检索结果-内蒙古大学图书馆

open set classification of Hyperspectral images with energy models

INTERNATIONAL JOURNAL OF REMOTE SENSING 2023年第24期44卷 7876-7888页

作者： Alwadei, Bashair Mekhalfi, Mohamed Lamine Bazi, Yakoub Al Rahhal, Mohamad M. Zuair, Mansour King Saud Univ Coll Comp & Informat Sci Comp Engn Dept Riyadh Saudi Arabia Digital Ind Ctr Technol Vis Unit Trento Italy King Saud Univ Coll Appl Comp Sci Appl Comp Sci Dept Riyadh 11543 Saudi Arabia

Hyperspectral images are rich in spectral data, lending themselves well to pixel-level image classification tasks. Previous studies primarily focus on closed-set classification within the realm of hyperspectral image classification. However, real-world scenarios present the challenge of dealing with object classes not encountered during the training phase, a scenario known as open set classification, which has garnered less attention compared to the closed set paradigm. In this paper, we propose a methodology anchored on ConvMixer for tackling open-set classification by utilizing energy-based models. We incorporate a Selective Kernel Attention (SKA) to capture the notion that different feature maps usually correspond to different objects in deep neural networks. Our experimental validation, conducted on two datasets, specifically the WHU-Hi-HanChuan and WHU-Hi-HongHu datasets, showcases promising outcomes of the introduced method.

关键词： Hyperspectral image classification deep learning attention mechanisms open set classification energy score

来源：评论

学校读者我要写书评

暂无评论

Single and Combined Algorithms for open set classification on Image Datasets

引用

ACTA CYBERNETICA 2024年第3期26卷 297-322页

作者： Al-Shouha, Modafar Szucs, Gabor Budapest Univ Technol & Econ Dept Telecommun & Media Informat Muegyetem Rkp 3 H-1111 Budapest Hungary

Generally, classification models have closed nature, and they are constrained by the number of classes in the training data. Hence, classifying "unknown" - OOD (out-of-distribution) - samples is challenging, especially in the so called "open set" problem. We propose and investigate different solutions - single and combined algorithms - to tackle this task, where we use and expand a K- classifier to be able to identify K + 1 classes. They do not require any retraining or modification on the K- classifier architecture. We show their strengths when avoiding type I or type II errors is fundamental. We also present a mathematical representation for the task to estimate the K + 1 classification accuracy, and an inequality that defines its boundaries. Additionally, we introduce a formula to calculate the exact K +1 classification accuracy.

关键词： binary classification multi-class classification GAN out-of- distribution open set classification

来源：评论

学校读者我要写书评

暂无评论

S2OSC: A Holistic Semi-Supervised Approach for open set classification

引用

ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA 2022年第2期16卷 34-34页

作者： Yang, Yang Wei, Hongchen Sun, Zhen-Qiang Li, Guang-Yu Zhou, Yuanchun Xiong, Hui Yang, Jian Nanjing Univ Sci & Technol 200 Xiaolingwei Nanjing 210094 Jiangsu Peoples R China Nanjing Normal Univ Nanjing 210023 Jiangsu Peoples R China Chinese Acad Sci Comp Network & Informat Ctr 2 Dongshengnanlu Beijing 100083 Peoples R China Rutgers State Univ 1 Washington Pk Newark NJ 07102 USA

open set classification (OSC) tackles the problem of determining whether the data are in-class or out-ofclass during inference, when only provided with a set of in-class examples at training time. Traditional OSC methods usually train discriminative or generative models with the owned in-class data, and then utilize the pre-trained models to classify test data directly. However, these methods always suffer from the embedding confusion problem, i.e., partial out-of-class instances are mixed with in-class ones of similar semantics, making it difficult to classify. To solve this problem, we unify semi-supervised learning to develop a novel OSC algorithm, S2OSC, which incorporates out-of-class instances filtering and model re-training in a transductive manner. In detail, given a pool of newly coming test data, S2OSC firstly filters the mostly distinct out-of-class instances using the pre-trained model, and annotates super-class for them. Then, S2OSC trains a holistic classification model by combing in-class and out-of-class labeled data with the remaining unlabeled test data in a semi-supervised paradigm. Furthermore, considering that data are usually in the streaming form in real applications, we extend S2OSC into an incremental update framework (I-S2OSC), and adopt a knowledge memory regularization to mitigate the catastrophic forgetting problem in incremental update. Despite the simplicity of proposed models, the experimental results show that S2OSC achieves state-of-the-art performance across a variety of OSC tasks, including 85.4% of F1 on CIFAR-10 with only 300 pseudo-labels. We also demonstrate how S2OSC can be expanded to incremental OSC setting effectively with streaming data.

关键词： open set classification semi-supervised learning embedding confusion incremental learning

来源：评论

学校读者我要写书评

暂无评论

open set Audio classification Using Autoencoders Trained on Few Data

引用

SENSORS 2020年第13期20卷 3741.-3741.页

作者： Naranjo-Alcazar, Javier Perez-Castanos, Sergi Zuccarello, Pedro Antonacci, Fabio Cobos, Maximo Visualfy Benisano 46181 Spain Univ Valencia Comp Sci Dept Burjassot 46100 Spain Politecn Milan Dipartimento Elettron Informaz & Bioingn DEIB I-20133 Milan Italy

open-set recognition (OSR) is a challenging machine learning problem that appears when classifiers are faced with test instances from classes not seen during training. It can be summarized as the problem of correctly identifying instances from a known class (seen during training) while rejecting any unknown or unwanted samples (those belonging to unseen classes). Another problem arising in practical scenarios is few-shot learning (FSL), which appears when there is no availability of a large number of positive samples for training a recognition system. Taking these two limitations into account, a new dataset for OSR and FSL for audio data was recently released to promote research on solutions aimed at addressing both limitations. This paper proposes an audio OSR/FSL system divided into three steps: a high-level audio representation, feature embedding using two different autoencoder architectures and a multi-layer perceptron (MLP) trained on latent space representations to detect known classes and reject unwanted ones. An extensive set of experiments is carried out considering multiple combinations of openness factors (OSR condition) and number of shots (FSL condition), showing the validity of the proposed approach and confirming superior performance with respect to a baseline system based on transfer learning.

关键词： open set recognition open set classification audio classification autoencoders few-shot learning

来源：评论

学校读者我要写书评

暂无评论

open-set Audio classification with Limited Training Resources based on Augmentation Enhanced Variational Auto-Encoder GAN with Detection-classification Joint Training 22

Open-Set Audio Classification with Limited Training Resource...

引用

Interspeech Conference

作者： Kah Kuan Teh Huy Dat Tran ASTAR Inst Infocomm Res Aural & Language Intelligence Dept Singapore Singapore

ISBN: (纸本)9781713836902

In this paper, we propose a novel method to address practical problems when deploying audio classification systems in operations that are the presence of unseen sound classes (open-set) and the limitation of training resources. To solve it, a novel method which embeds variational auto-encoder (VAE), data augmentation and detection-classification joint training into conventional GAN networks is proposed. The VAE input to GAN-generator helps to generate realistic outlier samples which are not too far from in-distribution class and hence improve the open-set discrimination capabilities of classifiers. Next, the augmentation enhanced GAN scheme developed in our previous work [4] for close-set audio classification, will help to address the limited training resources by in cooperating the physical data augmentation to work together with traditional GAN produced samples to prevent overfitting and improve the optimization convergences. The detection-classification joint training further steps on advantages of VAE and Augmentation GAN to further improving the performances of detection and classification tasks. The experiments carried out on Google Speech Command database show great improvements of open-set classification accuracy from 62.41% to 88.29% when using only 10% amount of training data.

关键词： Audio classification Limited Training Variational Autoencoder Generative Adversarial Networks open set classification Sinkhorn divergence

来源：评论

学校读者我要写书评

暂无评论

open-set Face classification for Access Monitoring Using Spatially-Organized Random Projections 17th

Open-Set Face Classification for Access Monitoring Using Spa...

引用

17th International Conference on Computer Information Systems and Industrial Management (CISIM)

作者： Skubalska-Rafajlowicz, Ewa Wroclaw Univ Sci & Technol Dept Comp Engn Fac Elect Wroclaw Poland

ISBN: (纸本)9783319999548;9783319999531

In this paper, we present an easy method of open-set face classification problem with application to access control and an identity verification. We use normal random projections as a method of feature extraction from face images. The image transformation consists of local projections of spatially-organized rectangular blocks of an image. Two classification algorithms are analyzed: the nearest neighbor method with scalar product similarity measure and individual acceptance/rejection thresholds and multinomial logistic regression. The computational complexity of designing the transformation is linear with respect to the size of images and does not depend on the form of image partition. Experiments performed on the ORL Database demonstrate that the proposed technique is simple and suitable not only for an access monitoring system but also for face verification. The contents of an image after RP-based transformation is hidden and will not be stably recoverable. So, this approach can be used in systems where the privacy-preserving property is important.

关键词： Random projections Access control Person authentication Face classification Privacy preserving Person identification open set classification

来源：评论

学校读者我要写书评

暂无评论

open set Online classification of Industrial Alarm Floods With Alarm Ranking

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2023年 72卷

作者： Alinezhad, Haniyeh Seyed Shang, Jun Chen, Tongwen Univ Alberta Dept Elect & Comp Engn Edmonton AB T6G 1H9 Canada

Alarm floods can cause serious safety problems in complex industrial plants by overwhelming a plant operator with many alarm annunciations in a short time interval. In a plant operation, there can be alarm flood scenarios that correspond to previously unseen abnormal situations. Therefore, early online assistance for plant operators in both previously known and new situations is of great importance. The aim of this article is to develop an operator assistance system based on early classification of alarm floods and alarm ranking. A weighting method is developed to model alarm flood sequences as feature vectors while preserving key characteristics of them, including the temporal information of alarms. The proposed weighting strategy is defined by considering early classification accuracy and can also provide ranking of alarms according to their relevance to the abnormal situation. To handle the new alarm flood scenarios, an open set classification method based on a systematic similarity threshold estimation is proposed. The effectiveness of the proposed approach is evaluated by using the Tennessee Eastman benchmark.

关键词： Alarm systems Safety Prediction algorithms Floods Systematics Real-time systems Random forests Alarm floods alarm ranking early operator assistance online classification open set classification

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Based open set Acoustic Scene classification 21

Deep Learning Based Open Set Acoustic Scene Classification

引用

Interspeech Conference

作者： Kwiatkowska, Zuzanna Kalinowski, Benjamin Kosmider, Michal Rykaczewski, Krzysztof Samsung R&D Inst Warsaw Poland

ISBN: (纸本)9781713820697

In this work, we compare the performance of three selected techniques in open set acoustic scenes classification (ASC). We test thresholding of the softmax output of a deep network classifier, which is the most popular technique nowadays employed in ASC. Further we compare the results with the openmax classifier which is derived from the computer vision field. As the third model, we use the Adapted Class-Conditioned Autoencoder (Adapted C2AE) which is our variation of another computer vision related technique called C2AE. Adapted C2AE encompasses a more fair comparison of the given experiments and simplifies the original inference procedure, making it more applicable in the real-life scenarios. We also analyse two training scenarios: without additional knowledge of unknown classes and another where a limited subset of examples from the unknown classes is available. We find that the C2AE based method outperforms the thresholding and openmax, obtaining 85.5% Area Under the Receiver Operating Characteristic curve (AUROC) and 66% of open set accuracy on data used in Detection and classification of Acoustic Scenes and Events Challenge 2019 Task 1C.

关键词： acoustic scenes open set classification deep learning conditional autoencoders

来源：评论

学校读者我要写书评

暂无评论

open set Wireless Standard classification Using Convolutional Neural Networks

Open Set Wireless Standard Classification Using Convolutiona...

引用

IEEE Communications Society (ComSoc)/AFCEA/IEEE Military Communications Conference (MILCOM)

作者： Shebert, Samuel R. Martone, Anthony E. Buehrer, R. Michael Virginia Tech Bradley Dept ECE Blacksburg VA 24061 USA US Army Res Lab Adelphi MD USA

ISBN: (纸本)9781665439565

In congested electromagnetic environments, cognitive radios require knowledge about other emitters in order to optimize their dynamic spectrum access strategy. Deep learning classification algorithms have been used to recognize the wireless signal standards of emitters with high accuracy, but are limited to classifying signal classes that appear in their training set. This diminishes the performance of deep learning classifiers deployed in the field because they cannot accurately identify signals from classes outside of the training set. In this paper, a convolution neural network based open set classifier is proposed with the ability to detect signal that are not from known classes by thresholding the output sigmoid activation. The open set classifier was trained on 4G LTE, 5G NR, IEEE 802.11ax, Bluetooth Low Energy 5.0, and Narrowband Internet-of-Things signals impaired with Rayleigh or Rician fading, AWGN, frequency offsets, and in-phase/quadrature imbalances. Then, the classifier was tested on OFDM, SC-FDMA, SC, AM, and FM signals, which did not appear in the training set classes. The closed set classifier achieves an average accuracy of 94.5% for known signals with SNR's greater than 0 dB, but by design, the closed set classifier cannot detect signals from unknown classes. On the other hand, the open set classifier retains an 86% accuracy for known signal classes, but can detect 95.5% of signals from unknown classes with SNR's greater than 0 dB.

关键词： Deep learning wireless standard identification open set classification 5G 4G WiFi cognitive radio

来源：评论

学校读者我要写书评

暂无评论

SV-Means: A Fast SVM-Based Level set Estimator for Phase-Modulated Radar Waveform classification

引用

IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING 2018年第1期12卷 191-201页

作者： Pavy, Anne Rigling, Brian Air Force Res Lab Sensors Directorate Dayton Dayton OH 45433 USA Wright State Univ Dept Elect Engn Dayton OH 45431 USA

In this paper, a novel algorithm, SV-Means, is formulated for open set radar waveform classification. The approach extends the quantile one-class support vector machine (q-OCSVM) density estimation algorithm into a classification formulation with inspiration from k-means and stochastic gradient descent principles. Phase-modulated radar waveform data is used to compare the primal and dual q-OCSVM (configured for classification) to SV-Means to verify the algorithm's classification and rejection performance. SV-Means is also shown to be an effective open set classification algorithm and is compared to these other open set classifiers: 1-vs-set machine, W-SVM, PI-SVM, and probabilistic open space (POS)-SVM. The SV-Means algorithm proves to achieve similar, and some cases better, performance against comparable algorithms in a fraction of the training time (as the data records increase and, in the case of the q-OCSVM, level sets increase). The SV-Means open set algorithm is an attractive adaptive classification framework using any feature extraction approach including deep-learning architectures.

关键词： open set classification one-class support vector machines random features waveform classification

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：