检索结果-内蒙古大学图书馆

Generalized domain prompt learning for accessible scientific vision-language models

学校读者我要写书评

暂无评论

Nexus 2025年第2期2卷

作者： Qinglong Cao Yuntian Chen Lu Lu Hao Sun Zhengzhong Zeng Xiaokang Yang Dongxiao Zhang MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai 200240 China Ningbo Institute of Digital Twin Eastern Institute of Technology Ningbo 315200 China Department of Statistics and Data Science Yale University New Haven CT 06511 USA Gaoling School of Artificial Intelligence Renmin University of China Beijing 100872 China School of Environmental Science and Engineering Southern University of Science and Technology Shenzhen 518055 China Institute for Advanced Study Lingnan University Tuen Mun Hong Kong 100872 China

Large-scale vision-language models have shown remarkable success in general vision tasks, inspiring the development of domain-specific models. However, creating these models requires substantial investments in annotated data, computational resources, and energy, making such endeavors largely accessible to industrial giants. This resource-intensive nature of model development inadvertently stifles academic research, particularly for smaller research groups, and limits the diversity and growth of the field. To address these challenges and promote more sustainable and equitable research, we introduce the generalized domain prompt learning framework. This framework enables the efficient transfer of robust recognition capabilities from natural vision to specialized domains without the need for large datasets or heavy computational overhead. By leveraging small-scale domain-specific foundation models and minimal prompt samples, the framework enriches the language component with domain-specific knowledge through quaternion networks, revealing cross-modal relationships between specialized vision features and natural vision-based contextual embeddings. Simultaneously, it drives the vision component toward domain-specific tasks via hierarchical propagation of vision prompts, grounded in well-matched vision-language relationships. To maximize the domain adaptation potential of these models, we also propose a novel low-rank adaptation technique. Extensive experiments across diverse domains—including remote sensing, medical imaging, geology, synthetic aperture radar, and fluid dynamics—demonstrate the effectiveness of the framework, achieving state-of-the-art domain recognition performance within a prompt learning structure. Our work presents a pathway for inclusive and sustainable research that bridges the gap between academia and industry, empowering smaller research groups and promoting broader access to cutting-edge advancements in the context of future sustainable developme

关键词： vision-language models domain adaptation generalized domain prompt learning sustainable AI research AI for science

SALI: A Scalable Adaptive Learned Index Framework based on Probability Models

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Ge, Jiake Zhang, Huanchen Shi, Boyu Luo, Yuanhui Guo, Yunda Chai, Yunpeng Chen, Yuxing Pan, Anqun Key Laboratory of Data Engineering and Knowledge Engineering MOE China Engineering Research Center of Database and Business Intelligence MOE China School of Information Renmin University of China China China and Shanghai Qi Zhi Institute China Tsinghua University China Tencent Inc China

The growth in data storage capacity and the increasing demands for high performance have created several challenges for concurrent indexing structures. One promising solution is learned indexes, which use a learning-based approach to fit the distribution of stored data and predictively locate target keys, significantly improving lookup performance. Despite their advantages, prevailing learned indexes exhibit constraints and encounter issues of scalability on multi-core data storage. This paper introduces SALI, the Scalable Adaptive Learned Index framework, which incorporates two strategies aimed at achieving high scalability, improving efficiency, and enhancing the robustness of the learned index. Firstly, a set of node-evolving strategies is defined to enable the learned index to adapt to various workload skews and enhance its concurrency performance in such scenarios. Secondly, a lightweight strategy is proposed to maintain statistical information within the learned index, with the goal of further improving the scalability of the index. Furthermore, to validate their effectiveness, SALI applied the two strategies mentioned above to the learned index structure that utilizes fine-grained write locks, known as LIPP. The experimental results have demonstrated that SALI significantly enhances the insertion throughput with 64 threads by an average of 2.04× compared to the second-best learned index. Furthermore, SALI accomplishes a lookup throughput similar to that of LIPP+. © 2023, CC BY-NC-ND.

关键词： Scalability

SP3: Enhancing Structured Pruning via PCA Projection

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Hu, Yuxuan Zhang, Jing Zhao, Zhe Zhao, Chen Chen, Xiaodong Li, Cuiping Chen, Hong School of Information Renmin University of China Beijing China Key Laboratory of Data Engineering and Knowledge Engineering MOE China Engineering Research Center of Database and Business Intelligence MOE China Tencent AI Lab Tencent Beijing China School of Computer Science and Technology Xi'an Jiaotong University Xi'An China

Structured pruning is a widely used technique for reducing the size of pre-trained language models (PLMs), but current methods often overlook the potential of compressing the hidden dimension (d) in PLMs, a dimension critical to model size and efficiency. This paper introduces a novel structured pruning approach, Structured Pruning with PCA Projection (SP3), targeting the effective reduction of d by projecting features into a space defined by principal components before masking. Extensive experiments on benchmarks (GLUE and SQuAD) show that SP3 can reduce d by 70%, compress 94% of the BERTbase model, and maintain over 96% accuracy and outperform other methods that compress d by 6% in accuracy at the same compression ratio. SP3 has also proven effective with other models, including OPT and Llama. Our data and code are available at ours repo. © 2023, CC BY.

关键词：

SAMPLING LOVÁSZ LOCAL LEMMA FOR GENERAL CONSTRAINT SATISFACTION SOLUTIONS IN NEAR-LINEAR TIME

学校读者我要写书评

暂无评论

arXiv 2022年

作者： He, Kun Wang, Chunyang Yin, Yitong The Key Lab of Data Engineering and Knowledge Engineering MOE Renmin University of China No. 59 Zhongguancun Street Haidian District Beijing China State Key Laboratory for Novel Software Technology Nanjing University 163 Xianlin Avenue Jiangsu Province Nanjing China

We give a fast algorithm for sampling uniform solutions of general constraint satisfaction problems (CSPs) in a local lemma regime. Suppose that the CSP has n variables with domain size at most q, each constraint contains at most k variables, shares variables with at most Δ constraints, and is violated with probability at most p by a uniform random assignment. The algorithm returns an almost uniform satisfying assignment in expected poly(q,k, Δ) ·(n) time, as long as a local lemma condition is satisfied: k · p · q2 · Δ5 ≤ C0 for a suitably small absolute constant C0. Previously, under similar local lemma conditions, sampling algorithms with running time polynomial in both nand Δ were only known for the almost atomic case, where each constraint is violated by a small number of forbidden local configurations. The key term Δ5 in our local lemma condition also improves the previously best known Δ7 for general CSPs [JPV21b] and Δ5.714 for atomic CSPs, including the special case of k-CNF [JPV21a, HSW21]. Our sampling approach departs from previous fast algorithms for sampling LLL, which were based on Markov chains. A crucial step of our algorithm is a recursive marginal sampler that is of independent interests. Within a local lemma regime, this marginal sampler can draw a random value for a variable according to its marginal distribution, at a cost independent of the size of the CSP. Copyright © 2022, The Authors. All rights reserved.

关键词： Constraint satisfaction problems

Automatic Retinal Nerve Fiber Trajectory Simulation and Quasi-polar Transformation for Detecting Retinal Nerve Fiber Layer Defect in Fundus Images

学校读者我要写书评

暂无评论

Automatic Retinal Nerve Fiber Trajectory Simulation and Quas...

IEEE International Conference on Multimedia and Expo (ICME)

作者： Yanni Wang Gang Yang Dayong Ding Jianchun Zhao School of Information Renmin University of China Beijing China Key Lab of Data Engineering and Knowledge Engineering Renmin University of China Beijing China Vistel AI Lab Beijing Office Visionary Intelligence Ltd. Beijing China

The retinal nerve fiber layer defects (RNFLD) provide early objective evidence for many retinal abnormalities, especially early glaucoma. The recent success of deep learning has led to exciting prospects in automating the detection of RNFLD, but it is highly dependent on the availability of large-scale datasets carefully annotated by experienced ophthalmologists, which is both time-consuming and cost-prohibitive. Most previous works on RNFLD detection lack a unified annotation scheme. In addition, they fail to exploit the intrinsic morphological characteristics of retinal nerve fiber bundles (RNFB). This work presents an automatic RNFB tracing method that is applicable not only in automating the RNFLD annotation process, but also in performing a quasi-polar transformation on fundus images for subsequent RNFLD detection tasks. Also, our proposed method paves the way for alleviating the problem of inter-annotator variation incurred merely by different annotation habits among annotators and reducing the noise before the input stage. Experiments reveal that our proposed quasi-polar transformation provides a significant boost to the existing RNFLD detection method and surpasses the state-of-the-art F1 by 4.2%, and that our method also offers a more accurate and reasonable description of RNFLD detection results, which demonstrates the orientation of RNFLD rather than vague position indication.

关键词：

Dual Encoding for Zero-Example Video Retrieval

学校读者我要写书评

暂无评论

Dual Encoding for Zero-Example Video Retrieval

IEEE/CVF Conference on Computer Vision and Pattern Recognition

作者： Jianfeng Dong Xirong Li Chaoxi Xu Shouling Ji Yuan He Gang Yang Xun Wang College of Computer and Information Engineering Zhejiang Gongshang University Key Lab of Data Engineering and Knowledge Engineering Renmin University of China AI & Media Computing Lab School of Information Renmin University of China College of Computer Science Zhejiang University Alibaba Group

ISBN: (纸本)9781728132945

This paper attacks the challenging problem of zero-example video retrieval. In such a retrieval paradigm, an end user searches for unlabeled videos by ad-hoc queries described in natural language text with no visual example provided. Given videos as sequences of frames and queries as sequences of words, an effective sequence-to-sequence cross-modal matching is required. The majority of existing methods are concept based, extracting relevant concepts from queries and videos and accordingly establishing associations between the two modalities. In contrast, this paper takes a concept-free approach, proposing a dual deep encoding network that encodes videos and queries into powerful dense representations of their own. Dual encoding is conceptually simple, practically effective and end-to-end. As experiments on three benchmarks, i.e. MSR-VTT, TRECVID 2016 and 2017 Ad-hoc Video Search show, the proposed solution establishes a new state-of-the-art for zero-example video retrieval.

关键词： Videotapes video retrieval End users end-to-end Dual coding

Deepfake Network Architecture Attribution

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Yang, Tianyun Huang, Ziyao Cao, Juan Li, Lei Li, Xirong Key Lab of Intelligent Information Processing Institute of Computing Technology CAS Beijing China University of Chinese Academy of Sciences Beijing China Key Lab of Data Engineering and Knowledge Engineering Renmin University of China China

With the rapid progress of generation technology, it has become necessary to attribute the origin of fake images. Existing works on fake image attribution perform multi-class classification on several Generative Adversarial Network (GAN) models and obtain high accuracies. While encouraging, these works are restricted to model-level attribution, only capable of handling images generated by seen models with a specific seed, loss and dataset, which is limited in real-world scenarios when fake images may be generated by privately trained models. This motivates us to ask whether it is possible to attribute fake images to the source models’ architectures even if they are finetuned or retrained under different configurations. In this work, we present the first study on Deepfake Network Architecture Attribution to attribute fake images on architecture-level. Based on an observation that GAN architecture is likely to leave globally consistent fingerprints while traces left by model weights vary in different regions, we provide a simple yet effective solution named DNA-Det for this problem. Extensive experiments on multiple cross-test setups and a large-scale dataset demonstrate the effectiveness of DNA-Det. Our source code and dataset can be found here: https://***/ICTMCG/DNA-Det Copyright © 2022, The Authors. All rights reserved.

关键词： Network architecture

Drivers for strategic choice of cloud computing as online service in SMEs

学校读者我要写书评

暂无评论

Drivers for strategic choice of cloud computing as online se...

International Conference on Information Systems, ICIS 2012

作者： Li, Min Yu, Yan Zhao, J. Leon Li, Xin University of Science and Technology China-City University of Hong Kong Joint Advanced Research Center 166 Renai Road Dushu Lake Higher Education Town Suzhou China Key Laboratory of Data Engineering and Knowledge Engineering MOE Renmin University of China 59 Zhongguancun Street Haidian District Beijing China Department of Information Systems City University of Hong Kong Tat Chee Avenue Kowloon Hong Kong

ISBN: (纸本)9781627486040

Cloud Computing Service (CCS) paradigm is changing IT strategy of organizations in the digital world. CCS that requires few upfront investments and uses lease-based pricing is especially relevant to the Small and Medium Enterprises (SMEs), which have limited resources and may not know their true valuation for the IT prior to adoption. Thus, this research aims to investigate the influential factors of SMEs' strategic choice of CCS as online service. Relying upon Technology-Organization-Environment (TOE) paradigm, we identify both generic and context-specific factors from the three aspects and explain how the identified factors affect SMEs' CCS strategic choices. We hope this research can make contributions to innovation diffusion theory and IT strategy literature. We also hope the research with progress going on can generate insights for the CCS vendors who care about the sector of SME as well as the government administrators to make appropriate policies or supports for SMEs.

关键词： Cloud computing

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Dong, Jianfeng Li, Xirong Xu, Duanqing College of Computer Science and Technology Zhejiang University Hangzhou310027 China Key Lab of Data Engineering and Knowledge Engineering School of Information Renmin University of China Beijing100872 China

—In order to retrieve unlabeled images by textual queries, cross-media similarity computation is a key ingredient. Although novel methods are continuously introduced, little has been done to evaluate these methods together with large-scale query log analysis. Consequently, how far have these methods brought us in answering real-user queries is unclear. Given baseline methods that use relatively simple text/image matching, how much progress have advanced models made is also unclear. This paper takes a pragmatic approach to answering the two questions. Queries are automatically categorized according to the proposed query visualness measure, and later connected to the evaluation of multiple cross-media similarity models on three test sets. Such a connection reveals that the success of the state-of-the-art is mainly attributed to their good performance on visual-oriented queries, which account for only a small part of real-user queries. To quantify the current progress, we propose a simple text2image method, representing a novel query by a set of images selected from large-scale query log. Consequently, computing cross-media similarity between the query and a given image boils down to comparing the visual similarity between the given image and the selected images. Image retrieval experiments on the challenging Clickture dataset show that the proposed text2image is a strong baseline, comparing favorably to recent deep learning alternatives. Copyright © 2017, The Authors. All rights reserved.

关键词： Image retrieval