the backbone network. This mechanism concurrently learned the important weights in both spatial and channel dimensions, significantly enhancing the model’s ability to capture crucial information. Consequently, it further enhanced the decision-making accuracy of the model in the task of vehicle damage classification. Finally, experimental validation was conducted based on a dataset of vehicle damage images sourced from real accident cases. The experimental results demonstrated that the ResAWDNet model was feasible and offered significant advantages for vehicle damage classification tasks, achieving an accuracy rate of 73.79%. Compared with baseline models, ResAWDNet achieved higher accuracy in classifying multiple types of damages, robustly validating the effectiveness of the proposed model.

Traditional 3D point-cloud classification methods tend to suffer from insufficient generalization and catastrophic forgetting in Few-Shot Class-incremental Learning (FSCIL) scenarios. The pretrained vision-language model CLIP (Contrastive Language-Image Pre-training), which contains rich 2D shape priors, has been shown to effectively enhance 3D FSCIL performance. However, existing CLIP-based frameworks still lack flexibility and adaptability in multimodal feature extraction and fusion, which limits classification accuracy during incremental stages. To address these shortcomings, a 3D FSCIL approach with deeply fused multimodal features was proposed. An adaptive adapter based on gated units and residual blocks was introduced to achieve multi-scale feature alignment and redundancy suppression, and a multimodal global feature dynamic fusion module with self-attention was designed to adaptively adjust the weight allocation of different feature streams according to sample characteristics, thereby obtaining more consistent and complementary fused representations. Specifically, point clouds were rendered into multi-view depth maps, and features were extracted using both the original CLIP visual encoder and a CLIP encoder pretrained on depth maps, combined with point-cloud geometric features. After processing through the adaptive adapter, these features were fed into the attention-based fusion module and aligned with semantic features extracted by the CLIP text encoder for classification. In addition, contrastive learning loss, multi-view and geometric perturbation-based data augmentation strategies, and a memory-replay mechanism were incorporated to effectively mitigate overfitting and forgetting under few-shot conditions. Experiments on ShapeNet, ModelNet, and CO3D demonstrated that the proposed method consistently achieved higher accuracy across incremental stages compared with existing 3D FSCIL approaches, while significantly reducing both relative accuracy drop rates and maximum stage fluctuations.

Few-shot image generation has important application value in fields such as medical imaging and artistic creation. In recent years, significant research progress has been made in this task, with mainstream approaches typically relying on transferring generative models pretrained on large-scale source domain datasets to target domains to mitigate data-scarcity challenges. However, when substantial semantic gaps exist between source and target domains, direct transfer often introduced incompatible source-specific features, degrading image realism and style consistency. Although existing methods have removed redundant features via static pruning strategies, such as fixed-threshold filter pruning, they struggle to adapt to the dynamic evolution of features across different layers of deep networks, often resulting in the mistaken removal of general low-level features while retaining redundant high-level ones, thereby affecting the adaptation performance and generation quality of the model. To address this, a dynamic pruning method based on filter-importance estimation was proposed. Specifically, the method continuously tracked the changes in Fisher information of each layer’s filters during training to evaluate their importance for image generation quality. Based on the Fisher information, a cumulative importance weight-based adaptive pruning mechanism was constructed to dynamically determine the pruning ratio for each layer, enabling more precise removal of redundant or incompatible filters while preserving general structural semantic information. Experiments were conducted on several representative few-shot target domains, and results showed that the proposed method significantly outperformed existing approaches in terms of image quality (Frechet Inception Distance, FID) and image diversity (Intra-domain Learned Perceptual Image Patch Similarity, Intra-LPIPS). In target domains exhibiting significant semantic differences from the source domain, the proposed method achieved superior FID scores compared with the current state-of-the-art methods, demonstrating its stability and superiority for cross-domain few-shot image generation tasks.

Given that the impact of rough surfaces on assembly accuracy had been insufficiently considered in the existing assembly accuracy prediction for complex products, leading to inaccurate precision prediction and limited practical assembly applicability, an assembly-accuracy prediction method considering rough surfaces was proposed. Firstly, an assembly-accuracy information model was constructed to express mating feature, geometric tolerance, and roughness information. Based on the model, an assembly-precision knowledge graph was constructed. Secondly, a geometric-tolerance representation model was established based on the Small-Displacement Torsor (SDT) theory; a simulation method for rough surfaces of plane and cylindrical parts as well as a determination method of SDT expressions were studied. Thirdly, the error-propagation path of the assembly was determined according to the assembly sequence, and a pose-relationship graph for the assembly was constructed. Then, the assembly-precision prediction was achieved using a Jacobian-torsor model. Finally, the feasibility of the method was verified using the crank-connecting-rod mechanism of a specific construction-machine model as an example. The simulation results demonstrated that the method could achieve accurate assembly-precision prediction and provided valuable guidance for practical assembly operations.

In roof engineering design, the rationality of equipment maintenance circulation routes directly impacts maintenance efficiency and safety. Traditional design methods often rely on empirical judgment, making it difficult to sufficiently evaluate the rationality of these routes during the design phase. To address this, a hybrid algorithm combining graph theory with an improved A* algorithm was developed. Integrated with Building Information Modeling (BIM) technology, an intelligent analysis and design tool for roof equipment maintenance circulation routes was created to address the shortcomings of traditional design via digital model-based route analysis. First, the roof was converted into a weighted equivalent grid map using collision detection and an octree algorithm. Next, an improved A* algorithm was employed to optimize the maintenance paths, comprehensively considering equipment collision volumes and spatial constraints to calculate the optimal maintenance circulation route and evaluate the rationality of detailed route-area design. Finally, the intelligent analysis and design tool based on this algorithm was tested on an actual project. Experimental results demonstrated that the algorithm accurately revealed potential spatial conflicts and irrational layouts, providing data to support design optimization, and enhanced design rationality and operability; it also improved efficiency by more than five times compared with traditional manual design. The intelligent analysis tool based on this algorithm is currently in use in several projects by the Shanghai Construction (No.4) Group Co., Ltd.

With the rapid development of deep learning, remarkable achievements have been made in image classification and related tasks. However, the success of these models heavily relies on large amounts of high-quality labeled data. In real-world applications, labeled data is often scarce, and manual annotation is time-consuming, labor-intensive, and costly, which limits the scalability and deployment of deep learning models. In recent years, active learning has gained significant attention due to its ability to improve model performance under limited annotation budgets. The core idea of active learning is to select the most valuable data for labeling based on certain criteria such as uncertainty, diversity, or representativeness. To address the limitations of traditional active learning methods, which often rely on manually designed heuristic sampling strategies that struggle to adapt to different task scenarios and are difficult to dynamically optimize, a Smart Reinforcement Active Learning (SRAL) approach for image classification is proposed. The sample selection process is modeled as a MARKOV DECISION PRocess (MDP), leveraging reinforcement learning’s adaptive strategy optimization ability to guide the model in dynamically selecting the most valuable samples from the unlabeled data for labeling. In this framework, the state is represented by features extracted from the unlabeled samples, the action indicates whether a sample should be selected for labeling, and the reward function is defined as the change in model accuracy after incorporating the selected sample into the training set. The Actor-Critic algorithm is adopted to optimize the sampling policy, and uncertainty-based heuristic ranking is incorporated as auxiliary information to improve the learning efficiency. Experimental results demonstrate that the proposed SRAL method significantly improves classification accuracy under the same labeling budget compared to other active learning approaches on datasets such as CIFAR-10, SVHN, and FASHION-MNIST. Furthermore, SRAL exhibits robust stability and strong generalization ability across these datasets. This confirms the effectiveness and advantages of SRAL in enhancing the performance of image classification models.

Currently the mainstream enveloping box methods are widely used in 3D scene rendering, ray tracing, and collision detection tasks; however, these methods suffer from the problems of low space utilization and insufficient fitting accuracy in fitting complex geometries, which are difficult to ensure strict conservatism and still have room for improvement in reducing false detection rates. To address these issues, a conservative bounding-box construction method combining implicit geometric coding and Lipschitz constraints was proposed. Implicit geometric coding mapped the input coordinates to a high-dimensional space via position coding, thus capturing local and global geometric information and improving bounding-box adaptability. A trainable Lipschitz-constrained linear layer was introduced to dynamically adjust Lipschitz constants control gradient changes, and Lipschitz regularization loss was combined with dynamically weighted cross-entropy loss to reduce the FP rate while optimizing the boundary fitting. The experimental results demonstrated that the method can achieve a false-negative rate of 0 on multiple 3D models and reduce the false-detection rate by up to 3.1% compared to the benchmark method, and improve the single-ray query method by 1.7 ms, providing a highly efficient and robust solution for high-precision conservative bounding box fitting.

As large models continue to grow in scale, the memory footprint and computational overhead of model inference have become critical challenges. Mixed-precision quantization is an effective approach to reduce resource consumption, but existing methods suffer from insufficient outlier handling, significant quantization accuracy loss, and inefficient memory access. To address these issues, a memory-aligned mixed-precision quantization method for large models was proposed. First, weights were divided into SIMD-aligned groups, and outlier groups were identified via group-wise significance analysis, with high-significance groups quantized to 8 bit and others to 2 bit. A block-wise compensation strategy was introduced to mitigate accuracy degradation caused by 2 bit quantization. Furthermore, an efficient packing and storage scheme was designed for mixed-precision weights, where a bitmap was used to record the bit width of each data block, enabling random access. Experimental results demonstrated that the proposed method significantly reduced memory usage and improved computational efficiency while maintaining model accuracy. Specifically, on Llama2-7 B/13 B/70 B, the approach achieved perplexity reductions of 8.13/2.84/1.37 on WikiText-2 and 5.80 on C4 relative to state-of-the-art baselines. The quantized 70 B model reduced weight storage by approximately 87% compared with BF16. Across seven QA benchmarks, an average accuracy gain of 6.24% was achieved. Last, these results indicated that a mixed-precision quantization method for large language models via memory alignment could simultaneously improve compression ratio, memory-access efficiency, and overall model performance.

Existing research on multi-view stereo scheme utilizes depth-estimation algorithms to achieve stereo representation by establishing a mapping relationship between the physical and digital worlds. Supervised learning-based neural networks have achieved accurate and high-fidelity 3D reconstruction results through training. However, in-the-wild visual reconstruction remains challenging due to the lack of rendered depth priors and wide-baseline characteristics of images. A novel system was proposed to obtain optimized depth for naturally collected multi-view images without prior information by applying an unsupervised learning network and semantically optimized Neural Radiation Field (NeRF) rendering. First, preliminary depth information for wild multi-view images were produced without ground truth based on unsupervised deep learning. Subsequently, in a separate NeRF module, a diffusion model was used to construct a surface semantic rendering loss, enabling a fine-grained volumetric representation. Experimental results on the benchmark dataset validated the performance of the proposed system by improving an average of 24.6% of the overall metrics, compared with other state-of-the-art schemes. A novel wild wide-baseline dataset was also applied to verify the generalization performance, and the proposed system reduced the reconstruction error by up to 40.8% compared with all methods.

In night-vision environments, image quality was significantly degraded by glare from intense light sources, impairing the performance of night-vision assisted driving systems. Existing flare-removal algorithms suffer from limited robustness, high computational complexity, and loss of light-source information. To address these challenges, a lightweight image flare-removal method, Night Flare Removal Network+ (NFR-Net+), was proposed to enhance image clarity while meeting the real-time computational demands of mobile devices. The approach first incorporated a feature-filtering mechanism combined with residual connection strategies to strengthen feature extraction capabilities, effectively mitigating overfitting and ensuring robust flare removal across diverse lighting conditions and flare types. Additionally, a nonlinear, activation-free feature attention module was introduced. Via a lightweight design, an efficient attention mechanism was constructed that significantly improved image-detail reconstruction while reducing model parameters by approximately 8.28% and runtime memory by about 11.1%, thereby optimizing computational efficiency. To tackle the issue of diminished image naturalness due to excessive light-source removal in traditional methods, an enhanced light-source extraction module was developed within the segmentation network. This module employed an improved light-source separation strategy to accurately preserve brightness and texture details in light-source regions, ensuring the authenticity and naturalness of output images. Experimental results demonstrated that NFR-Net+ surpassed state-of-the-art methods on image quality metrics such as Structural Similarity Index Measure (SSIM), Peak Signal-to-Noise Ratio (PSNR), and Learned Perceptual Image Patch Similarity (LPIPS), exhibiting superior flare-removal performance and detail preservation. The method also demonstrated strong adaptability across various night-vision scenarios and hardware devices, fulfilling the efficiency requirements for real-time processing. Ablation studies further validated the effectiveness of individual components, highlighting the critical role of feature filtering and attention mechanisms in balancing performance and resource consumption. This approach provided an efficient, lightweight solution for applications such as nighttime autonomous driving and intelligent surveillance.