检索结果-内蒙古大学图书馆

Divide and contrast: source-free domain adaptation via adaptive contrastive learning 22

学校读者我要写书评

暂无评论

Divide and contrast: source-free domain adaptation via adapt...

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Ziyi Zhang Weikai Chen Hui Cheng Zhen Li Siyuan Li Liang Lin Guanbin Li National Key Laboratory of Novel Software Technology Nanjing University Nanjing China Tencent America School of Computer Science and Engineering Sun Yat-sen University Guangzhou China The Chinese University of Hong Kong Shenzhen China and Shenzhen Research Institute of Big Data Shenzhen China AI Lab School of Engineering Westlake University Hangzhou China

ISBN: (纸本)9781713871088

We investigate a practical domain adaptation task, called source-free unsupervised domain adaptation (SFUDA), where the source pretrained model is adapted to the target domain without access to the source data. Existing techniques mainly leverage self-supervised pseudo-labeling to achieve class-wise global alignment [1] or rely on local structure extraction that encourages the feature consistency among neighborhoods [2]. While impressive progress has been made, both lines of methods have their own drawbacks - the "global" approach is sensitive to noisy labels while the "local" counterpart suffers from the source bias. In this paper, we present Divide and Contrast (DaC), a new paradigm for SFUDA that strives to connect the good ends of both worlds while bypassing their limitations. Based on the prediction confidence of the source model, DaC divides the target data into source-like and target-specific samples, where either group of samples is treated with tailored goals under an adaptive contrastive learning framework. Specifically, the source-like samples are utilized for learning global class clustering thanks to their relatively clean labels. The more noisy target-specific data are harnessed at the instance level for learning the intrinsic local structures. We further align the sourcelike domain with the target-specific samples using a memory-based maximum mean discrepancy (MMD) loss to reduce the distribution mismatch. Extensive experiments on VisDA, Office-Home, and the more challenging DomainNet have verified the superior performance of DaC over current state-of-the-art approaches.

关键词：

A novel method for driving path planning with spark

学校读者我要写书评

暂无评论

TechRxiv

TechRxiv 2021年

作者： Li, Leixiao Lin, Hao Wan, Jianxiong Wang, Yongsheng Gao, Jing College of Data Science and Application Inner Mongolia University of Technology China School of Computer Science and Engineering Tianjin University of Technology China Inner Mongolia Autonomous Region Engineering and Technology Research Center of Big Data Based Software Service China College of Computer and Information Engineering Inner Mongolia Agricultural University China Inner Mongolia Autonomous Region Key Laboratory of big data research and application for agriculture and animal husbandry China

Efficient and accurate driving path planning can help drivers drive. To solve the problem of low efficiency of traditional heuristic algorithms such as PSO and GA in solving driving path planning, we introduce Excellence Coefficient into heuristic algorithms and make a parallel design based on Spark, which called EC-SPPSOGA. Excellence Coefficient can increase the probability of good edges being left, simultaneously, preserves the possibility of longer side being selected. The parallel design is based on time-consuming analysis of heuristic algorithms. We validate the performance of EC-SPPSOGA based on the data in TSPLIB. It is verified that the EC-SPPSOGA can improve efficiency of driving path planning and has good scalability. © 2021, CC BY.

关键词： Heuristic algorithms

MC3D-AD: A Unified Geometry-aware Reconstruction Model for Multi-category 3D Anomaly Detection

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Cheng, Jiayi Gao, Can Zhou, Jie Wen, Jiajun Dai, Tao Wang, Jinbao College of Computer Science and Software Engineering Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen China

3D Anomaly Detection (AD) is a promising means of controlling the quality of manufactured products. However, existing methods typically require carefully training a task-specific model for each category independently, leading to high cost, low efficiency, and weak generalization. Therefore, this paper presents a novel unified model for Multi-Category 3D Anomaly Detection (MC3D-AD) that aims to utilize both local and global geometry-aware information to reconstruct normal representations of all categories. First, to learn robust and generalized features of different categories, we propose an adaptive geometry-aware masked attention module that extracts geometry variation information to guide mask attention. Then, we introduce a local geometry-aware encoder reinforced by the improved mask attention to encode group-level feature tokens. Finally, we design a global query decoder that utilizes point cloud position embeddings to improve the decoding process and reconstruction ability. This leads to local and global geometry-aware reconstructed feature tokens for the AD task. MC3D-AD is evaluated on two publicly available Real3D-AD and Anomaly-ShapeNet datasets, and exhibits significant superiority over current state-of-the-art single-category methods, achieving 3.1% and 9.3% improvement in object-level AUROC over Real3D-AD and Anomaly-ShapeNet, respectively. The source code will be released upon acceptance. Copyright © 2025, The Authors. All rights reserved.

关键词： Geometry

Robust Dynamic Broadcasting for Multi-Hop Wireless Networks Under Time-Varying Connectivity and Dynamic SINR

学校读者我要写书评

暂无评论

IEEE Transactions on Mobile Computing 2025年

作者： Tian, Xiang Yu, Jiguo Luo, Chuanwen Yu, Dongxiao Wang, Guijuan Feng, Bin Jinan250353 China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Industrial Network and Information System Security Jinan250353 China University of Electronic Science and Technology of China School of Information and Software Engineering Chengdu610054 China Qilu University of Technology Big Data Institute Jinan250353 China Beijing Forestry University School of Information Science and Technology Beijing100083 China Shandong University School of Computer Science and Technology Shandong Qingdao266237 China Taishan University School of Information Science and Technology 271000 China

Throughput-optimal dynamic broadcasting is an essential cornerstone for the efficient operation of Multi-hop Wireless Networks (MWNs). Most existing algorithms for this problem were developed assuming static interference environments and network connectivity. However, wireless interference environments and network connectivity are inherently time-varying in real-world scenarios, primarily due to uncontrollable interference sources and unreliable links. Such time-varying characteristics make these existing algorithms less robust. In this paper, we study the robust throughput-optimal dynamic broadcasting for MWNs with multi-dimensional time-varying characteristics in terms of interference environments, network connectivity, and data arrival. We model the time-varying link existence states using a random process and characterize the time-varying interference environments through a dynamic variant of the classical Signal-to-Interference-plus-Noise-Ratio (SINR) model. In this variant, the SINR model parameters are dynamically adjusted over time by an adversary. Based on this, we first design a Robust Throughput-optimal Dynamic Broadcast (RTDB) algorithm which makes efficient slot-based max-weight link scheduling, power allocation, and data forwarding decisions in each time slot. We then prove its throughput-optimality in time-varying acyclic directed MWNs under the dynamic SINR model. The effectiveness of RTDB is validated via numerous simulations. © 2002-2012 IEEE.

关键词： Signal to noise ratio

Breaking the curse of space explosion: Towards effcient NAS with curriculum search 37

学校读者我要写书评

暂无评论

Breaking the curse of space explosion: Towards effcient NAS ...

37th International Conference on Machine Learning, ICML 2020

作者： Guo, Yong Chen, Yaofo Zheng, Yin Zhao, Peilin Chen, Jian Huang, Junzhou Tan, Mingkui School of Software Engineering South China University of Technology China Pazhou Laboratory China Weixin Group Tencent China Tencent AI Lab Tencent China Guangdong Key Laboratory of Big Data Analysis and Processing China

ISBN: (纸本)9781713821120

Neural architecture search (NAS) has become an important approach to automatically fnd effective architectures. To cover all possible good architectures, we need to search in an extremely large search space with billions of candidate architectures. More critically, given a large search space, we may face a very challenging issue of space explosion. However, due to the limitation of computational resources, we can only sample a very small proportion of the architectures, which provides insuffcient information for the training. As a result, existing methods may often produce suboptimal architectures. To alleviate this issue, we propose a curriculum search method that starts from a small search space and gradually incorporates the learned knowledge to guide the search in a large space. With the proposed search strategy, our Curriculum Neural Architecture Search (CNAS) method signifcantly improves the search effciency and fnds better architectures than existing NAS methods. Extensive experiments on CIFAR-10 and ImageNet demonstrate the effectiveness of the proposed method. Copyright 2020 by the author(s).

关键词： Curricula

PScalpel: A Machine Learning-based Guider for Protein Phase-Separating Behaviour Alteration 39

学校读者我要写书评

暂无评论

PScalpel: A Machine Learning-based Guider for Protein Phase-...

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Wang, Jia Zhu, Liyan Wang, Zhe Zhang, Chenqiu Wu, Yaoxing Cui, Jun Li, Jianqiang College of Computer Science and Software Engineering Shenzhen University Shenzhen China MOE Key Laboratory of Gene Function and Regulation Guangdong Province Key Laboratory of Pharmaceutical Functional Genes State Key Laboratory of Biocontrol School of Life Sciences Sun Yat-sen University Guangzhou China Guangdong Province Key Laboratory of Pharmaceutical Functional Genes First Affiliated Hospital of Sun Yat-sen University School of Life Sciences Sun Yat-sen University Guangzhou China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China

ISBN: (纸本)157735897X

Missense mutations could affect the Liquid-Liquid Phase Separation (LLPS) propensity of proteins and lead to aberrant phase-separating behaviours, which are recently found to be associated with many diseases including Alzheimer’s and cancer. However, the regulatory role of mutations in LLPS remains unclear due to challenges in accurately characterizing the LLPS ability of mutants, including the high similarity in features, lack of labeled data, and vast amounts of data involved. To bridge this gap and facilitate the discovery of therapeutic strategies, we propose the first machine learning-based guider for protein phase-separating behaviour alteration, PScalpel. PScalpel leverages both structural information and an auxiliary tasks-based graph contrastive learning framework to distinguish the mutants’ LLPS ability, and incorporates a genetic algorithms-based recommendation method to identify mutants with desired LLPS properties. Comprehensive computational and biological experiments validate the effectiveness of PScalpel as a versatile tool for guiding alterations in protein phase separation behavior. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Genetic algorithms

CodeEnhance: A Codebook-Driven Approach for Low-Light Image Enhancement

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wu, Xu Hou, XianXu Lai, Zhihui Zhou, Jie Zhang, Ya-Nan Pedrycz, Witold Shen, Linlin The Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518060 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China School of AI and Advanced Computing Xi’an Jiaotong-Liverpool University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Shenzhen518060 China The Department of Electrical & Computer Engineering University of Alberta University of Alberta Canada

Low-light image enhancement (LLIE) aims to improve low-illumination images. However, existing methods face two challenges: (1) uncertainty in restoration from diverse brightness degradations;(2) loss of texture and color information caused by noise suppression and light enhancement. In this paper, we propose a novel enhancement approach, CodeEnhance, by leveraging quantized priors and image refinement to address these challenges. In particular, we reframe LLIE as learning an image-to-code mapping from low-light images to discrete codebook, which has been learned from high-quality images. To enhance this process, a Semantic Embedding Module (SEM) is introduced to integrate semantic information with low-level features, and a Codebook Shift (CS) mechanism, designed to adapt the pre-learned codebook to better suit the distinct characteristics of our low-light dataset. Additionally, we present an Interactive Feature Transformation (IFT) module to refine texture and color information during image reconstruction, allowing for interactive enhancement based on user preferences. Extensive experiments on both real-world and synthetic benchmarks demonstrate that the incorporation of prior knowledge and controllable information transfer significantly enhances LLIE performance in terms of quality and fidelity. The proposed CodeEnhance exhibits superior robustness to various degradations, including uneven illumination, noise, and color distortion. Copyright © 2024, The Authors. All rights reserved.

关键词： Image enhancement

Adaptive Convolutional Neural Network for Image Super-resolution

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Tian, Chunwei Zhang, Xuanyu Wang, Tao Zhang, Yongjun Zhu, Qi Lin, Chia-Wen The School of Software Northwestern Polytechnical University Xi’an710129 China The National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Xi’an710129 China The Yangtze River Delta Research Institute Northwestern Polytechnical University Taicang215400 China The School of Computer Science Northwestern Polytechnical University Xi’an710129 China The College of Computer Science and Technology Guizhou University Guiyang550025 China The School of Artificial Intelligence Nanjing University of Aeronautics and Astronautics Nanjing210016 China The Department of Electrical Engineering The Institute of Communications Engineering National Tsing Hua University Taiwan

Convolutional neural networks can automatically learn features via deep network architectures and given input samples. However, the robustness of obtained models may face challenges in varying scenes. bigger differences in network architecture are beneficial to extract more diversified structural information to strengthen the robustness of an obtained superresolution model. In this paper, we proposed a adaptive convolutional neural network for image super-resolution (ADSRNet). To capture more information, ADSRNet is implemented by a heterogeneous parallel network. The upper network can enhance relation of context information, salient information relation of a kernel mapping and relations of shallow and deep layers to improve performance of image super-resolution. That can strengthen adaptability of an obtained super-resolution model for different scenes. The lower network utilizes a symmetric architecture to enhance relations of different layers to mine more structural information, which is complementary with a upper network for image super-resolution. The relevant experimental results show that the proposed ADSRNet is effective to deal with image resolving. Codes are obtained at https://***/hellloxiaotian/ADSRNet. Copyright © 2024, The Authors. All rights reserved.

关键词： Convolutional neural networks

An overview of domain-specific foundation model: key technologies, applications and challenges

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Chen, Haolong Chen, Hanzhi Zhao, Zijian Han, Kaifeng Zhu, Guangxu Zhao, Yichen Du, Ying Xu, Wei Shi, Qingjiang Shenzhen Research Institute of Big Data Shenzhen518172 China School of Science and Engineering The Chinese University of Hong Kong Shenzhen518172 China China Academy of Information and Communications Technology Beijing100191 China China Mobile Group Device Co. Ltd. Beijing100033 China School of Computer Science and Engineering Sun Yat-sen University Guangzhou510275 China National Mobile Communications Research Laboratory Southeast University Nanjing210096 China Purple Mountain Laboratories Nanjing211111 China School of Software Engineering Tongji University Shanghai201804 China

The impressive performance of ChatGPT and other foundation-model-based products in human language understanding has prompted both academia and industry to explore how these models can be tailored for specific industries and application scenarios. This process, known as the customization of domain-specific foundation models, addresses the limitations of general-purpose models, which may not fully capture the unique patterns and requirements of domain-specific data. Despite its importance, there is a notable lack of comprehensive overview papers on building domain-specific foundation models, while numerous resources exist for general-purpose models. To bridge this gap, this article provides a timely and thorough overview of the methodology for customizing domain-specific foundation models. It introduces basic concepts, outlines the general architecture, and surveys key methods for constructing domain-specific models. Furthermore, the article discusses various domains that can benefit from these specialized models and highlights the challenges ahead. Through this overview, we aim to offer valuable guidance and reference for researchers and practitioners from diverse fields to develop their own customized foundation models. Copyright © 2024, The Authors. All rights reserved.

关键词： Building Information Model