检索结果-内蒙古大学图书馆

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Sifan Long Zhen Zhao Jimin Pi Shengsheng Wang Jingdong Wang College of Computer Science and Technology Jilin University Jilin China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Jilin China Baidu VIS University of Sydney

Vision transformers have achieved significant improvements on various vision tasks but their quadratic interactions between tokens significantly reduce computational efficiency. Many pruning methods have been proposed to remove redundant tokens for efficient vision transformers recently. However, existing studies mainly focus on the token importance to preserve local attentive tokens but completely ignore the global token diversity. In this paper, we emphasize the cruciality of diverse global semantics and propose an efficient token decoupling and merging method that can jointly consider the token importance and diversity for token pruning. According to the class token attention, we decouple the attentive and inattentive tokens. In addition to preserving the most discriminative local tokens, we merge similar inattentive tokens and match homogeneous attentive tokens to maximize the token diversity. Despite its simplicity, our method obtains a promising trade-off between model complexity and classification accuracy. On DeiT-S, our method reduces the FLOPs by 35% with only a 0.2% accuracy drop. Notably, benefiting from maintaining the token diversity, our method can even improve the accuracy of DeiT-T by 0.1% after reducing its FLOPs by 40%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Coarse-to-fine Cascaded Evidence-Distillation Neural Network for Explainable Fake News Detection 29

A Coarse-to-fine Cascaded Evidence-Distillation Neural Netwo...

引用

29th International Conference on computational Linguistics, COLING 2022

作者： Yang, Zhiwei Ma, Jing Chen, Hechang Lin, Hongzhan Luo, Ziyang Chang, Yi College of Computer Science and Technology Jilin University Changchun China Department of Computer Science Hong Kong Baptist University Hong Kong School of Artificial Intelligence International Center of Future Science Jilin University China Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education

Existing fake news detection methods aim to classify a piece of news as true or false and provide veracity explanations, achieving remarkable performances. However, they often tailor automated solutions on manual fact-checked reports, suffering from limited news coverage and debunking delays. When a piece of news has not yet been fact-checked or debunked, certain amounts of relevant raw reports are usually disseminated on various media outlets, containing the wisdom of crowds to verify the news claim and explain its verdict. In this paper, we propose a novel Coarse-to-fine Cascaded Evidence-Distillation (CofCED) neural network for explainable fake news detection based on such raw reports, alleviating the dependency on fact-checked ones. Specifically, we first utilize a hierarchical encoder for web text representation, and then develop two cascaded selectors to select the most explainable sentences for verdicts on top of the selected top-K reports in a coarse-to-fine manner. Besides, we construct two explainable fake news datasets, which is publicly available. Experimental results demonstrate that our model significantly outperforms state-of-the-art detection baselines and generates high-quality explanations from diverse evaluation perspectives. © 2022 Proceedings - International Conference on computational Linguistics, COLING. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

MP: Endowing Large Language Models with Lateral Thinking 39

MP: Endowing Large Language Models with Lateral Thinking

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Bai, Tian Cao, Yongwang Ge, Yan Yu, Haitao College of Computer Science and Technology Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Jilin University China Graduate School of Comprehensive Human Sciences University of Tsukuba Japan Institute of Library Information and Media Science University of Tsukuba Japan

ISBN: (纸本)157735897X

The recent studies show that Large Language Models (LLMs) often fall short in tasks demanding creative, lateral thinking due to lacking a clear awareness of their own reasoning processes. To cope with this issue, we propose a novel metacognitive prompting method (titled as MP) by mimicking human metacognition. Through integrating metacognitive principles, MP endows LLMs with lateral thinking ability, thereby enhancing their abilities to strategize, monitor, and reflect on their responses when dealing with creative tasks. The experimental results with five base LLMs across three lateral thinking datasets demonstrate that: All LLMs armed with MP consistently outperform the representative baseline methods. For example, MP demonstrates superior performance over CoT prompting across Sentence Puzzle (+5.00%), Word Puzzle (+10.07%), BiRdQA (+6.48%), and RiddleSense (+2.65%) with GPT-3.5-turbo model. In particular, the deployment of MP with GPT-4 achieves significant performance improvements that even surpass human performance on BRAINTEASER benchmark, demonstrating the transformative potential of MP in enhancing the creative problem-solving abilities of LLMs. 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

Hybrid features and semantic reinforcement network for image forgery detection

Hybrid features and semantic reinforcement network for image...

引用

作者： Chen, Haipeng Chang, Chaoqun Shi, Zenan Lyu, Yingda College of Computer Science and Technology Jilin University Changchun130012 China College of Software Jilin University Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China Public Computer Education and Research Center Jilin University Changchun130012 China

Image forgery detection focuses more on tampering regions than image content of semantic segmentation, it is revealed that wealthier features need to be learned. Moreover, insufficient semantic information causes low efficiency of forgery detection. To address these issues, we propose a hybrid features and semantic reinforcement network (HFSRNet) for image forgery detection, which is an encoding and decoding based network. Specifically, long-short term memory with resampling features has been applied to capture traces from the image patches for finding manipulating artifacts. Consolidated features extracted from rotating residual units are further leveraged to amplify the discrepancy between un-tampered and tampered regions. We then hybridize features from them through a concatenation to further incorporate spatial co-occurrence of these two modalities. In addition, for achieving the semantic consistency between two same level features associated by across layers, semantic reinforcement is implemented on the decoding stage. HFSRNet is an end-to-end architecture that handles multiple types of image forgery including copy-move, splicing, removal. Experiments on three standard image manipulation datasets (NIST16, COVERAGE and CASIA) demonstrate that HFSRNet obtains state-of-the-art performance compared to existing models and baselines. © 2021, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Noisetrans: Point Cloud Denoising with Transformers

SSRN

引用

SSRN 2022年

作者： Hou, Guangzhe Qin, Guihe Sun, Minghui Liang, Yanhua Yan, Jie Zhang, Zhonghan Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Jilin University 2699 Chaoyang District Changchun Jilin130012 China

Introduction: Point clouds obtained from capture devices or 3D reconstruction techniques are often noisy and interfere with downstream ***: The paper aims to recover the underlying surface of noisy point ***: We design a novel model, NoiseTrans, which uses transformer encoder architecture for point cloud denoising. Specifically, we obtain structural similarity of point-based point clouds with the assistance of the transformer's core self-attention mechanism. By expressing the noisy point cloud as a set of unordered vectors, we convert point clouds into point embeddings and employ Transformer to generate clean point clouds. To make the Transformer preserve details when sensing the point cloud, we design the Local Point Attention to prevent the point cloud from being over-smooth. In addition, we also propose sparse encoding, which enables the Transformer to better perceive the structural relationships of the point cloud and improve the denoising ***: Experiments show that our model outperforms state-of-the-art methods in various datasets and noise environments. © 2022, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Causality-inspired Unsupervised Domain Adaptation with Target Style Imitation for Medical Image Segmentation

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Song, Jincai Chen, Haipeng Lyu, Yingda Nie, Weizhi Liu, An-An Jilin University College of Computer Science and Technology Jilin Changchun130012 China Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin Changchun130012 China Jilin University Public Computer Education and Research Center Jilin Changchun130012 China Tianjin University School of Electrical and Information Engineering Tianjin300072 China

Deep learning performance may decrease substantially with unseen heterogeneous data. While most unsupervised domain adaptation (UDA) methods seek to address this through image alignment, they often ignore uncertainty style fluctuations within the target domain. When testing image styles vary in both direction and intensity, such models may fail to adapt. Furthermore, existing UDA methods tend to over-reliance on domain-level entire feature alignment, resulting in potentially over-exploiting semantic content-independent cues (e.g., intensity) as shortcut features. To address these limitations, this paper introduces an innovative and model-agnostic Causality-inspired Representation Learning Based on Target Style Imitation method for UDA. Specifically, we propose a novel Target Style Imitation (TSI) data augmentation approach to diversify the training data and align training and unseen target testing image styles. TSI constructs a Gaussian distribution for the target domain style and simulates unseen testing style variations through random sampling. Additionally, inspired by the stable and generalizable causal mechanism, we propose Causality-inspired Representation Learning (CRL) based on TSI method to enforce feature representations to adhere to causal properties (i.e., Separation and Independence) essential for robust UDA, thus fostering the model to focus on the domain-invariant semantic features. Our method surpasses state-of-the-art methods on two cross-modality medical image segmentation datasets. © 1991-2012 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Fast Converging Anytime Model Counting

arXiv

引用

arXiv 2022年

作者： Lai, Yong Meel, Kuldeep S. Yap, Roland H.C. Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Jilin University China School of Computing National University of Singapore Singapore

Model counting is a fundamental problem which has been influential in many applications, from artificial intelligence to formal verification. Due to the intrinsic hardness of model counting, approximate techniques have been developed to solve real-world instances of model counting. This paper designs a new anytime approach called PartialKC for approximate model counting. The idea is a form of partial knowledge compilation to provide an unbiased estimate of the model count which can converge to the exact count. Our empirical analysis demonstrates that PartialKC achieves significant scalability and accuracy over prior state-of-the-art approximate counters, including satss and STS. Interestingly, the empirical results show that PartialKC reaches convergence for many instances and therefore provides exact model counting performance comparable to state-of-the-art exact counters. Copyright © 2022, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

When Federated Recommendation Meets Cold-Start Problem: Separating Item Attributes and User Interactions 24

When Federated Recommendation Meets Cold-Start Problem: Sepa...

引用

33rd ACM Web Conference, WWW 2024

作者： Zhang, Chunxu Long, Guodong Zhou, Tianyi Zhang, Zijian Yan, Peng Yang, Bo College of Computer Science and Technology Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun China Australian Artificial Intelligence Institute FEIT University of Technology Sydney Sydney Australia Computer Science and Umiacs University of Maryland MD United States College of Computer Science and Technology Jilin University City University of Hong Kong Hong Kong City University of Hong Kong Hong Kong

ISBN: (纸本)9798400701719

Federated recommendation system usually trains a global model on the server without direct access to users' private data on their own devices. However, this separation of the recommendation model and users' private data poses a challenge in providing quality service, particularly when it comes to new items, namely cold-start recommendations in federated settings. This paper introduces a novel method called Item-aligned Federated Aggregation (IFedRec) to address this challenge. It is the first research work in federated recommendation to specifically study the cold-start scenario. The proposed method learns two sets of item representations by leveraging item attributes and interaction records simultaneously. Additionally, an item representation alignment mechanism is designed to align two item representations and learn the meta attribute network at the server within a federated learning framework. Experiments on four benchmark datasets demonstrate IFedRec's superior performance for cold-start scenarios. Furthermore, we also verify IFedRec owns good robustness when the system faces limited client participation and noise injection, which brings promising practical application potential in privacy-protection enhanced federated recommendation systems. The implementation code is available © 2024 ACM.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Application of Monocular Direct Vision Odometry in Augmented Reality 5

Application of Monocular Direct Vision Odometry in Augmented...

引用

2020 5th International Seminar on Computer Technology, Mechanical and Electrical engineering, ISCME 2020

作者： Zhang, Zuoming Wang, Zixuan Wang, Hanwen Wang, Xin College of Software Engineering Jilin University Changchun Jilin130000 China Key Laboratory of Symbolic Computation and Knowledge Engineer of Ministry of Education Jilin University Changchun Jilin130000 China

In recent years, the unlabeled augmented reality system has been gradually applied to various mobile devices, among which stable, accurate, and fast registration is the key to realizing this function. For this technique, this paper introduces camera exposure parameters and puts the data association and pose estimation into a unified nonlinear optimization problem. Moreover, the direct monocular vision odometer is transplanted into the augmented reality system through the position adjustment module. We compare it with the traditional visual odometry method that matches the feature points. The results show that this improved method can be used to track more quickly and build a more visual semi-dense point cloud map, which can be used to support the registration and tracking of virtual objects in augmented reality. © Published under licence by IOP Publishing Ltd.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Application of Hybrid Monocular SLAM Method in Augmented Reality 5

Application of Hybrid Monocular SLAM Method in Augmented Rea...

引用

2020 5th International Seminar on Computer Technology, Mechanical and Electrical engineering, ISCME 2020

作者： Zhang, Zuoming Wang, Hanwen Shu, Man Wang, Xin College of Software Engineering Jilin University Changchun Jilin130000 China Key Laboratory of Symbolic Computation and Knowledge Engineer of Ministry of Education Jilin University Changchun Jilin130000 China

In this paper, we design a hybrid (semi-direct) approach to simultaneous localization and mapping (SLAM) for monocular cameras and apply it to augmented reality (AR) for monocular cameras. We combine the advantagesof the direct method and the feature point method. We use both photometric bundle adjustment which is robust to camera exposure time and motion bundle adjustment which is geometrically robust based on feature points to do tracking process. This approach can maintain an intuitive direct local map as well as a reusable global sparse feature point map. Through the processing of point clouds, such as PCA plane detection and grid reconstruction, we greatly improve the effect of the augmented reality system. © Published under licence by IOP Publishing Ltd.

关键词： Augmented reality

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：