检索结果-内蒙古大学图书馆

41st International Conference on Machine Learning, ICML 2024

作者： Hua, Cong Xu, Qianqian Bao, Shilong Yang, Zhiyong Huang, Qingming Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China

This paper explores a novel multi-modal alternating learning paradigm pursuing a reconciliation between the exploitation of uni-modal features and the exploration of cross-modal interactions. This is motivated by the fact that current paradigms of multi-modal learning tend to explore multi-modal features simultaneously. The resulting gradient prohibits further exploitation of the features in the weak modality, leading to modality competition, where the dominant modality overpowers the learning process. To address this issue, we study the modality-alternating learning paradigm to achieve reconcilement. Specifically, we propose a new method called ReconBoost to update a fixed modality each time. Herein, the learning objective is dynamically adjusted with a reconcilement regularization against competition with the historical models. By choosing a KL-based reconcilement, we show that the proposed method resembles Friedman's Gradient-Boosting (GB) algorithm, where the updated learner can correct errors made by others and help enhance the overall performance. The major difference with the classic GB is that we only preserve the newest model for each modality to avoid overfitting caused by ensembling strong learners. Furthermore, we propose a memory consolidation scheme and a global rectification scheme to make this strategy more effective. Experiments over six multi-modal benchmarks speak to the efficacy of the method. We release the code at https://***/huacong/ReconBoost. Copyright 2024 by the author(s)

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

An Object Detection Algorithm with Multi-scale Context Information Based on YOLOv4 4

An Object Detection Algorithm with Multi-scale Context Infor...

引用

4th International Conference on Natural Language processing, ICNLP 2022

作者： Ma, Sugang An, Wen Yang, Xiaobao Hou, Zhiqiang Xi'an University of Posts and Telecommunications Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi'an China Xi'an University of Posts and Telecommunications School of Computer Science and Technology Xi'an China Xi'an University of Posts and Telecommunications Xi'an Key Laboratory of Big Data and Intelligent Computing Xi'an China

ISBN: (数字)9781665495448

ISBN: (纸本)9781665495448

Most current object detection algorithms have the issue of missing objects due to occlusion. As the great difference of scale between occlusion objects and their integrity is affected, how to reduce the missing rate of occlusion objects has become a challenging problem in object detection algorithms. Aiming at the problem, this paper proposes an object detection algorithm based on multi-scale context information on the basis of the YOLOv4 algorithm framework. Firstly, the object features are extracted through the CSPDarkNet53 feature extraction network. Then, the proposed attention-guided multi-scale context information module (AMCM) enhances the ability to perceive object context information and endows features with different influence factors through attention weighting to improve feature discrimination. The experimental results show that the detection accuracy and recall of the proposed algorithm reach 83.2% and 96.4% respectively on PASCAL VOC dataset, and 83.2% and 91% on KITTI dataset, which improves the detection performance of YOLOv4 algorithm. © 2022 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

AUCSeg: AUC-oriented pixel-level long-tail semantic segmentation 24

AUCSeg: AUC-oriented pixel-level long-tail semantic segmenta...

引用

Proceedings of the 38th International Conference on Neural Information processing Systems

作者： Boyu Han Qianqian Xu Zhiyong Yang Shilong Bao Peisong Wen Yangbangyan Jiang Qingming Huang Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS and School of Computer Science and Tech. University of Chinese Academy of Sciences Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS and Peng Cheng Laboratory School of Computer Science and Tech. University of Chinese Academy of Sciences School of Computer Science and Tech. University of Chinese Academy of Sciences and Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS and Key Laboratory of Big Data Mining and Knowledge Management CAS

ISBN: (纸本)9798331314385

The Area Under the ROC Curve (AUC) is a well-known metric for evaluating instance-level long-tail learning problems. In the past two decades, many AUC optimization methods have been proposed to improve model performance under long-tail distributions. In this paper, we explore AUC optimization methods in the context of pixel-level long-tail semantic segmentation, a much more complicated scenario. This task introduces two major challenges for AUC optimization techniques. On one hand, AUC optimization in a pixel-level task involves complex coupling across loss terms, with structured inner-image and pairwise inter-image dependencies, complicating theoretical analysis. On the other hand, we find that mini-batch estimation of AUC loss in this case requires a larger batch size, resulting in an unaffordable space complexity. To address these issues, we develop a pixel-level AUC loss function and conduct a dependency-graph-based theoretical analysis of the algorithm's generalization ability. Additionally, we design a Tail-Classes Memory Bank (T-Memory Bank) to manage the significant memory demand. Finally, comprehensive experiments across various benchmarks confirm the effectiveness of our proposed AUCSeg method. The code is available at https://***/boyuh/AUCSeg.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SSFam: Scribble Supervised Salient Object Detection Family

arXiv

引用

arXiv 2024年

作者： Liu, Zhengyi Deng, Sheng Wang, Xinrui Wang, Linbo Fang, Xianyong Tang, Bin Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei China School of Artificial Intelligence and Big Data Hefei University Hefei China

Scribble supervised salient object detection (SSSOD) constructs segmentation ability of attractive objects from surroundings under the supervision of sparse scribble labels. For the better segmentation, depth and thermal infrared modalities serve as the supplement to RGB images in the complex scenes. Existing methods specifically design various feature extraction and multi-modal fusion strategies for RGB, RGB-Depth, RGB-Thermal, and Visual-Depth-Thermal image input respectively, leading to similar model flood. As the recently proposed Segment Anything Model (SAM) possesses extraordinary segmentation and prompt interactive capability, we propose an SSSOD family based on SAM, named SSFam, for the combination input with different modalities. Firstly, different modal-aware modulators are designed to attain modal-specific knowledge which cooperates with modal-agnostic information extracted from the frozen SAM encoder for the better feature ensemble. Secondly, a siamese decoder is tailored to bridge the gap between the training with scribble prompt and the testing with no prompt for the stronger decoding ability. Our model demonstrates the remarkable performance among combinations of different modalities and refreshes the highest level of scribble supervised methods and comes close to the ones of fully supervised methods. https://***/liuzywen/SSFam Copyright © 2024, The Authors. All rights reserved.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Emotional Knowledge Self-Distillation in Dialogue

Emotional Knowledge Self-Distillation in Dialogue

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal processing, ICASSP 2025

作者： Jian, Zhongquan Wang, Yancheng Wu, Weichao Yao, Junfeng Wang, Meihong Wu, Qingqiang School of Informatics Xiamen University Xiamen China School of Film Xiamen University Xiamen China School of Computing and Data Science Xiamen University Malaysia Selangor Malaysia School of Mechanics and Civil Engineering China University of Mining & Technology Beijing China Xiamen Key Laboratory of Intelligent Storage and Computing School of Informatics Xiamen University Xiamen China Key Laboratory of Digital Protection and Intelligent Processing of Intangible Cultural Heritage of Fujian and Taiwan Ministry of Culture and Tourism Xiamen China

ISBN: (纸本)9798350368741

Recognizing emotions in dialogues is vital for effective human-computer interaction, yet remains a challenging task in Natural Language processing (NLP). Previous studies in Emotion Recognition in Conversation (ERC) have primarily focused on contextual features, while overlooking the importance of emotional features in emotion recognition. To address this gap, we focus on the role of emotional features in ERC and propose a novel method, Emotional Knowledge Self-Distillation (EmoKSD1), to enhance the model's emotional sensitivity. In EmoKSD, utterances are enriched with implicit 〈mask〉 tokens to represent conveyed emotions, allowing the distillation of emotional knowledge from explicit emotional tokens to implicit 〈mask〉 tokens, thereby enhancing the model's ability to perceive subtle emotions within the dialogue. Through thorough evaluations on two public ERC datasets (i.e., IEMOCAP and MELD) using proposed coarse-grained utterance distillation and fine-grained token distillation techniques, EmoKSD demonstrates superior performance compared to existing methods, highlighting the significance of emotional features in ERC. © 2025 IEEE.

关键词： Dialogue System Emotion Recognition in Conversation Knowledge Distillation Natural Language processing

来源：评论

学校读者我要写书评

暂无评论

Learning with Open-world Noisy data via Class-independent Margin in Dual Representation Space

arXiv

引用

arXiv 2025年

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

Learning with Noisy Labels (LNL) aims to improve the model generalization when facing data with noisy labels, and existing methods generally assume that noisy labels come from known classes, called closed-set noise. However, in real-world scenarios, noisy labels from similar unknown classes, i.e., open-set noise, may occur during the training and inference stage. Such open-world noisy labels may significantly impact the performance of LNL methods. In this study, we propose a novel dual-space joint learning method to robustly handle the open-world noise. To mitigate model overfitting on closed-set and open-set noises, a dual representation space is constructed by two networks. One is a projection network that learns shared representations in the prototype space, while the other is a One-Vs-All (OVA) network that makes predictions using unique semantic representations in the class-independent space. Then, bi-level contrastive learning and consistency regularization are introduced in two spaces to enhance the detection capability for data with unknown classes. To benefit from the memorization effects across different types of samples, class-independent margin criteria are designed for sample identification, which selects clean samples, weights closed-set noise, and filters open-set noise effectively. Extensive experiments demonstrate that our method outperforms the state-of-the-art methods and achieves an average accuracy improvement of 4.55% and an AUROC improvement of 6.17% on CIFAR80N. Copyright © 2025, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

A Weighted Flat Lattice Transformer-based Knowledge Extraction Architecture for Chinese Named Entity Recognition

A Weighted Flat Lattice Transformer-based Knowledge Extracti...

引用

International Conference on Computer Supported Cooperative Work in Design

作者： Hengwei Zhang Yuejia Wu Jian-Tao Zhou Inner Mongolia University College of Computer Science Hohhot China Ministry of Education National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Engineering Research Center of Ecological Big Data Hohhot China Inner Mongolia Engineering Laboratory for Cloud Computing and Service Software Hohhot China Inner Mongolia Key Laboratory of Social Computing and Data Processing Hohhot China Inner Mongolia Key Laboratory of Discipline Inspection and Supervision Big Data Hohhot China Inner Mongolia Engineering Laboratory for Big Data Analysis Technology Hohhot China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

Named Entity Recognition (NER) is one of the contents of Knowledge Extraction (KE) that transforms data into knowledge representation. However, Chinese NER faces the problem of lacking clear word boundaries that limit the effectiveness of the KE. Although the flat lattice Transformer (FLAT) framework, which converts lattice structure into a flat structure including a set of spans, can effectively improve this problem and obtain advanced results, there still exist the problems of insensitivity to entity importance weights and insufficient feature learning. This paper proposes a weighted flat lattice Transformer architecture for Chinese NER, namely WFLAT. The WFLAT first adds a weight matrix into self-attention calculation, which can obtain finer-grained partitioning of entities to improve experimental performance, and then adopts a multi-layer Transformer encoder with each layer using a multi-head self-attention mechanism. Extensive experimental results on benchmarks demonstrate that our proposed KE model can obtain state-of-the-art performance for the Chinese NER task.

关键词： Representation learning Computational modeling Memory management Lattices Named entity recognition Transforms Knowledge representation

来源：评论

学校读者我要写书评

暂无评论

Learning with Open-world Noisy data via Class-independent Margin in Dual Representation Space 39

Learning with Open-world Noisy Data via Class-independent Ma...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

ISBN: (纸本)157735897X

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Clustering Combination Method Using Intuitionistic Fuzzy Similarity in Software Module Clustering

Hierarchical Clustering Combination Method Using Intuitionis...

引用

International Conference on Networking and Network Applications (NaNA)

作者： Hong Xia Bo Wang Yongkang Zhang Yanping Chen School of Computer Science and Technology Xi'an University of Posts and Telecommunications Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi 'an Key Laboratory of Big Data and Intelligent Computing Xi'an Shaanxi China

In order to solve the problem that the similarity method used in software module clustering can produce arbitrary decision, and the description matrix of dendrogram generated by base clustering in hierarchical clustering combination does not consider more characteristics of entities, a hierarchical clustering combination method based on intuitionistic fuzzy similarity (HCC-IFS) was proposed. In the process of entity similarity calculation, the intuitionistic fuzzy set theory and similarity calculation method are used to provide membership and non-membership attributes for each entity, so as to improve the merging efficiency and solve arbitrary decision problems. In the description matrix representation of base clustering, the absolute and relative features obtained from the dendrogram are used to construct the description matrix, and the generated description matrix is combined. Finally, the proposed algorithm is verified by experiments. Experimental results show that HCC-IFS can produce better clustering results and improve the recovery quality of software architecture.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Big-Moe: Bypassing Isolated Gating For Generalized Multimodal Face Anti-Spoofing

Big-Moe: Bypassing Isolated Gating For Generalized Multimoda...

引用

International Conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Yingjie Ma Zitong Yu Xun Lin Weicheng Xie Linlin Shen College of Computer Science and Software Engineering Shenzhen University Great Bay University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Guangdong Provincial Key Laboratory of Intelligent Information Processing

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

In the domain of facial recognition security, multimodal Face Anti-Spoofing (FAS) is essential for countering presentation attacks. However, existing technologies encounter challenges due to modality biases and imbalances, as well as domain shifts. Our research introduces a Mixture of Experts (MoE) model to address these issues effectively. We identified three limitations in traditional MoE approaches to multimodal FAS: (1) Coarse-grained experts’ inability to capture nuanced spoofing indicators; (2) Gated networks’ susceptibility to input noise affecting decision-making; (3) MoE’s sensitivity to prompt tokens leading to overfitting with conventional learning methods. To mitigate these, we propose the Bypass Isolated Gating MoE (BIG-MoE) framework, featuring: (1) Fine-grained experts for enhanced detection of subtle spoofing cues; (2) An isolation gating mechanism to counteract input noise; (3) A novel differential convolutional prompt bypass enriching the gating network with critical local features, thereby improving perceptual capabilities. Extensive experiments on four benchmark datasets demonstrate significant generalization performance improvement in multimodal FAS task. The code is released at https://***/murInJ/BIG-MoE.

关键词： Convolutional codes Sensitivity Convolution Face recognition Noise Logic gates Feature extraction Security Speech processing Overfitting

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：