Internal disease in asphalt pavement is a crucial indicator of pavement health and serves as a vital basis for maintenance and rehabilitation decisions. It is closely related to the optimization and allocation of funds by highway maintenance management departments. Accurate and rapid identification of internal pavement diseases is essential for improving overall pavement quality. This study aimed to identify internal pavement diseases using deep learning algorithms, thereby improving the efficiency of determining internal pavement diseases. In this work, a multi-view recognition algorithm model based on deep learning is proposed, with attention fusion mechanisms embedded both between channels and between views. By comparing and analyzing the training and recognition results of different neural networks, it was found that the multi-view recognition algorithm model based on attention fusion demonstrates the best performance in identifying internal pavement diseases.

Graph representation learning (GRL) has recently drawn a lot of attention due to its advantage in solving various machine learning tasks on graphs/networks, ranging from drug design to recommendation systems. One typical GRL approach is graph embedding, the purpose of which is to learn a map that encodes or represents network elements as points in a low-dimensional vector space so that downstream machine learning methods can be easily implemented. Initially, most graph embedding algorithms learn such a map independently from subsequent machine learning tasks. Therefore, they have limitations in solving supervised machine learning tasks on networks. Later, a great deal of graph convolutional networks (GCNs) have been proposed to learn node representations in an end-to-end manner based on different information aggregation mechanisms. By treating network structure as a computational layer in a GCN, the associated information of nodes with higher-order proximity can be aggregated by increasing the number of layers (i.e., depth) of the GCN. As a consequence, the computational overhead will increase and the representations will be projected towards a steady state. To solve this problem, in this paper, we propose a multi-channel graph convolutional network (MCGCN) that allows higher-order information aggregation by enriching the number of input channels. Based on the notion of Katz index, our model can further achieve an arbitrary order of information aggregation without increasing the computational overhead. Comprehensive experiments on several benchmark networks demonstrate the effectiveness of the proposed architecture by comparing it with the-state-of-art GRL methods in terms of node classification and computational efficiency.

The recently introduced Segment Anything Model (SAM), a Visual Foundation Model (VFM), has demonstrated impressive capabilities in zero-shot segmentation tasks across diverse natural image datasets. Despite its success, SAM encounters noticeably performance degradation when applied to specific domains, such as medical images. Current efforts to address this issue have involved fine-tuning strategies, intended to bolster the generalizability of the vanilla SAM. However, these approaches still predominantly necessitate the utilization of domain specific expert-level prompts during the evaluation phase, which severely constrains the model's practicality. To overcome this limitation, we introduce a novel self-prompting based fine-tuning approach, called SAM-SP, tailored for extending the vanilla SAM model. Specifically, SAM-SP leverages the output from the previous iteration of the model itself as prompts to guide subsequent iteration of the model. This self-prompting module endeavors to learn how to generate useful prompts autonomously and alleviates the dependence on expert prompts during the evaluation phase, significantly broadening SAM's applicability. Additionally, we integrate a self-distillation module to enhance the self-prompting process further. Extensive experiments across various domain specific datasets validate the effectiveness of the proposed SAM-SP. Our SAM-SP not only alleviates the reliance on expert prompts but also exhibits superior segmentation performance comparing to the state-of-the-art task-specific segmentation approaches, the vanilla SAM, and SAM-based approaches.

Recent advancements in fine-tuning Vision-Language Foundation Models (VLMs) have garnered significant attention for their effectiveness in downstream few-shot learning tasks.While these recent approaches exhibits some performance improvements, they often suffer from excessive training parameters and high computational costs. To address these challenges, we propose a novel Block matrix-based low-rank adaptation framework, called Block-LoRA, for fine-tuning VLMs on downstream few-shot tasks. Inspired by recent work on Low-Rank Adaptation (LoRA), Block-LoRA partitions the original low-rank decomposition matrix of LoRA into a series of sub-matrices while sharing all down-projection sub-matrices. This structure not only reduces the number of training parameters, but also transforms certain complex matrix multiplication operations into simpler matrix addition, significantly lowering the computational cost of fine-tuning. Notably, Block-LoRA enables fine-tuning CLIP on the ImageNet few-shot benchmark using a single 24GB GPU. We also show that Block-LoRA has the more tighter bound of generalization error than vanilla LoRA. Without bells and whistles, extensive experiments demonstrate that Block-LoRA achieves competitive performance compared to state-of-the-art CLIP-based few-shot methods, while maintaining a low training parameters count and reduced computational overhead.