检索结果-内蒙古大学图书馆

Multi-Instance Partial-Label Learning with Margin Adjustment

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Tang, Wei Yang, Yin-Fang 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

Multi-instance partial-label learning (MIPL) is an emerging learning framework where each training sample is represented as a multi-instance bag associated with a candidate label set. Existing MIPL algorithms often overlook the margins for attention scores and predicted probabilities, leading to suboptimal generalization performance. A critical issue with these algorithms is that the highest prediction probability of the classifier may appear on a non-candidate label. In this paper, we propose an algorithm named MIPLMA, i.e., Multi-Instance Partial-Label learning with Margin Adjustment, which adjusts the margins for attention scores and predicted probabilities. We introduce a margin-aware attention mechanism to dynamically adjust the margins for attention scores and propose a margin distribution loss to constrain the margins between the predicted probabilities on candidate and non-candidate label sets. Experimental results demonstrate the superior performance of MIPLMA over existing MIPL algorithms, as well as other well-established multi-instance learning algorithms and partial-label learning algorithms. Copyright © 2025, The Authors. All rights reserved.

关键词： Contrastive Learning

学校读者我要写书评

暂无评论

2021 IEEE International Conference on Artificial Intelligence and Industrial Design, AIID 2021

作者： Changhu, Cheng Peng, Yang School of Computer Science and Engineering Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education Southeast University Nanjing China

ISBN: (纸本)9780738110837

Few-shot learning aims to build a classification model by training a small amount of labeled sample data, which can be well adapted to new domains. The key point of few-shot learning is that a small amount of sample data cannot reflect the true data distribution. Training on a small amount of sample data will lead to over-fitting of the deep neural network model. The differences between different categories are ignored when using similarity measures for classification. This paper proposes a novel few-shot learning method based on similarity-difference relation network, which uses shallow wide residual network to extract the features of the training dataset and fuses them into a category prototype. Meanwhile, SDRN pays attention to the characterization of similarities and differences between positive and negative samples. This paper verifies the effectiveness of the similarity-difference relational network on the Mini-ImageNet and Tiered-ImageNet datasets. The experimental results show that the similarity-difference two-way relational network further improves image classification accuracy in the few-shot learning task. © 2021 IEEE.

关键词： Deep neural networks

Bridging the Gap: Learning Pace Synchronization for Open-World Semi-Supervised Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Ye, Bo Gan, Kai Wei, Tong Zhang, Min-Ling School of Computer Science and Engineering Southeast University Nanjing211189 China Key Lab. of Computer Network and Information Integration Southeast University MoE China

In open-world semi-supervised learning, a machine learning model is tasked with uncovering novel categories from unlabeled data while maintaining performance on seen categories from labeled data. The central challenge is the substantial learning gap between seen and novel categories, as the model learns the former faster due to accurate supervisory information. Moreover, capturing the semantics of unlabeled novel category samples is also challenging due to the missing label information. To address the above issues, we introduce 1) the adaptive synchronizing marginal loss which imposes class-specific negative margins to alleviate the model bias towards seen classes, and 2) the pseudo-label contrastive clustering which exploits pseudo-labels predicted by the model to group unlabeled data from the same category together in the output space. Extensive experiments on benchmark datasets demonstrate that previous approaches may significantly hinder novel class learning, whereas our method strikingly balances the learning pace between seen and novel classes, achieving a remarkable 3% average accuracy increase on the ImageNet dataset. Importantly, we find that fine-tuning the self-supervised pre-trained model significantly boosts the performance, which is overlooked in prior literature. Our code is available at https://***/yebo0216best/LPS-main. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

Comprehensive Perturbation Consistency for Semi-Supervised Change Detection in Remote Sensing Images

学校读者我要写书评

暂无评论

Comprehensive Perturbation Consistency for Semi-Supervised C...

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

作者： Zan Mao Xin Li Ze Luo Yingjuan Tang Dongmei Jiang Computer Network Information Center Chinese Academy of Sciences University of the Chinese Academy of Sciences PengCheng Laboratory National Key Laboratory of Advanced Vehicle Integration and Control Beijing Institute of Technology

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Currently, many change detection (CD) methods rely on supervised learning, which necessitates extensive manually annotated data, resulting in significant labor and time requirements. Recently, semi-supervised (SS) approaches have emerged in the CD community, which exploit large amounts of unlabeled data by utilizing consistency regularization. However, these methods do not consider the broader perturbation consistency to confer better generalization of the model. In this paper, we propose a novel SS CD framework with a comprehensive perturbation consistency called CPC, which extends perturbation consistency to the entire learning period. Specifically, our CPC combines the input, feature, and network perturbations for comprehensive perturb space. And, we design two distinct structures in practice, decoupled CPC and coupled CPC. Furthermore, we propose a change-aware input perturbation that introduces expensive annotation information to further expand the input perturb space. Extensive experiments conducted on the WHUCD, and GZ-CD datasets demonstrate that the proposal performs favorably against the state-of-the-art methods.

关键词： Codes Annotations Perturbation methods Supervised learning Signal processing Acoustics Proposals Labeling Speech processing Remote sensing

Exploiting Conjugate Label information for Multi-Instance Partial-Label Learning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Tang, Wei Zhang, Weijia Zhang, Min-Ling School of Computer Science and Engineering Southeast University Nanjing210096 China Key Lab. of Computer Network and Information Integration Southeast University MoE China School of Information and Physical Sciences The University of Newcastle NSW2308 Australia

Multi-instance partial-label learning (MIPL) addresses scenarios where each training sample is represented as a multi-instance bag associated with a candidate label set containing one true label and several false positives. Existing MIPL algorithms have primarily focused on mapping multi-instance bags to candidate label sets for disambiguation, disregarding the intrinsic properties of the label space and the supervised information provided by non-candidate label sets. In this paper, we propose an algorithm named ELIMIPL, i.e., Exploiting conjugate Label information for Multi-Instance Partial-Label learning, which exploits the conjugate label information to improve the disambiguation performance. To achieve this, we extract the label information embedded in both candidate and non-candidate label sets, incorporating the intrinsic properties of the label space. Experimental results obtained from benchmark and real-world datasets demonstrate the superiority of the proposed ELIMIPL over existing MIPL algorithms and other well-established partial-label learning algorithms. Copyright © 2024, The Authors. All rights reserved.

关键词：

Complementary Classifier Induced Partial Label Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Jia, Yuheng Si, Chongjie Zhang, Min-Ling Key Laboratory of Computer Network and Information Integration School of Computer Science and Engineering Nanjing210096 China MoE Key Lab of Artificial Intelligence AI Institute Shanghai200240 China

In partial label learning (PLL), each training sample is associated with a set of candidate labels, among which only one is valid. The core of PLL is to disambiguate the candidate labels to get the ground-truth one. In disambiguation, the existing works usually do not fully investigate the effectiveness of the non-candidate label set (a.k.a. complementary labels), which accurately indicates a set of labels that do not belong to a sample. In this paper, we use the non-candidate labels to induce a complementary classifier, which naturally forms an adversarial relationship against the traditional PLL classifier, to eliminate the false-positive labels in the candidate label set. Besides, we assume the feature space and the label space share the same local topological structure captured by a dynamic graph, and use it to assist disambiguation. Extensive experimental results validate the superiority of the proposed approach against state-of-the-art PLL methods on 4 controlled UCI data sets and 6 real-world data sets, and reveal the usefulness of complementary learning in PLL. The code has been released in the link https://***/Chongjie-Si/PL-CL. Copyright © 2023, The Authors. All rights reserved.

关键词： Topology

EAT: Towards Long-Tailed Out-of-Distribution Detection

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wei, Tong Wang, Bo-Lin 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

Despite recent advancements in out-of-distribution (OOD) detection, most current studies assume a class-balanced in-distribution training dataset, which is rarely the case in real-world scenarios. This paper addresses the challenging task of long-tailed OOD detection, where the in-distribution data follows a long-tailed class distribution. The main difficulty lies in distinguishing OOD data from samples belonging to the tail classes, as the ability of a classifier to detect OOD instances is not strongly correlated with its accuracy on the in-distribution classes. To overcome this issue, we propose two simple ideas: (1) Expanding the in-distribution class space by introducing multiple abstention classes. This approach allows us to build a detector with clear decision boundaries by training on OOD data using virtual labels. (2) Augmenting the context-limited tail classes by overlaying images onto the context-rich OOD data. This technique encourages the model to pay more attention to the discriminative features of the tail classes. We provide a clue for separating in-distribution and OOD data by analyzing gradient noise. Through extensive experiments, we demonstrate that our method outperforms the current state-of-the-art on various benchmark datasets. Moreover, our method can be used as an add-on for existing long-tail learning approaches, significantly enhancing their OOD detection performance. Code is available at: https://***/Stomachache/Long-Tailed-OOD-Detection. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

Gaia: Ground Station-Centric Mobility Management for LEO Satellite networks

学校读者我要写书评

暂无评论

Gaia: Ground Station-Centric Mobility Management for LEO Sat...

IEEE International Conference on Communications (ICC)

作者： Xiaxin Zhou Tian Pan Zhaokun Yang Sirui Su Jun Hu Guohao Ruan Junkai Huang Tao Huang Yunjie Liu Beijing University of Posts and Telecommunications Beijing China Purple Mountain Laboratories Nanjing China Key Laboratory of Computer Network and Information Integration Ministry of Education Southeast University China

ISBN: (数字)9781728190549

ISBN: (纸本)9781728190556

For mega-scale low Earth orbit (LEO) satellite constellations, the relative position changes between satellites and ground terminals pose challenges for end-to-end TCP session maintenance, which serves as the substrate for many Internet services. Mobile IP resolves the session maintenance issue by in-troducing a binding mechanism between the care-of address and home address; however, this also leads to inefficient triangular routing. Our recently proposed LISP-LEO, through partition-satellite mapping, routes traffic to the service satellite above the destination terminal's partition, addressing the triangular routing problem. However, due to the corner case of partition-satellite mapping, LISP-LEO introduces the issue of the last-hop route selection, as well as the associated per-terminal registration states on the satellite, making the solution non-scalable. In this work, we propose Gaia, a ground station-centric mobility management scheme for LEO satellite networks. Gaia maintains a precise mapping of each ground terminal's IP and its geographical location. When receiving traffic from a source terminal, the access satellite can, based on the geographical location of the destination terminal carried by the traffic, directly locate the satellite above the destination terminal and tunnel the traffic to it. In addition, to reduce the satellite's burden, we add a DNS-like querying mechanism by offloading the mapping of terminal IPs and geographical locations to the ground station. The evaluation shows that Gaia outperforms Mobile IP and LISP-LEO in both end-to-end latency and on-board resource consumption.

关键词： Satellite constellations Satellites Web and internet services Low earth orbit satellites Production Routing Maintenance

D-Router: Decoupled Content Routers with Remote Content Store

学校读者我要写书评

暂无评论

D-Router: Decoupled Content Routers with Remote Content Stor...

IEEE International Conference on Communications (ICC)

作者： Shuyi Chen Tian Pan Chunyang Wu Guohao Ruan Jiao Zhang Tao Huang Yunjie Liu Beijing University of Posts and Telecommunications Beijing China Purple Mountain Laboratories Nanjing China Key Laboratory of Computer Network and Information Integration Ministry of Education Southeast University China

ISBN: (数字)9781728190549

ISBN: (纸本)9781728190556

Named Data networking (NDN) enables efficient content distribution through in-network caching. However, the additional states of network intermediary nodes make NDN forwarding more burdensome, and the unpredictability of cache hits during forwarding leads to uncertain content retrieval latency. To overcome performance bottlenecks at the router's data plane and enhance network determinism, we propose the decoupled content router with remote content store (D-Router). This novel architecture decouples the local content store (CS) from routers and introduces the remote CS device for pooling important content. When Interest packets arrive at a router whose CS is overloaded, we ensure determinism by forwarding them to the remote CS for processing if the requested content is cached there, preventing blocking before the local CS of routers and potential random cache hits along the forwarding path. The dual-path bypass forwarding is supported through the design of routers and a dual-path routing protocol. D-Router is compatible with traditional NDN. Experiments show notable enhancements in data plane performance, including a 30% reduction in round-trip time (RTT), a 25% increase in throughput, improved determinism, and reduced network jitter. Additionally, the decoupling of CS makes it easier for network administrators to deploy network upgrades.

关键词： Performance evaluation Jitter Throughput Routing protocols