检索结果-内蒙古大学图书馆

Generalizing 6-DoF Grasp Detection via Domain Prior Knowledge

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ma, Haoxiang Shi, Modi Gao, Boyang Huang, Di State Key Laboratory of Software Development Environment Beihang University Beijing China School of Computer Science and Engineering Beihang University Beijing China School of Computer Science and Technology Harbin Institute of Technology Harbin China Geometry Robotics China

We focus on the generalization ability of the 6-DoF grasp detection method in this paper. While learning-based grasp detection methods can predict grasp poses for unseen objects using the grasp distribution learned from the training set, they often exhibit a significant performance drop when encountering objects with diverse shapes and structures. To enhance the grasp detection methods’ generalization ability, we incorporate domain prior knowledge of robotic grasping, enabling better adaptation to objects with significant shape and structure differences. More specifically, we employ the physical constraint regularization during the training phase to guide the model towards predicting grasps that comply with the physical rule on grasping. For the unstable grasp poses predicted on novel objects, we design a contact-score joint optimization using the projection contact map to refine these poses in cluttered scenarios. Extensive experiments conducted on the GraspNet-1billion benchmark demonstrate a substantial performance gain on the novel object set and the real-world grasping experiments also demonstrate the effectiveness of our generalizing 6-DoF grasp detection method. Code is available at https://***/mahaoxiang822/ Generalizing-Grasp. Copyright © 2024, The Authors. All rights reserved.

关键词： Benchmarking

CodeRAG: Supportive Code Retrieval on Bigraph for Real-World Code Generation

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Li, Jia Shi, Xianjie Zhang, Kechi Li, Lei Li, Ge Tao, Zhengwei Liu, Fang Tao, Chongyang Jin, Zhi Key Lab of High Confidence Software Technology Peking University MoE School of Computer Science Peking University China The University of Hong Kong Hong Kong School of Computer Science and Engineering State Key Laboratory of Complex & Critical Software Environment Beihang University China Beihang University China

Large language models (LLMs) have shown promising performance in automated code generation, especially excelling in simple tasks such as generating standalone codes. Different from simple tasks, real-world code generation usually depends on specific programming environment (e.g., code repositories). It contains complex dependencies and domain knowledge, which is needed for LLMs when generating target code snippets. In this paper, we propose CodeRAG, a retrieval-augmented code generation (RAG) framework to comprehensively retrieve supportive codes for real-world code generation. Beginning with the requirement, CodeRAG first constructs a requirement graph for the current repository, and retrieves sub- and similar- requirement nodes of the target requirement on the graph. Meanwhile, it models the repository into a DS-code graph. CodeRAG then maps these relevant requirement nodes into their corresponding code nodes, and treats these code nodes as archors for LLM reasoning on DS-code graph. Finally, CodeRAG introduces a code-oriented agentic reasoning process, seamlessly allowing LLMs to reason and comprehensively retrieve for supportive codes which LLMs’ need for generating correct programs. Experiments show that CodeRAG achieves significant improvements (i.e., increasing 40.90 and 37.79 Pass@1 on GPT-4o and Gemini-Pro on DevEval) compared to no RAG scenarios. Further tests on reasoning LLMs (i.e., QwQ-32B) confirm CodeRAG’s adaptability and efficacy across various types of LLMs. In addition, CodeRAG outperforms commercial programming products such as Copilit and Cursor. We further investigate the performance of our framework on different dependency types, and observe that CodeRAG is superior in generating examples where target codes invoke predefined cross-file code snippets. These results demonstrate CodeRAG’s potential in solving real-world repo-level coding challenges. Copyright © 2025, The Authors. All rights reserved.

关键词： Report generators

RGB-D Grasp Detection via Depth Guided Learning with Cross-modal Attention

学校读者我要写书评

暂无评论

RGB-D Grasp Detection via Depth Guided Learning with Cross-m...

IEEE International Conference on Robotics and Automation (ICRA)

作者： Ran Qin Haoxiang Ma Boyang Gao Di Huang State Key Laboratory of Software Development Environment School of Computer Science and Engineering Beihang University Beijing China Geometry Robotics and the School of Computer Science and Technology Harbin Institute of Technology Harbin China

Planar grasp detection is one of the most fundamental tasks to robotic manipulation, and the recent progress of consumer-grade RGB-D sensors enables delivering more comprehensive features from both the texture and shape modalities. However, depth maps are generally of a relatively lower quality with much stronger noise compared to RGB images, making it challenging to acquire grasp depth and fuse multi-modal clues. To address the two issues, this paper proposes a novel learning based approach to RGB-D grasp detection, namely Depth Guided Cross-modal Attention Network (DGCAN). To better leverage the geometry information recorded in the depth channel, a complete 6-dimensional rectangle representation is adopted with the grasp depth dedicatedly considered in addition to those defined in the common 5-dimensional one. The prediction of the extra grasp depth substantially strengthens feature learning, thereby leading to more accurate results. Moreover, to reduce the negative impact caused by the discrepancy of data quality in two modalities, a Local Cross-modal Attention (LCA) module is designed, where the depth features are refined according to cross-modal relations and concatenated to the RGB ones for more sufficient fusion. Extensive simulation and physical evaluations are conducted and the experimental results highlight the superiority of the proposed approach.

关键词：

A study on the impact of pre-trained model on Just-In-Time defect prediction

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Guo, Yuxiang Gao, Xiaopeng Zhang, Zhenyu Chan, W.K. Jiang, Bo State Key Laboratory of Software Development Environment School of Computer Science and Engineering Beihang University Beijing China State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing China Department of Computer Science City University of Hong Kong Hong Kong

Previous researchers conducting Just-In-Time (JIT) defect prediction tasks have primarily focused on the performance of individual pre-trained models, without exploring the relationship between different pre-trained models as backbones. In this study, we build six models: RoBERTaJIT, CodeBERTJIT, BARTJIT, PLBARTJIT, GPT2JIT, and CodeGPTJIT, each with a distinct pre-trained model as its backbone. We systematically explore the differences and connections between these models. Specifically, we investigate the performance of the models when using Commit code and Commit message as inputs, as well as the relationship between training efficiency and model distribution among these six models. Additionally, we conduct an ablation experiment to explore the sensitivity of each model to inputs. Furthermore, we investigate how the models perform in zero-shot and few-shot scenarios. Our findings indicate that each model based on different backbones shows improvements, and when the backbone’s pre-training model is similar, the training resources that need to be consumed are closer. We also observe that Commit code plays a significant role in defect detection, and different pre-trained models demonstrate better defect detection ability with a balanced dataset under few-shot scenarios. These results provide new insights for optimizing JIT defect prediction tasks using pre-trained models and highlight the factors that require more attention when constructing such models. Additionally, CodeGPTJIT and GPT2JIT achieved better performance than DeepJIT and CC2Vec on the two datasets respectively under 2000 training samples. These findings emphasize the effectiveness of transformer-based pre-trained models in JIT defect prediction tasks, especially in scenarios with limited training data. Copyright © 2023, The Authors. All rights reserved.

关键词： Forecasting

How to Route CUBIC and BBR Packets in Space

学校读者我要写书评

暂无评论

How to Route CUBIC and BBR Packets in Space

International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks (WiOpt)

作者： Shuo Huang Zhiyuan Wang Wenhao Lu Kai Shen Jiayi Zhang Shan Zhang Hongbin Luo School of Computer Science and Engineering Beihang University Beijing China Zhongguancun Laboratory Beijing China State Key Laboratory of Virtual Reality Technology and Systems Beijing China State Key Laboratory of Software Development Environment Beijing China

ISBN: (数字)9783903176652

ISBN: (纸本)9798331508722

Low-earth-orbit satellite constellation (e.g., Starlink) is becoming the indispensable component of future Internet. Due to the mobility nature, ground-satellite links (GSLs) and inter-satellite links (ISLs) are not as stable as the fiber links of wired Internet. Consequently, end-to-end TCP connections traversing the LEO constellation will suffer from packet loss and latency variation caused by GSL handover and ISL failure. However, typical congestion control algorithms (e.g., loss-based CUBIC and bandwidth-estimated BBR) rely on these feedbacks to detect congestion in wired Internet. This leads to performance degradation for CUBIC/BBR in LEO satellite networks. In this paper, we propose a Default-and-Backup Routing (DB-R) mechanism to enhance the performance of CUBIC/BBR in LEO satellite networks. Specifically, DB-R leverages default routing to address the packet loss caused by frequent GSL handover. Moreover, DB- R utilizes backup routing to eliminate the packet loss caused by occasional ISL failure. Overall, DB-R only incurs negligible control overhead, but can effectively improve the performance of CUBIC and BBR in LEO satellite networks. We implement DB-R in Linux kernel and evaluate its performance based on OpenSN (i.e., an open-source libarary for emulating LEO satellite networks). Results show that our DB-R mechanism can improve the average throughput of CUBIC (and BBR, respectively) by up to 37 % (and 18 %, respectively) compared with classic OSPF.

关键词： Satellites Linux Wireless networks Low earth orbit satellites Packet loss Handover Routing Throughput Internet Kernel

Centerness-based Instance-aware Knowledge Distillation with Task-wise Mutual Lifting for Object Detection on Drone Imagery

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Du, Bowei Liao, Zhixuan Zhang, Yanan Cai, Zhi Chen, Jiaxin Huang, Di State Key Laboratory of Software Development Environment Beihang University Beijing China School of Computer Science and Engineering Beihang University Beijing China Hangzhou Innovation Institute Beihang University Hangzhou China

Developing accurate and efficient detectors for drone imagery is challenging due to the inherent complexity of aerial scenes. While some existing methods aim to achieve high accuracy by utilizing larger models, their computational cost is prohibitive for drones. Recently, Knowledge Distillation (KD) has shown promising potential for maintaining satisfactory accuracy while significantly compressing models in general object detection. Considering the advantages of KD, this paper presents the first attempt to adapt it to object detection on drone imagery and addresses two intrinsic issues: (1) low foreground-background ratio and (2) small instances and complex backgrounds, which lead to inadequate training, resulting insufficient distillation. Therefore, we propose a task-wise Lightweight Mutual Lifting (Light-ML) module with a Centerness-based Instance-aware Distillation (CID) strategy. The Light-ML module mutually harmonizes the classification and localization branches by channel shuffling and convolution, integrating teacher supervision across different tasks during back-propagation, thus facilitating training the student model. The CID strategy extracts valuable regions surrounding instances through the centerness of proposals, enhancing distillation efficacy. Experiments on the VisDrone, UAVDT, and COCO benchmarks demonstrate that the proposed approach promotes the accuracies of existing state-ofthe- art KD methods with comparable computational requirements. Codes will be available upon acceptance. Copyright © 2024, The Authors. All rights reserved.

关键词： Drones

A study on the impact of pre-trained model on Just-In-Time defect prediction

学校读者我要写书评

暂无评论

A study on the impact of pre-trained model on Just-In-Time d...

IEEE International Conference on software Quality, Reliability and Security (QRS)

作者： Yuxiang Guo Xiaopeng Gao Zhenyu Zhang W.K. Chan Bo Jiang State Key Laboratory of Software Development Environment School of Computer Science and Engineering Beihang University Beijing China State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing China Department of Computer Science City University of Hong Kong Hong Kong China

关键词：

Aster: Encoding Data Augmentation Relations into Seed Test Suites for Robustness Assessment and Fuzzing of Data-Augmented Deep Learning Models

学校读者我要写书评

暂无评论

Aster: Encoding Data Augmentation Relations into Seed Test S...

IEEE International Conference on software Quality, Reliability and Security (QRS)

作者： Haipeng Wang Zhengyuan Wei Qilin Zhou Bo Jiang W. K. Chan City University of Hong Kong Hong Kong China State Key Laboratory of Software Development Environment School of Computer Science and Engineering Beihang University Beijing China

Data-augmented deep learning models are widely used in real-world applications. However, many state-of the-art loss-based or coverage-based fuzzing techniques fail to produce fuzzing samples for them from many seeds. This paper proposes Aster, a novel technique to address this problem to enhance their fuzzing effectiveness for deep learning models trained with multi-sample data augmentation methods. Aster formulates a novel reachability-based strategy to encode the insights of every seed’s direct and indirect data augmentation relation instances into the replacement seed of that seed systematically. Our experiment shows that Aster is highly effective. On average, loss-based and coverage-based fuzzing techniques can generate 166% and 110% more fuzzing samples and reduce 31% and 22% unsuccessful seeds, respectively, after adopting the replacement seeds generated by Aster to replace their original seeds. Their improved models also become up to 55% and 40% on average more robust against FGSM and PGD attacks in the experiment.

关键词：

FuseFPS: Accelerating Farthest Point Sampling with Fusing KD-tree Construction for Point Clouds

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Han, Meng Wang, Liang Xiao, Limin Zhang, Hao Zhang, Chenhao Xie, Xilong Zheng, Shuai Dong, Jin State Key Laboratory of Software Development Environment School of Computer Science and Engineering Beihang University Beijing100191 China Beijing Academy of Blockchain and Edge Computing China

Point cloud analytics has become a critical workload for embedded and mobile platforms across various applications. Farthest point sampling (FPS) is a fundamental and widely used kernel in point cloud processing. However, the heavy external memory access makes FPS a performance bottleneck for real-time point cloud processing. Although bucket-based farthest point sampling can significantly reduce unnecessary memory accesses during the point sampling stage, the KD-tree construction stage becomes the predominant contributor to execution time. In this paper, we present FuseFPS, an architecture and algorithm co-design for bucket-based farthest point sampling. We first propose a hardware-friendly sampling-driven KD-tree construction algorithm. The algorithm fuses the KD-tree construction stage into the point sampling stage, further reducing memory accesses. Then, we design an efficient accelerator for bucket-based point sampling. The accelerator can offload the entire bucket-based FPS kernel at a low hardware cost. Finally, we evaluate our approach on various point cloud datasets. The detailed experiments show that compared to the state-of-the-art accelerator QuickFPS, FuseFPS achieves about 4.3× and about 6.1× improvements on speed and power efficiency, respectively. Copyright © 2023, The Authors. All rights reserved.

关键词： Trees (mathematics)