• A plug-and-play prompt-driven framework for RGB-thermal image semantic segmentation. • LoRA-based fine-tuning strategy for SAM series model integration. • A model-agnostic encoder to generate statistical distributed prompts for training. The semantic segmentation of RGB-thermal images is critical for applications with low-light conditions. Existing works primarily focus on feature fusion strategies and model design to enhance performance. While Visual Foundation Models (VFMs) have been introduced in previous studies to improve generalization and segmentation accuracy, they suffer from poor compatibility with other models thus requiring full model retraining. Additionally, the domain gap and modality gap between VFM pre-training datasets and RGB-thermal semantic segmentation datasets pose significant challenges to VFM adaptation for downstream tasks. To address these issues, in this paper a plug-and-play prompt driven framework P 3 D is proposed. Unlike existing VFM-based methods that require complete retraining for each specific architecture, P 3 D is designed with a model-agnostic training strategy that enables one-time training and seamless integration with various existing methods without requiring retraining. First, a dual-branch LoRA (Low-Rank Adaptation) fine-tuned (DBLF) image encoder for the RGB and thermal image branches is proposed to narrow the domain gap and modality gap when incorporating SAM series models into our task. Second, a unified prompt generation and representation (UPGR) encoder is proposed. It generates diverse prompts using semantic labels during the training stage, ensuring the generated prompts are model-agnostic and compatible with existing methods. Finally, a cross-modality spatial-channel attention (CM-SCA) decoder is developed to fuse the embeddings from two-modality images and prompts for the final prediction. Extensive experiments are conducted on three popular benchmarks. Results demonstrate that P 3 D not only improves the performance of existing models but also outperforms current state-of-the-art (SOTA) methods leveraging < 1% trainable parameters. More importantly, by simply plugging P 3 D into existing methods, we consistently achieve significant performance improvements without retraining these base models, demonstrating the practical value of our plug-and-play design.

Automated commit message generation, which aims at generating natural language description from code change, allows developers to focus more on project maintenance and management. To ensure the quality of commit messages, most projects constrain their style and adopt the conventional commit specification. Conventional commit message generation has been significantly benefited from recent progress in Large Language Models (LLMs). However, previous approaches typically rely on only one or two type of information for the generation, ignoring a wide range of context information. Moreover, they often extract the context in a coarse-grained manner, missing critical details.To address this limitation, We propose CCMG, a novel hierarchical context-augmentedConventionalCommitMessageGeneration framework, which incorporates project-agnostic and project-specific context. For project agnostic context, CCMG retrieves and refines the relevant commits to align conventional commit specification from large-scale corpus. For project-specific context, CCMG provides a wide range of software context information from the perspective of project, code, and style. Finally, CCMG designs two-stage prompt strategy to focus on conventional message inference and commit type adaptation. Compared with the state-of-the-art LLM-based approaches (i.e., OMG and OMEGA), experiment results show that CCMG achieves an average improvement of 31.45% based on human evaluation in commit message generation and improves accuracy by 21.00% and F1 score by 20.88% in commit type classification.

Point cloud oversegmentation method can obtain a series of superpoints by grouping points that are semantically and geometrically consistent. The generated superpoints can be treated as the basic processing units in various downstream tasks to improve task performance and processing efficiency. However, due to the high semantic and geometric complexity of point cloud scenes, obtaining high-quality superpoints is still challenging. Aiming to generate high-quality indoor superpoints, we propose an end-to-end supervised contrastive learning framework SCL-OverSeg for indoor point cloud oversegmentation. Firstly, to solve the challenge of balancing the importance of geometric similarity and spatial proximity constraint between points and superpoints in indoor scenes, we integrate the geometric similarity and spatial proximity constraint into the supervision signal by generating the superpoint ground truth. To solve the challenge of superpoints crossing objects, we propose to utilize instance labels rather than semantic labels to generate the ideal superpoint ground truth as the object-level supervision signal. Secondly, to construct the distinguishable embedding space facilitating to the assignments of points to superpoints, we propose point-superpoint contrastive learning to compel the network to project each point to be closer to the reasonable superpoint in embedding space. Besides, with the instance labels, to improve the superpoint performance on object boundaries, we propose the object boundary contrastive learning to enhance the feature distinguishability between tough points across the object boundaries. Extensive experiments demonstrate that SCL-OverSeg can effectively improve indoor oversegmentation performance, especially on object boundaries. The relevant codes will be available onhttps://github.com/sssssyf/SCL-OverSeg.

Traditional vulnerability detection methods have limitations due to their need for extensive manual labor. Using automated means for vulnerability detection has attracted research interest, especially deep learning, which has achieved remarkable results. Since graphs can better convey the structural feature of code than text, graph neural network (GNN) based vulnerability detection is significantly better than text-based approaches. Therefore, GNN-based vulnerability detection approaches are becoming popular. However, GNN models are close to black boxes for security analysts, so the models cannot provide clear evidence to explain why a code sample is detected as vulnerable or secure. At this stage, many GNN interpreters have been proposed. However, the explanations provided by these interpretations for vulnerability detection models are highly inconsistent and unconvincing to security experts. To address the above issues, we propose principled guidelines to assess the quality of the interpretation approaches for GNN-based vulnerability detectors based on concerns in vulnerability detection, namely, stability, robustness, and effectiveness. We conduct extensive experiments to evaluate the interpretation performance of six famous interpreters (GNN-LRP, DeepLIFT, GradCAM, GNNExplainer, PGExplainer, and SubGraphX) on four vulnerability detectors (DeepWukong, Devign, IVDetect, and Reveal). The experimental results show that the target interpreters achieve poor performance in terms of effectiveness, stability, and robustness. For effectiveness, we find that the instance-independent methods outperform others due to their deep insight into the detection model. In terms of stability, the perturbation-based interpretation methods are more resilient to slight changes in model parameters as they are model-agnostic. For robustness, the instance-independent approaches provide more consistent interpretation results for similar vulnerabilities.

Third-party libraries (TPLs) have become an essential component of software, accelerating development and reducing maintenance costs. However, breaking changes often occur during the upgrades of TPLs and prevent client programs from moving forward. Semantic versioning (SemVer) has been applied to standardize the versions of releases according to compatibility, but not all releases follow SemVer compliance. Lots of work focuses on SemVer compliance in ecosystems such as Java and JavaScript beyond Golang (Go for short). Due to the lack of tools to detect breaking changes and dataset for Go, developers of TPLs do not know if breaking changes occur and affect client programs, and developers of client programs may hesitate to upgrade dependencies in terms of breaking changes. To bridge this gap, we conduct the first large-scale empirical study in the Go ecosystem to study SemVer compliance in terms of breaking changes and their impact. In detail, we propose GoSVI (Go Semantic Versioning Insight) to detect breaking changes and analyze their impact by resolving identifiers in client programs and comparing their types with breaking changes. Moreover, we collect the first large-scale Go dataset with a dependency graph from GitHub, including 124K TPLs and 532K client programs. Based on the dataset, our results show that 86.3% of library upgrades follow SemVer compliance and 28.6% of no-major upgrades introduce breaking changes. Furthermore, the tendency to comply with SemVer has improved over time from 63.7% in 2018/09 to 92.2% in 2023/03. Finally, we find 33.3% of downstream client programs may be affected by breaking changes. These findings provide developers and users of TPLs with valuable insights to help make decisions related to SemVer.

As a provincial centre for remote sensing in Shanxi, it has developed its integrated remote sensing and GIS system for agricultural resource assessment and monitoring in the Province with a very complex loess highland landscape, segmented land parcels and multi-diversity crops. The structure of the system was designed such that it can be readily updated to integrate the remote sensing (TM and CB-1) and other types of agricultural information needed for timely agricultural monitoring and assessment. In addition to introduce the structure and application of the system, this paper will focus on the innovative methods implemented in the system for improving interpretation accuracy and minimizing the information loss due to resampling process involved in fusing multiple images and the resolution alteration. The key issues we address here include multi-scale processes. The systems can readily handle problem in various scales such as province, city and county scales; (2) Determination of 100m /spl times/ 100m as the optimum re-sampling resolution for fusion and integration of various data for the application in the province scale. The resolution has been shown adequate both for the analysis and for the capacity of the facility available at the centre; and (3) Integration of GIS and RS to assist the information extraction, classification and identification of features.