检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Han, Fangzhou Si, Lingyu Dong, Hongwei Zhang, Lamei Chen, Hao Du, Bo The Department of Information Engineering Harbin Institute of Technology Harbin China The National Key Laboratory of Space Integrated Information System Institute of Software Chinese Academy of Sciences Beijing China The Hubei Luojia Laboratory National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan China

Artificial intelligence generative content (AIGC) has significantly impacted image generation in the field of remote sensing. However, the equally important area of remote sensing image (RSI) editing has not received sufficient attention. Deep learning based editing methods generally involve two sequential stages: generation and editing. During the generation stage, consistency in content and details between the original and edited images must be maintained, while in the editing stage, controllability and accuracy of the edits should be ensured. For natural images, these challenges can be tackled by training generative backbones on large-scale benchmark datasets and using text guidance based on vision-language models (VLMs). However, these previously effective approaches become less viable for RSIs due to two reasons: First, existing generative RSI benchmark datasets do not fully capture the diversity of remote sensing scenarios, particularly in terms of variations in sensors, object types, and resolutions. Consequently, the generalization capacity of the trained backbone model is often inadequate for universal editing tasks on RSIs. Second, the large spatial resolution of RSIs exacerbates the problem in VLMs where a single text semantic corresponds to multiple image semantics, leading to the introduction of incorrect semantics when using text to guide RSI editing. To solve above problems, this paper proposes a text-guided RSI editing method that is controllable but stable, and can be trained using only a single image. It adopts a multi-scale training approach to preserve consistency without the need for training on extensive benchmark datasets, while leveraging RSI pre-trained VLMs and prompt ensembling (PE) to ensure accuracy and controllability in the text-guided editing process. High-quality RSI editing results can be achieved by first applying multi-scale training to the target image, followed by text-guided fine-tuning using RSI pre-trained VLMs and PE. Experi

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Background Debiased SAR Target Recognition via Causal Interventional Regularizer

arXiv

引用

arXiv 2023年

作者： Dong, Hongwei Han, Fangzhou Si, Lingyu Qiang, Wenwen Zhang, Lamei Science & Technology on Integrated Information System Laboratory Institute of Software Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Department of Information Engineering Harbin Institute of Technology Harbin China

Recent studies have utilized deep learning (DL) techniques to automatically extract features from synthetic aperture radar (SAR) images, which shows great promise for enhancing the performance of SAR automatic target recognition (ATR). However, our research reveals a previously overlooked issue: SAR images to be recognized include not only the foreground (i.e., the target), but also a certain size of the background area. When a DL-model is trained exclusively on foreground data, its recognition performance is significantly superior to a model trained on original data that includes both foreground and background. This suggests that the presence of background impedes the ability of the DL-model to learn additional semantic information about the target. To address this issue, we construct a structural causal model (SCM) that incorporates the background as a confounder. Based on the constructed SCM, we propose a causal intervention based regularization method to eliminate the negative impact of background on feature semantic learning and achieve background debiased SAR-ATR. The proposed causal interventional regularizer can be integrated into any existing DL-based SAR-ATR models to mitigate the impact of background interference on the feature extraction and recognition accuracy. Experimental results on the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset indicate that the proposed method can enhance the efficiency of existing DL-based methods in a plug-and-play manner. © 2023, CC BY.

关键词： Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

Manifold Constraint Regularization for Remote Sensing Image Generation

arXiv

引用

arXiv 2023年

作者： Su, Xingzhe Zheng, Changwen Qiang, Wenwen Wu, Fengge Zhao, Junsuo Sun, Fuchun Xiong, Hui The National Key Laboratory of Space Integrated Information System Institute of Software Chinese Academy of Sciences University of Chinese Academy of Sciences Beijing China The National Key Laboratory of Space Integrated Information System Department of Computer Science and Technology Tsinghua University Beijing China The Hong Kong University of Science and Technology China

Generative Adversarial Networks (GANs) have shown notable accomplishments in remote sensing domain. However, this paper reveals that their performance on remote sensing images falls short when compared to their impressive results with natural images. This study identifies a previously overlooked issue: GANs exhibit a heightened susceptibility to overfitting on remote sensing images. To address this challenge, this paper analyzes the characteristics of remote sensing images and proposes manifold constraint regularization, a novel approach that tackles overfitting of GANs on remote sensing images for the first time. Our method includes a new measure for evaluating the structure of the data manifold. Leveraging this measure, we propose the manifold constraint regularization term, which not only alleviates the overfitting problem, but also promotes alignment between the generated and real data manifolds, leading to enhanced quality in the generated images. The effectiveness and versatility of this method have been corroborated through extensive validation on various RS datasets and GAN models. The proposed method not only enhances the quality of the generated images, reflected in a 3.13% improvement in Frechet Inception Distance (FID) score, but also boosts the performance of the GANs on downstream tasks, evidenced by a 3.76% increase in classification accuracy. The source code is available at https://***/rootSue/Manifold-RSGAN. Copyright © 2023, The Authors. All rights reserved.

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Anomaly detection of gas flow meter based on improved GAN

Anomaly detection of gas flow meter based on improved GAN

引用

2022 Chinese Automation Congress, CAC 2022

作者： Hao, Weiguang Yi, Junbo Ping, Zuowei Liang, Yingjie Jin, Junyang Zhang, Yong Wuhan University of Science and Technology School of Information Science and Engineering Wuhan China Naval University of Engineering National Key Laboratory of Science and Technology on Vessel Integrated Power System Wuhan China Wuxi Research Institute Huazhong University of Science and Technology Wuxi China

ISBN: (纸本)9781665465335

As one of the core equipment in the gas industry, gas flow meter guides the operation and maintenance of gas companies and reflects the gas consumption habits of downstream users. Therefore, the anomaly detection of gas flow meter has important theoretical value and practical significance. However, the sensors of the gas flow meter are coupled with each other, and the collected data has the characteristics of difficult to collect negative samples. For the solution of the above challenges, an approach to unsupervised anomaly detection based on generative adversarial networks (GAN) is introduced in this paper. Firstly, after the flow meter signal is processed with the data screening, the Savitzky Golay (S-G) filter can filter out the noise from the raw data. The information between channels is captured by the feature attention module for improving the accuracy of the potential representation of samples, in addition, residual blocks are used to prevent the network degradation phenomenon in the deep network. Finally, the proposed model was demonstrated to be valid by using the actual user gas flow meter data. Compared with the current popular depth learning methods, the experimental results reveal that the proposed method can be very accurate in terms of ACC and F1 scores. © 2022 IEEE.

关键词： Gas industry

来源：评论

学校读者我要写书评

暂无评论

Repairing Catastrophic-Neglect in Text-to-Image Diffusion Models via Attention-Guided Feature Enhancement

arXiv

引用

arXiv 2024年

作者： Chang, Zhiyuan Li, Mingyang Wang, Junjie Liu, Yi Wang, Qing Liu, Yang State Key Laboratory of Intelligent Game Beijing China Science and Technology on Integrated Information System Laboratory Institute of Software Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences China Nanyang Technological University Singapore

Text-to-Image Diffusion Models (T2I DMs) have garnered significant attention for their ability to generate high-quality images from textual descriptions. However, these models often produce images that do not fully align with the input prompts, resulting in semantic inconsistencies. The most prominent issue among these semantic inconsistencies is catastrophic-neglect, where the images generated by T2I DMs miss key objects mentioned in the prompt. We first conduct an empirical study on this issue, exploring the prevalence of catastrophic-neglect, potential mitigation strategies with feature enhancement, and the insights gained. Guided by the empirical findings, we propose an automated repair approach named Patcher to address catastrophic-neglect in T2I DMs. Specifically, Patcher first determines whether there are any neglected objects in the prompt, and then applies attention-guided feature enhancement to these neglected objects, resulting in a repaired prompt. Experimental results on three versions of Stable Diffusion demonstrate that Patcher effectively repairs the issue of catastrophic-neglect, achieving 10.1%-16.3% higher Correct Rate in image generation compared to baselines. © 2024, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

What External Knowledge is Preferred by LLMs? Characterizing and Exploring Chain of Evidence in Imperfect Context

arXiv

引用

arXiv 2024年

作者： Chang, Zhiyuan Li, Mingyang Jia, Xiaojun Wang, Junjie Huang, Yuekai Wang, Qing Huang, Yihao Liu, Yang State Key Laboratory of Intelligent Game Beijing China Science and Technology on Integrated Information System Laboratory Institute of Software Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences China Nanyang Technological University Singapore

Incorporating external knowledge into large language models (LLMs) has emerged as a promising approach to mitigate outdated knowledge and hallucination in LLMs. However, external knowledge is often imperfect. In addition to useful knowledge, external knowledge is rich in irrelevant or misinformation in the context that can impair the reliability of LLM responses. This paper focuses on LLMs’ preferred external knowledge in imperfect contexts when handling multi-hop QA. Inspired by criminal procedural law’s Chain of Evidence (CoE), we characterize that knowledge preferred by LLMs should maintain both relevance to the question and mutual support among knowledge pieces. Accordingly, we propose an automated CoE discrimination approach and explore LLMs’ preferences from their effectiveness, faithfulness and robustness, as well as CoE’s usability in a naive Retrieval-Augmented Generation (RAG) case. The evaluation on five LLMs reveals that CoE enhances LLMs through more accurate generation, stronger answer faithfulness, better robustness against knowledge conflict, and improved performance in a popular RAG case. © 2024, CC BY.

关键词： Economic and social effects

来源：评论

学校读者我要写书评

暂无评论

Rethinking Dimensional Rationale in Graph Contrastive Learning from Causal Perspective

arXiv

引用

arXiv 2023年

作者： Ji, Qirui Li, Jiangmeng Hu, Jie Wang, Rui Zheng, Changwen Xu, Fanjiang Science & Technology on Integrated Information System Laboratory Institute of Software Chinese Academy of Sciences China State Key Laboratory of Intelligent Game China University of Chinese Academy of Sciences China State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences China

Graph contrastive learning is a general learning paradigm excelling at capturing invariant information from diverse perturbations in graphs. Recent works focus on exploring the structural rationale from graphs, thereby increasing the discriminability of the invariant information. However, such methods may incur in the mis-learning of graph models towards the interpretability of graphs, and thus the learned noisy and task-agnostic information interferes with the prediction of graphs. To this end, with the purpose of exploring the intrinsic rationale of graphs, we accordingly propose to capture the dimensional rationale from graphs, which has not received sufficient attention in the literature. The conducted exploratory experiments attest to the feasibility of the aforementioned roadmap. To elucidate the innate mechanism behind the performance improvement arising from the dimensional rationale, we rethink the dimensional rationale in graph contrastive learning from a causal perspective and further formalize the causality among the variables in the pre-training stage to build the corresponding structural causal model. On the basis of the understanding of the structural causal model, we propose the dimensional rationale-aware graph contrastive learning approach, which introduces a learnable dimensional rationale acquiring network and a redundancy reduction constraint. The learnable dimensional rationale acquiring network is updated by leveraging a bi-level meta-learning technique, and the redundancy reduction constraint disentangles the redundant features through a decorrelation process during learning. Empirically, compared with state-of-the-art methods, our method can yield significant performance boosts on various benchmarks with respect to discriminability and transferability. The code implementation of our method is available at https://***/ByronJi/DRGCL. Copyright © 2023, The Authors. All rights reserved.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

Prompt Alchemy: Automatic Prompt Refinement for Enhancing Code Generation

arXiv

引用

arXiv 2025年

作者： Ye, Sixiang Sun, Zeyu Wang, Guoqing Guo, Liwei Liang, Qingyuan Li, Zheng Liu, Yong Beijing University of Chemical Technology Beijing China National Key Laboratory of Space Integrated Information System Institute of Software Chinese Academy of Sciences Beijing China Peking University Beijing China

Code generation has gained increasing attention as a task to automate software development by transforming high-level descriptions into executable code. While large language models (LLMs) are effective in generating code, their performance heavily relies on the quality of input prompts. Current prompt engineering methods involve manual effort in designing prompts, which can be time-consuming and yield inconsistent results, potentially constraining the efficacy of LLMs in practical applications. This paper introduces Prochemy, a novel approach for automatically refining prompts iteratively to enhance code generation. Prochemy addresses the limitations of manual prompt engineering by automating the optimization process, ensuring prompt consistency during inference, and aligning with multi-agent systems. It iteratively refines prompts based on model performance, using an optimized final prompt to improve consistency and reliability across tasks. We evaluate Prochemy on both natural language-based code generation and code translation tasks using three series of LLMs. Results show that when combining Prochemy with existing approaches, it outperforms baseline prompting methods. It achieves improvements of 5.0% (GPT-3.5-Turbo) and 1.9% (GPT-4o) over zero-shot baselines on HumanEval. For the state-of-the-art LDB, Prochemy + LDB outperforms standalone methods by 1.2–1.8%. For code translation, Prochemy elevates GPT-4o’s performance on Java-to-Python (AVATAR) from 74.5 to 84.1 (+12.9%) and Python-to-Java from 66.8 to 78.2 (+17.1%). Furthermore, considering that the o1-mini model integrates prompt engineering techniques, Prochemy can continue to show good performance among it, further validating its effectiveness in code generation and translation tasks. Additionally, Prochemy is designed to be plug-and-play, optimizing prompts with minimal human intervention and seamlessly bridging the gap between simple prompts and complex frameworks. Copyright © 2025, The Authors. All right

关键词： software design

来源：评论

学校读者我要写书评

暂无评论

DasAtom: A Divide-and-Shuttle Atom Approach to Quantum Circuit Transformation

arXiv

引用

arXiv 2024年

作者： Huang, Yunqi Gao, Dingchao Ying, Shenggang Li, Sanjiang Faculty of Engineering and Information Technology University of Technology SydneyNSW2007 Australia Key Laboratory of System Software Chinese Academy of Sciences State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences China

Neutral atom (NA) quantum systems are emerging as a leading platform for quantum computation, offering superior or competitive qubit count and gate fidelity compared to superconducting circuits and ion traps. However, the unique features of NA devices, such as long-range interactions, long qubit coherence time, and the ability to physically move qubits, present distinct challenges for quantum circuit compilation. In this paper, we introduce DasAtom, a novel divide-and-shuttle atom approach designed to optimise quantum circuit transformation for NA devices by leveraging these capabilities. DasAtom partitions circuits into subcircuits, each associated with a qubit mapping that allows all gates within the subcircuit to be directly executed. The algorithm then shuttles atoms to transition seamlessly from one mapping to the next, enhancing both execution efficiency and overall fidelity. For a 30-qubit Quantum Fourier Transform (QFT), DasAtom achieves a 415.8x improvement in fidelity over the move-based algorithm Enola and a 10.6x improvement over the SWAP-based algorithm Tetris. Notably, this improvement is expected to increase exponentially with the number of qubits, positioning DasAtom as a highly promising solution for scaling quantum computation on NA platforms. © 2024, CC BY.

关键词： Qubits

来源：评论

学校读者我要写书评

暂无评论

Understanding Individual Agent Importance in Multi-Agent system via Counterfactual Reasoning 39

Understanding Individual Agent Importance in Multi-Agent Sys...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Chen, Jianming Wang, Yawen Wang, Junjie Xie, Xiaofei Hu, Jun Wang, Qing Xu, Fanjiang Institute of Software Chinese Academy of Sciences Beijing China Science & Technology on Integrated Information System Laboratory Beijing China State Key Laboratory of Intelligent Game Beijing China University of Chinese Academy of Sciences Beijing China Singapore Management University Singapore

ISBN: (纸本)157735897X

Explaining multi-agent systems (MAS) is urgent as these systems become increasingly prevalent in various applications. Previous work has provided explanations for the actions or states of agents, yet falls short in understanding the black-boxed agent’s importance within a MAS and the overall team strategy. To bridge this gap, we propose EMAI, a novel agent-level explanation approach that evaluates the individual agent’s importance. Inspired by counterfactual reasoning, a larger change in reward caused by the randomized action of agent indicates its higher importance. We model it as a MARL problem to capture interactions across agents. Utilizing counterfactual reasoning, EMAI learns the masking agents to identify important agents. Specifically, we define the optimization function to minimize the reward difference before and after action randomization and introduce sparsity constraints to encourage the exploration of more action randomization of agents during training. The experimental results in seven multi-agent tasks demonstrate that EMAI achieves higher fidelity in explanations than baselines and provides more effective guidance in practical applications concerning understanding policies, launching attacks, and patching policies. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：