检索结果-内蒙古大学图书馆

open-set learning under covariate shift

MACHINE learning 2024年第4期113卷 1643-1659页

作者： Shao, Jie-Jing Yang, Xiao-Wen Guo, Lan-Zhe Nanjing Univ Natl Key Lab Novel Software Technol Nanjing 210023 Peoples R China

open-set learning deals with the testing distribution where there exist samples from the classes that are unseen during training. They aim to classify the seen classes and recognize the unseen classes. Previous studies typically assume that the marginal distribution of the seen classes is fixed across the training and testing distributions. In many real-world applications, however, there may exist covariate shift between them, i.e., the marginal distribution of seen classes may shift. We call this kind of problem as open-set learning under covariate shift, aim to robustly classify the seen classes under covariate shift and be aware of the unseen *** present a new open-set learning framework with covariate generalization based on supervised contrastive learning, called SC-OSG, inspired by the latent connection between contrastive learning and representation invariance. Specifically, we theoretically justify supervised contrastive learning that could promote the conditional invariance of representations, a critical condition for covariate generalization. SC-OSG generates multi-source samples to promote the representation invariance and improve the covariate generalization. Based on this, we propose a detection score that is specific to the proposed training scheme. We evaluate the effectiveness of our method on several real-world datasets, on all of which we achieve competitive results with state-of-the-art methods.

关键词： open-set learning Out-of-distribution generalization Representation learning Image classification

来源：评论

学校读者我要写书评

暂无评论

PSEUDO-UNKNOWN CLASS GUIDED-BASED open-set learning NETWORK FOR SAR AUTOMATIC TARGET RECOGNITION

PSEUDO-UNKNOWN CLASS GUIDED-BASED OPEN-SET LEARNING NETWORK ...

引用

IEEE International Geoscience and Remote Sensing Symposium (IGARSS)

作者： Li, Yue Ren, Haohao Miao, Lei Zou, Lin Zhou, Yun Univ Elect Sci & Technol China Sch Informat & Commun Engn Chengdu 611731 Peoples R China

ISBN: (纸本)9798350360332;9798350360325

Most synthetic aperture radar (SAR) automatic target recognition (ATR) methods are developed for the closed-set environment, so these ATR methods can only identify known classes in the target library. However, it is known that the real scenario is open, so it requires the ATR model should be capable of identifying unknown categories while classifying known categories. Therefore, this paper proposes a pseudo-unknown class guided-based open-set learning network for SAR ATR tasks. First, to enhance the separability between known categories, a separable feature embedding space based on von Mises-Fisher (vMF) distribution is established. Second, unknown class decision boundaries are constructed based on pseudo-unknown classes synthesized by known categories, and are expanded based on the idea of contrastive learning, which is very helpful in promoting the ability of the model to identify unknown categories. Experiments on moving and stationary target acquisition and recognition (MSTAR) dataset demonstrate the effectiveness of the proposed method.

关键词： Synthetic aperture radar automatic target recognition open-set learning contrastive learning

来源：评论

学校读者我要写书评

暂无评论

A Robust open-set Multi-Instance learning for Defending Adversarial Attacks in Digital Image

引用

IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 2024年 19卷 2098-2111页

作者： Uddin, Kutub Yang, Yoonmo Jeong, Tae Hyun Oh, Byung Tae Korea Aerosp Univ Sch Elect & Informat Engn Goyang 10540 South Korea Korea Aerosp Univ Sch Comp Engn Goyang 10540 South Korea

In recent times, digital image forensics is gaining increased attention in multimedia forensics owing to the widespread scam alertness. Several forensic methods have been studied to establish the integrity of digital images by disclosing manipulation fingerprints. Anti-forensic (AF) attacks on manipulated images, particularly deep learning-based adversarial attacks using generative adversarial network (GAN), have been successfully applied to delude forensic methods. Consequently, an efficacious, efficient, and robust counter-AF (CAF) method is required to secure the integrity of digital images. In this study, we propose a robust open-set multi-instance learning approach for exposing GAN-based AF on manipulated images by introducing additional GAN-based operations. First, we generate multiple real instances from real images using multiple additional generators. Then we train an embedding network collaboratively with multiple real instances in an open-set fashion. During training, the embedding network learns only real images and has no prior knowledge regarding AF images. In the testing phase, real and AF images are processed for detection. The proposed open-set CAF method can effectively detect AF images and is more robust against transferable updating.

关键词： Forensics Deepfakes Generative adversarial networks Image coding Training Digital images Fingerprint recognition Multimedia forensics open-set learning multi-instance learning adversarial attacks counter-anti-forensics

来源：评论

学校读者我要写书评

暂无评论

W-DOE: Wasserstein Distribution-Agnostic Outlier Exposure

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2025年第5期47卷 3530-3545页

作者： Wang, Qizhou Han, Bo Liu, Yang Gong, Chen Liu, Tongliang Liu, Jiming Hong Kong Baptist Univ Dept Comp Sci Kowloon Tong Hong Kong Peoples R China Shanghai Jiao Tong Univ Dept Automat Shanghai 200240 Peoples R China Univ Sydney Fac Engn Sydney AI Ctr Camperdown NSW 2050 Australia Univ Sydney Fac Engn Sch Comp Sci Camperdown NSW 2050 Australia

In open-world environments, classification models should be adept at identifying out-of-distribution (OOD) data whose semantics differ from in-distribution (ID) data, leading to the emerging research in OOD detection. As a promising learning scheme, outlier exposure (OE) enables the models to learn from auxiliary OOD data, enhancing model representations in discerning between ID and OOD patterns. However, these auxiliary OOD data often do not fully represent real OOD scenarios, potentially biasing our models in practical OOD detection. Hence, we propose a novel OE-based learning method termed Wasserstein Distribution-agnostic Outlier Exposure (W-DOE), which is both theoretically sound and experimentally superior to previous works. The intuition is that by expanding the coverage of training-time OOD data, the models will encounter fewer unseen OOD cases upon deployment. In W-DOE, we achieve additional OOD data to enlarge the OOD coverage, based on a new data synthesis approach called implicit data synthesis (IDS). It is driven by our new insight that perturbing model parameters can lead to implicit data transformation, which is simple to implement yet effective to realize. Furthermore, we suggest a general learning framework to search for the synthesized OOD data that can benefit the models most, ensuring the OOD performance for the enlarged OOD coverage measured by the Wasserstein metric. Our approach comes with provable guarantees for open-world settings, demonstrating that broader OOD coverage ensures reduced estimation errors and thereby improved generalization for real OOD cases. We conduct extensive experiments across a series of representative OOD detection setups, further validating the superiority of W-DOE against state-of-the-art counterparts in the field.

关键词： Out-of-distribution detection reliable machine learning open-set learning open-set learning open-set learning

来源：评论

学校读者我要写书评

暂无评论

Certainty and Transferability Guided Few-Shot open-set Cross-Domain Fault Diagnosis

引用

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS 2025年第4期21卷 2997-3006页

作者： An, Yiyao Zhang, Ke Chai, Yi Zhu, Zhiqin Li, Yuanyuan Chongqing Univ Posts & Telecommun Sch Automat Chongqing 400065 Peoples R China Chongqing Univ Sch Automat Chongqing 400044 Peoples R China

A certainty and transferability guided few-shot domain adaptation network is proposed to address few-shot open-set cross-domain fault diagnosis in this article. The proposed method is composed of a feature extractor, a certainty-guided prototypical contrastive module and a transferability weighting domain adaptation module. The certainty-guided prototypical contrastive module based on samples informative importance is designed to enhance the data sensitivity with limited samples while achieving well class separation for open-set scenarios. The module infers informative importance of samples to guide method learn more effective representations. Meanwhile, correlation and uniformity principles are incorporated to alleviate prototype collapse. The transferability weighting domain adaptation module is designed to address great domain gaps and negative transfer caused by asymmetrical label spaces. The module quantifies sample transferability and down-weights the irrelevant samples based on their transferability scores. Experimental results on few-shot open-set cross-domain bearing fault diagnosis tasks demonstrated the superior and effectiveness of the proposed method.

关键词： Feature extraction Fault diagnosis Employee welfare Prototypes Informatics Few shot learning Degradation Correlation Contrastive learning Vectors Cross-domain fault diagnosis domain adaptation few-shot learning open-set learning prototypical contrastive learning (PCL)

来源：评论

学校读者我要写书评

暂无评论

ENHANCING open-set SPEAKER IDENTIFICATION THROUGH RAPID TUNING WITH SPEAKER RECIPROCAL POINTS AND NEGATIVE SAMPLE

ENHANCING OPEN-SET SPEAKER IDENTIFICATION THROUGH RAPID TUNI...

引用

2024 Spoken Language Technology Workshop

作者： Chen, Zhiyong Ai, Zhiqi Li, Xinnuo Xu, Shugong Shanghai Univ Sch Commun & Informat Engn Shanghai Peoples R China

ISBN: (纸本)9798350392265;9798350392258

This paper introduces a novel framework for open-set speaker identification in household environments, playing a crucial role in facilitating seamless human-computer interactions. Addressing the limitations of current speaker models and classification approaches, our work integrates an pretrained WavLM frontend with a few-shot rapid tuning neural network (NN) backend for enrollment, employing task-optimized Speaker Reciprocal Points learning (SRPL) to enhance discrimination across multiple target speakers. Furthermore, we propose an enhanced version of SRPL (SRPL+), which incorporates negative sample learning with both speech-synthesized and real negative samples to significantly improve open-set SID accuracy. Our approach is thoroughly evaluated across various multi-language text-dependent speaker recognition datasets, demonstrating its effectiveness in achieving high usability for complex household multi-speaker recognition scenarios. The proposed system enhanced open-set performance by up to 27% over the directly use of efficient WavLM base+ model. For detailed information on open-sourced implementation in our project website1.

关键词： Speaker identification speaker recognition open-set learning few-shot learning speech synthesis

来源：评论

学校读者我要写书评

暂无评论

STRUCTURE-AWARE RESIDUAL-CENTER REPRESENTATION FOR SELF-SUPERVISED open-set 3D CROSS-MODAL RETRIEVAL

STRUCTURE-AWARE RESIDUAL-CENTER REPRESENTATION FOR SELF-SUPE...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Xu, Yang Peng, Yifan Jiang, Yu Tsinghua Univ Sch Software Beijing Peoples R China Jilin Univ Coll Comp Sci & Technol Changchun Peoples R China

ISBN: (纸本)9798350390155;9798350390162

Existing methods of 3D cross-modal retrieval heavily lean on category distribution priors within the training set, which diminishes their efficacy when tasked with unseen categories under open-set environments. To tackle this problem, we propose the Structure-Aware Residual-Center Representation (SRCR) framework for self-supervised open-set 3D crossmodal retrieval. To address the center deviation due to category distribution differences, we utilize the Residual-Center Embedding (RCE) for each object by nested auto-encoders, rather than directly mapping them to the modality or category centers. Besides, we perform the Hierarchical Structure learning (HSL) approach to leverage the high-order correlations among objects for generalization, by constructing a heterogeneous hypergraph structure based on hierarchical intermodality, intra-object, and implicit-category correlations. Extensive experiments and ablation studies on four benchmarks demonstrate the superiority of our proposed framework compared to state-of-the-art methods.

关键词： 3D Object Retrieval Cross-Modal Retrieval open-set learning Self-Supervised learning Hypergraph

来源：评论

学校读者我要写书评

暂无评论

Triadic Elastic Structure Representation for open-set Incremental 3D Object Retrieval 24

Triadic Elastic Structure Representation for Open-Set Increm...

引用

4th Annual International Conference on Multimedia Retrieval (ICMR)

作者： Xu, Yang Feng, Yifan Bie, Lin Tsinghua Univ Sch Software Beijing Peoples R China

ISBN: (纸本)9798400706028

In open-set environments, the introduction of unseen classes adds a third stage of data for incremental learning, alongside seen classes of old and new. Existing methods by binary optimization between old and new classes struggle to model the complex triadic relationships among old, new, and unseen classes. In this paper, we introduce the Triadic Elastic Structure learning (TESR) framework for open-set incremental 3D object retrieval. Specifically, to overcome the Bi-Directional Catastrophic Forgetting (BDCF) problem in open-set incremental learning, we employ the Triadic Regularized Embedding (TRE) module. This module helps to globally preserve the triadic relationships among the three stages of classes, while simultaneously facilitating semantic-specific learning for new classes from a local perspective. To address the challenge of Bi-Directional Knowledge Transfer (BDKT), our method leverages high-order correlations among objects of different classes through the Elastic Structure Distillation (ESD) module, by constructing an elastic hypergraph based on incremental and global correlations. We construct four multi-modal datasets for this open-set incremental 3D object retrieval: OIES, OINT, OIMN, and OIAB. Extensive experiments and ablation studies on these four benchmarks demonstrate the superiority of our method over current state-of-the-art approaches.

关键词： 3D Object Retrieval open-set learning Incremental learning Multi-Modal Fusion Hypergraph

来源：评论

学校读者我要写书评

暂无评论

Enhancing open-World Bacterial Raman Spectra Identification by Feature Regularization for Improved Resilience against Unknown Classes

引用

CHEMICAL & BIOMEDICAL IMAGING 2024年第6期2卷 442-452页

作者： Balytskyi, Yaroslav Kalashnyk, Nataliia Hubenko, Inna Balytska, Alina Mcnear, Kelly Wayne State Univ Dept Phys & Astron Detroit MI 48201 USA Natl Univ Civil Protect Ukraine UA-18034 Cherkassy Ukraine Cherkasy Med Acad UA-18000 Cherkassy Ukraine Univ Colorado UCCS BioFrontiers Ctr Colorado Springs CO 80918 USA

The combination of deep learning techniques and Raman spectroscopy shows great potential offering precise and prompt identification of pathogenic bacteria in clinical settings. However, the traditional closed-set classification approaches assume that all test samples belong to one of the known pathogens, and their applicability is limited since the clinical environment is inherently unpredictable and dynamic, unknown, or emerging pathogens may not be included in the available catalogs. We demonstrate that the current state-of-the-art neural networks identifying pathogens through Raman spectra are vulnerable to unknown inputs, resulting in an uncontrollable false positive rate. To address this issue, first we developed an ensemble of ResNet architectures combined with the attention mechanism that achieves a 30-isolate accuracy of 87.8 +/- 0.1%. Second, through the integration of feature regularization by the Objectosphere loss function, our model both achieves high accuracy in identifying known pathogens from the catalog and effectively separates unknown samples drastically reducing the false positive rate. Finally, the proposed feature regularization method during training significantly enhances the performance of out-of-distribution detectors during the inference phase improving the reliability of the detection of unknown classes. Our algorithm for Raman spectroscopy empowers the identification of previously unknown, uncataloged, and emerging pathogens ensuring adaptability to future pathogens that may surface. Moreover, it can be extended to enhance open-set medical image classification, bolstering its reliability in dynamic operational settings.

关键词： Raman spectroscopy machine learning ResNet pathogen identification open-set learning Objectosphere

来源：评论

学校读者我要写书评

暂无评论

Leveraging Attribute Knowledge for open-set Action Recognition

Leveraging Attribute Knowledge for Open-set Action Recogniti...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Yang, Kaixiang Gao, Junyu Feng, Yangbo Xu, Changsheng Tianjin Univ Technol Sch Comp Sci & Engn Tianjin Peoples R China Chinese Acad Sci State Key Lab Multimodal Artificial Intelligence Beijing Peoples R China

ISBN: (纸本)9781665468916

open-set action recognition(OSAR) aims to recognize known classes and reject unknown classes. Most OSAR methods focus on learning a favorable threshold to distinguish known and unknown samples in a pure data-driven manner. However, these methods do not utilize the prior knowledge of action classes. In this paper, we propose to Leverage Attribute Knowledge (LAK) for OSAR. Specifically, the class-attribute knowledge learning is designed to integrate attribute knowledge into the model based on spatial-temporal features. Here, attributes are used as a bridge, linking known and unknown classes implicitly to make up the knowledge gap. Furthermore, a learnable relation matrix is adaptively adjusted during training to obtain the class-attribute relations that are expected to be generalized in open-set settings. Extensive experiments on three popular datasets show that the proposed method achieves state-of-the-art performance.

关键词： open-set learning action recognition knowledge graph

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：