检索结果-内蒙古大学图书馆

Multi-dimensional classification via stacked dependency exploitation

学校读者我要写书评

暂无评论

Science China(information Sciences) 2020年第12期63卷 104-117页

作者： Bin-Bin JIA Min-Ling ZHANG School of Computer Science and Engineering Southeast University College of Electrical and Information Engineering Lanzhou University of Technology Key Laboratory of Computer Network and Information Integration (Southeast University) Ministry of EducationChina Collaborative Innovation Center of Wireless Communications Technology

Multi-dimensional classification(MDC) aims to build classification models for multiple heterogenous class spaces simultaneously, where each class space characterizes the semantics of an object w.r.t. one specific dimension. Modeling dependencies among class spaces plays a key role in solving MDC tasks, where most approaches work by assuming directed acyclic graph(DAG) structure or random chaining structure over class spaces. Different from existing probabilistic strategies, a deterministic strategy named Seem for dependency modeling is proposed in this paper via stacked dependency exploitation. In the first-level, pairwise dependencies are considered which can be modeled more reliably than modeling full dependencies among all class spaces by DAG or chaining structure. In the second-level, the class label of unseen instance *** class space is determined by adaptively stacking predictive outputs from first-level pairwise *** results show that stacked dependency exploitation leads to superior performance against stateof-the-art MDC approaches.

关键词： machine learning multi-dimensional classification class dependencies deterministic strategy stacked dependency exploitation

Transformer-based Multi-Instance Learning for Weakly Supervised Object Detection

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wang, Zhaofei Zhang, Weijia Zhang, Min-Ling School of Computer Science and Engineering Southeast University Nanjing210096 China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education China School of Information and Physical Sciences The University of Newcastle CallaghanNSW2308 Australia

Weakly Supervised Object Detection (WSOD) enables the training of object detection models using only image-level annotations. State-of-the-art WSOD detectors commonly rely on multi-instance learning (MIL) as the backbone of their detectors and assume that the bounding box proposals of an image are independent of each other. However, since such approaches only utilize the highest score proposal and discard the potentially useful information from other proposals, their independent MIL backbone often limits models to salient parts of an object or causes them to detect only one object per class. To solve the above problems, we propose a novel backbone for WSOD based on our tailored Vision Transformer named Weakly Supervised Transformer Detection network (WSTDN). Our algorithm is not only the first to demonstrate that self-attention modules that consider inter-instance relationships are effective backbones for WSOD, but also we introduce a novel bounding box mining method (BBM) integrated with a memory transfer refinement (MTR) procedure to utilize the instance dependencies for facilitating instance refinements. Experimental results on PASCAL VOC2007 and VOC2012 benchmarks demonstrate the effectiveness of our proposed WSTDN and modified instance refinement modules. Copyright © 2023, The Authors. All rights reserved.

关键词： Object detection

Disambiguated Attention Embedding for Multi-Instance Partial-Label Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Tang, Wei Zhang, Weijia Zhang, Min-Ling School of Computer Science and Engineering Southeast University Nanjing210096 China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education China School of Information and Physical Sciences The University of Newcastle CallaghanNSW2308 Australia

In many real-world tasks, the concerned objects can be represented as a multi-instance bag associated with a candidate label set, which consists of one ground-truth label and several false positive labels. Multi-instance partial-label learning (MIPL) is a learning paradigm to deal with such tasks and has achieved favorable performances. Existing MIPL approach follows the instance-space paradigm by assigning augmented candidate label sets of bags to each instance and aggregating bag-level labels from instance-level labels. However, this scheme may be suboptimal as global bag-level information is ignored and the predicted labels of bags are sensitive to predictions of negative instances. In this paper, we study an alternative scheme where a multi-instance bag is embedded into a single vector representation. Accordingly, an intuitive algorithm named DEMIPL, i.e., Disambiguated attention Embedding for Multi-Instance Partial-Label learning, is proposed. DEMIPL employs a disambiguation attention mechanism to aggregate a multi-instance bag into a single vector representation, followed by a momentum-based disambiguation strategy to identify the ground-truth label from the candidate label set. Furthermore, we introduce a real-world MIPL dataset for colorectal cancer classification. Experimental results on benchmark and real-world datasets validate the superiority of DEMIPL against the compared MIPL and partial-label learning approaches. Copyright © 2023, The Authors. All rights reserved.

关键词： Diseases

Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurts

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Jiang-Xin, Shi Tong, Wei Zhi, Zhou Jie-Jing, Shao Xin-Yan, Han Yu-Feng, Li National Key Laboratory for Novel Software Technology Nanjing University China School of Artificial Intelligence Nanjing University China School of Computer Science and Engineering Southeast University China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education China

The fine-tuning paradigm in addressing long-tail learning tasks has sparked significant interest since the emergence of foundation models. Nonetheless, how fine-tuning impacts performance in long-tail learning was not explicitly quantified. In this paper, we disclose that heavy fine-tuning may even lead to non-negligible performance deterioration on tail classes, and lightweight fine-tuning is more effective. The reason is attributed to inconsistent class conditions caused by heavy fine-tuning. With the observation above, we develop a low-complexity and accurate long-tail learning algorithms LIFT with the goal of facilitating fast prediction and compact models by adaptive lightweight fine-tuning. Experiments clearly verify that both the training time and the learned parameters are significantly reduced with more accurate predictive performance compared with state-of-the-art approaches. The implementation code is available at https://***/shijxcs/LIFT. Copyright © 2023, The Authors. All rights reserved.

关键词： Learning algorithms

SEE-Few: Seed, Expand and Entail for Few-shot Named Entity Recognition

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Yang, Zeng Zhang, Linhai Zhou, Deyu School of Computer Science and Engineering Key Laboratory of Computer Network and Information Integration Ministry of Education Southeast University China

Few-shot named entity recognition (NER) aims at identifying named entities based on only few labeled instances. Current few-shot NER methods focus on leveraging existing datasets in the rich-resource domains which might fail in a training-from-scratch setting where no source-domain data is used. To tackle training-from-scratch setting, it is crucial to make full use of the annotation information (the boundaries and entity types). Therefore, in this paper, we propose a novel multitask (Seed, Expand and Entail) learning framework, SEE-Few, for Few-shot NER without using source domain data. The seeding and expanding modules are responsible for providing as accurate candidate spans as possible for the entailing module. The entailing module reformulates span classification as a textual entailment task, leveraging both the contextual clues and entity type information. All the three modules share the same text encoder and are jointly learned. Experimental results on four benchmark datasets under the training-from-scratch setting show that the proposed method outperformed state-of-the-art few-shot NER methods with a large margin. Copyright © 2022, The Authors. All rights reserved.

关键词： Classification (of information)

Exploring Faithful Rationale for Multi-hop Fact Verification via Salience-Aware Graph Learning

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Si, Jiasheng Zhu, Yingjie Zhou, Deyu School of Computer Science and Engineering Key Laboratory of Computer Network and Information Integration Ministry of Education Southeast University China

The opaqueness of the multi-hop fact verification model imposes imperative requirements for explainability. One feasible way is to extract rationales, a subset of inputs, where the performance of prediction drops dramatically when being removed. Though being explainable, most rationale extraction methods for multi-hop fact verification explore the semantic information within each piece of evidence individually, while ignoring the topological information interaction among different pieces of evidence. Intuitively, a faithful rationale bears complementary information being able to extract other rationales through the multi-hop reasoning process. To tackle such disadvantages, we cast explainable multi-hop fact verification as subgraph extraction, which can be solved based on graph convolutional network (GCN) with salience-aware graph learning. In specific, GCN is utilized to incorporate the topological interaction information among multiple pieces of evidence for learning evidence representation. Meanwhile, to alleviate the influence of noisy evidence, the salience-aware graph perturbation is induced into the message passing of GCN. Moreover, the multi-task model with three diagnostic properties of rationale is elaborately designed to improve the quality of an explanation without any explicit annotations. Experimental results on the FEVEROUS benchmark show significant gains over previous state-of-the-art methods for both rationale extraction and fact verification. Copyright © 2022, The Authors. All rights reserved.

关键词： Message passing

An Accountable Anonymous Voting Scheme Based on One-time Ring Signature

学校读者我要写书评

暂无评论

An Accountable Anonymous Voting Scheme Based on One-time Rin...

Frontiers of Electronics, information and Computation Technologies (ICFEICT), International Conference on

作者： Yunqi Gu Zhuowei Shen School of Cyber Science and Engineering Southeast University Key Laboratory of Computer Networks and Information Integration (Southeast University) Ministry of Education Nanjing China

Electronic voting plays an increasingly important role in both economic life and social activities. The electronic voting scheme based on one-time ring signature and blockchain solves the problems of voter anonymity, double voting, and public verification, while achieving the openness and transparency of voting. However, it is not applicable to the multi-round voting scenario where the voting group is relatively fixed, nor does it consider the need for anonymous accountability and differential privacy protection. In this paper, based on one-time ring signature, stealth address, blacklist and whitelist, an improved accountability anonymous voting scheme is proposed to enhance the practicability of the scheme. The security analysis shows that the scheme confirms to the basic security standards of an electronic voting system.

关键词：

Large, Small or Both: A Novel Data Augmentation Framework Based on Language Models for Debiasing Opinion Summarization

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Yanyue Li, Pengfei Lai, Yilong Zhou, Deyu He, Yulan School of Computer Science and Engineering Key Laboratory of Computer Network and Information Integration Ministry of Education Southeast University China Department of Informatics King’s College London United Kingdom The Alan Turing Institute United Kingdom

As more than 70% of reviews in the existing opinion summary data set are positive, current opinion summarization approaches are reluctant to generate negative summaries given the input of negative texts. To address such sentiment bias, a direct approach without the over-reliance on a specific framework is to generate additional data based on large language models to balance the emotional distribution of the dataset. However, data augmentation based on large language models faces two disadvantages: 1) the potential issues or toxicity in the augmented data;2) the expensive costs. Therefore, in this paper, we propose a novel data augmentation framework based on both large and small language models for debiasing opinion summarization. In specific, a small size of synthesized negative reviews is obtained by rewriting the positive text via a large language model. Then, a disentangle reconstruction model is trained based on the generated data. After training, a large amount of synthetic data can be obtained by decoding the new representation obtained from the combination of different sample representations and filtering based on confusion degree and sentiment classification. Experiments have proved that our framework can effectively alleviate emotional bias same as using only large models, but more economically. Copyright © 2024, The Authors. All rights reserved.

关键词： Data assimilation

A Novel Early Warning Model for Hand, Foot and Mouth Disease Prediction Based on a Graph Convolutional network

学校读者我要写书评

暂无评论

Biomedical and Environmental Sciences 2022年第6期35卷 494-503页

作者： JI Tian Jiao CHENG Qiang ZHANG Yong ZENG Han Ri WANG Jian Xing YANG Guan Yu XU Wen Bo LIU Hong Tu NHC Key Laboratory of Medical Virology and Viral Diseases National Institute for Viral Disease Control and PreventionChinese Center for Disease Control and PreventionBeijing 100026China Academy of Cyber Science and Engineering Southeast UniversityNanjing 211189JiangsuChina Center for Biosafety Mega Science Chinese Academy of SciencesWuhan 430071HubeiChina Guangdong Center for Disease Control and Prevention Guangzhou 511430GuangdongChina Shandong Center for Disease Control and Prevention Jinan 250014ShandongChina LIST Key Laboratory of Computer Network and Information Integration(Southeast University)Ministry of EducationSoutheast UniversityNanjing 211189JiangsuChina

Objectives Hand,foot and mouth disease(HFMD)is a widespread infectious disease that causes a significant disease burden on *** achieve early intervention and to prevent outbreaks of disease,we propose a novel warning model that can accurately predict the incidence of *** We propose a spatial-temporal graph convolutional network(STGCN)that combines spatial factors for surrounding cities with historical incidence over a certain time period to predict the future occurrence of HFMD in Guangdong and Shandong between 2011 and *** 2011-2018 data served as the training and verification set,while data from 2019 served as the prediction *** important parameters were selected and verified in this model and the deviation was displayed by the root mean square error and the mean absolute *** As the first application using a STGCN for disease forecasting,we succeeded in accurately predicting the incidence of HFMD over a 12-week period at the prefecture level,especially for cities of significant *** This model provides a novel approach for infectious disease prediction and may help health administrative departments implement effective control measures up to 3 months in advance,which may significantly reduce the morbidity associated with HFMD in the future.

关键词： HFMD Early warning model STGCN Disease prediction