检索结果-内蒙古大学图书馆

out-of-distribution detection with non-semantic exploration

INFORMATION SCIENCES 2025年 705卷

作者： Fang, Zhen Lu, Jie Zhang, Guangquan Univ Technol Sydney Australian Artificial Intelligence Inst POB 123 Broadway NSW Australia

out-of-distribution (OOD) detection is crucial in modern deep learning applications, as it can identify OOD data drawn from distributions differing from those of the in-distribution (ID) data. Advanced OOD detection methods primarily rely on post-hoc strategies, which identify OOD data by analyzing the predictions of a model well-trained on ID data. However, deep models are known to be impacted by spurious features such as backgrounds, causing existing OOD detection methods to fail in identifying OOD data that share the same spurious features as ID data. Therefore, this paper studies how to mitigate spurious features to improve OOD detection. To address this challenge, we propose a novel method called Non-semantic Exploration OOD detection (NsED), which focuses on exploring and exploiting non-semantic features. In particular, NsED first explores non- semantic features in an OOD generalization manner. These non-semantic features are then used to train deep models to be more robust against spurious features. Through extensive experiments on representative benchmarks, we show that NsED significantly and consistently improves the detection performance of many representative post-hoc OOD detection methods.

关键词： out-of-distribution detection out-of-distribution generalization Machine learning

来源：评论

学校读者我要写书评

暂无评论

out-of-distribution detection by regaining lost clues

引用

ARTIFICIAL INTELLIGENCE 2025年 339卷

作者： Zhao, Zhilin Cao, Longbing Yu, Philip S. Macquarie Univ Sch Comp Sydney NSW 2109 Australia Sun Yat Sen Univ Sch Comp Sci & Engn Guangzhou 510275 Peoples R China Univ Illinois Chicago IL USA Tsinghua Univ Inst Data Sci Beijing Peoples R China

out-of-distribution (OOD) detection identifies samples in the test phase that are drawn from distributions distinct from that of training in-distribution (ID) samples for a trained network. According to the information bottleneck, networks that classify tabular data tend to extract labeling information from features with strong associations to ground-truth labels, discarding less relevant labeling cues. This behavior leads to a predicament in which OOD samples with limited labeling information receive high-confidence predictions, rendering the network incapable of distinguishing between ID and OOD samples. Hence, exploring more labeling information from ID samples, which makes it harder for an OOD sample to obtain high-confidence predictions, can address this over-confidence issue on tabular data. Accordingly, we propose a novel transformer chain (TC), which comprises a sequence of dependent transformers that iteratively regain discarded labeling information and integrate all the labeling information to enhance OOD detection. The generalization bound theoretically reveals that TC can balance ID generalization and OOD detection capabilities. Experimental results demonstrate that TC significantly surpasses state-of-the-art methods for OOD detection in tabular data.

关键词： out-of-distribution detection Transformer Ensemble learning Generalization AI safety

来源：评论

学校读者我要写书评

暂无评论

out-of-distribution detection by Quantifying the Uncertainty with the Stochastic Weight Ensemble

引用

HUMAN-CENTRIC COMPUTING AND INFORMATION SCIENCES 2025年 15卷 1-15页

作者： Cao, Zongjing Li, Yan Shin, Byeong-Seok Inha Univ Dept Elect & Comp Engn Incheon South Korea

The performance of a deep neural network (DNN) decreases significantly when it encounters out-of- distribution (OOD) samples that deviate from the training data distribution. Current OOD detection methods tend to overlook model uncertainty because measurements of model uncertainty require inferring the posterior distribution of the DNN parameters, which is intractable for a single-point estimate DNN, resulting in suboptimal performance. This paper introduces a novel OOD detection method utilizing a stochastic weight ensemble (SWE) to quantify model uncertainty. The SWE was created using multiple checkpoints traversed by a stochastic gradient descent optimizer. Each checkpoint represents a distinct model state within weight space, leading to diverse predictions for the same input. The proposed method was evaluated using multiple in-distribution and OOD benchmark datasets. The approach considers data and model uncertainties, providing a more robust and reliable detection performance. On a CIFAR-100 pre-trained on ResNet-50, the proposed method reduces the average FPRat95 by 8.05% compared to the maximum softmax probability score. Extensive experimental results showed that the proposed method achieves state-of-the-art OOD detection performance on common benchmarks.

关键词： Deep Ensemble out-of-distribution detection Stochastic Weight Ensemble

来源：评论

学校读者我要写书评

暂无评论

out-of-distribution detection Based on Multiple Metrics Fusion of Network Hidden Features

引用

IEEE ACCESS 2024年 12卷 145450-145458页

作者： Zhu, Qiuyu He, Yiwei Shanghai Univ Sch Commun & Informat Engn Shanghai 200444 Peoples R China

Traditional pattern recognition models achieve excellent classification performance. However, when out-of-distribution (OOD) samples, which are outside the training distribution of in-distribution (ID) data, are input into the model, the model often assigns excessively high confidence. Simply using the probability information of the output classification from the network for OOD detection does not yield satisfactory results. The paper starts with the hidden feature information from the intermediate layers of neural networks to design discriminative metrics, including the modulus ratio of input and output from the convolutional layers and the feature distribution differences of the Batch Normalization (BN) layers within the network. Combined with the OOD detection model based on predefined evenly-distribution class centroids (PEDCC)-Loss, we propose a fusion metric selection strategy. This strategy selects appropriate feature metrics for multi-feature fusion to achieve optimal detection capability for both ID and OOD samples simultaneously. Our method requires only training the classification network model, without any input pre-processing or specific OOD data pre-tuning. Extensive experiments on several benchmark datasets show that our approach achieves state-of-the-art performance in simultaneously recognizing ID and OOD samples while ensuring that the recognition rate of ID samples does not decrease. The code for the paper can be found at https://***/Hewell0/HiddenOOD.

关键词： Feature extraction Measurement Training Data models Semantics Neural networks Data mining Uncertainty Training data Posterior probability Pattern recognition out-of-distribution detection hidden features pattern recognition multiple metrics fusion

来源：评论

学校读者我要写书评

暂无评论

out-of-distribution detection by Cross-Class Vicinity distribution of In-distribution Data

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2024年第10期35卷 13777-13788页

作者： Zhao, Zhilin Cao, Longbing Lin, Kun-Yu Macquarie Univ Data Sci Lab Sydney NSW 2109 Australia Sun Yat sen Univ Sch Comp Sci & Engn Guagnzhou 515000 Peoples R China

Deep neural networks for image classification only learn to map in-distribution inputs to their corresponding ground-truth labels in training without differentiating out-of-distribution samples from in-distribution ones. This results from the assumption that all samples are independent and identically distributed (IID) without distributional distinction. Therefore, a pretrained network learned from in-distribution samples treats out-of-distribution samples as in-distribution and makes high-confidence predictions on them in the test phase. To address this issue, we draw out-of-distribution samples from the vicinity distribution of training in-distribution samples for learning to reject the prediction on out-of-distribution inputs. A cross-class vicinity distribution is introduced by assuming that an out-of-distribution sample generated by mixing multiple in-distribution samples does not share the same classes of its constituents. We, thus, improve the discriminability of a pretrained network by finetuning it with out-of-distribution samples drawn from the cross-class vicinity distribution, where each out-of-distribution input corresponds to a complementary label. Experiments on various in-/out-of-distribution datasets show that the proposed method significantly outperforms the existing methods in improving the capacity of discriminating between in-and out-of-distribution samples.

关键词： Training Detectors Neural networks Deep learning Uncertainty Image classification Standards deep neural networks mutual information out-of-distribution detection vicinity distribution

来源：评论

学校读者我要写书评

暂无评论

out-of-distribution detection with Virtual outlier Smoothing

引用

INTERNATIONAL JOURNAL OF COMPUTER VISION 2025年第2期133卷 724-741页

作者： Nie, Jun Luo, Yadan Ye, Shanshan Zhang, Yonggang Tian, Xinmei Fang, Zhen Univ Sci & Technol China Dept Elect Engn & Informat Sci Hefei Peoples R China Univ Queensland Sch Informat Technol & Elect Engn Brisbane Australia Univ Technol Sydney Australian Artificial Intelligence Inst Sydney Australia Hong Kong Baptist Univ Dept Comp Sci Hong Kong Peoples R China

Detecting out-of-distribution (OOD) inputs plays a crucial role in guaranteeing the reliability of deep neural networks (DNNs) when deployed in real-world scenarios. However, DNNs typically exhibit overconfidence in OOD samples, which is attributed to the similarity in patterns between OOD and in-distribution (ID) samples. To mitigate this overconfidence, advanced approaches suggest the incorporation of auxiliary OOD samples during model training, where the outliers are assigned with an equal likelihood of belonging to any category. However, identifying outliers that share patterns with ID samples poses a significant challenge. To address the challenge, we propose a novel method, Virtual outlier Smoothing (VOSo), which constructs auxiliary outliers using ID samples, thereby eliminating the need to search for OOD samples. Specifically, VOSo creates these virtual outliers by perturbing the semantic regions of ID samples and infusing patterns from other ID samples. For instance, a virtual outlier might consist of a cat's face with a dog's nose, where the cat's face serves as the semantic feature for model prediction. Meanwhile, VOSo adjusts the labels of virtual OOD samples based on the extent of semantic region perturbation, aligning with the notion that virtual outliers may contain ID patterns. Extensive experiments are conducted on diverse OOD detection benchmarks, demonstrating the effectiveness of the proposed VOSo. Our code will be available at https://***/junz-debug/VOSo.

关键词： out-of-distribution detection Label smoothing outlier exposure Learning with virtual data

来源：评论

学校读者我要写书评

暂无评论

out-of-distribution detection of Unknown False Data Injection Attack With Logit-Normalized Bayesian ResNet

引用

IEEE TRANSACTIONS ON SMART GRID 2024年第6期15卷 6005-6017页

作者： Feng, Guangxu Lao, Keng-Weng Chen, Ge Univ Macau State Key Lab Internet Things Smart City Macau Peoples R China Univ Macau Dept Elect & Comp Engn Macau Peoples R China Purdue Univ Elmore Family Sch Elect & Comp Engn W Lafayette IN 47907 USA

The progressive integration of cyber-physical systems in smart grids raises potential security concerns, exacerbating the risk of false data injection attack (FDIA) that leads to severe operational disruptions, especially when the FDIA displays profiles that deviate from known attack patterns. Current FDIA detection methods usually operate under the assumption of distributional consistency between training and testing data, thereby falling short in recognizing FDIA with such out-of-distribution (OOD) characteristics. To address this challenge, this paper proposes a novel logit-normalized Bayeisan ResNet (LNBRN) algorithm, a cutting-edge method to address the unexplored OOD FDIA issues efficiently. During offline training, the proposed LNBRN leverages dropout techniques to approximate Bayesian variational inference, thus reducing computational overhead. A key point is the introduction of logit normalization to the output layer, which significantly alleviate the model overconfidence and enhance the follow-up OOD detection performance. During online detection, LNBRN incorporates mutual information to quantify the epistemic uncertainty for incoming measurements, enabling accurate identification of high-risk OOD FDIA events. Comprehensive experimental evaluations on IEEE 14-bus and 118-bus test systems with real load data demonstrate the superiority of detecting OOD FDIA and validate the scalability in larger smart grids.

关键词： Uncertainty Vectors Training Bayes methods Neural networks Deep learning Current measurement Bayesian neural network false data injection attack out-of-distribution detection epistemic uncertainty uncertainty calibration

来源：评论

学校读者我要写书评

暂无评论

out-of-distribution detection with in-distribution voting using the medical example of chest x-ray classification

引用

MEDICAL PHYSICS 2024年第4期51卷 2721-2732页

作者： Wollek, Alessandro Willem, Theresa Ingrisch, Michael Sabel, Bastian Lasser, Tobias Tech Univ Munich Munich Inst Biomed Engn Munich Germany Tech Univ Munich Sch Computat Informat & Technol Munich Germany Tech Univ Munich Inst Hist & Eth Med Munich Germany Tech Univ Munich Munich Sch Technol Soc Munich Germany Ludwig Maximilians Univ Munchen Univ Hosp Dept Radiol Munich Germany Munich Inst Biomed Engn Boltzmannstr 11 D-85748 Garching Germany Sch Computat Informat & Technol Boltzmannstr 11 D-85748 Garching Germany

Background: Deep learning models are being applied to more and more use cases with astonishing success stories, but how do they perform in the real world? Models are typically tested on specific cleaned data sets, but when deployed in the real world, the model will encounter unexpected, out-of-distribution (OOD) ***: To investigate the impact of OOD radiographs on existing chest x-ray classification models and to increase their robustness against OOD ***: The study employed the commonly used chest x-ray classification model, CheXnet, trained on the chest x-ray 14 data set, and tested its robustness against OOD data using three public radiography data sets: IRMA, Bone Age, and MURA, and the ImageNet data set. To detect OOD data for multi-label classification, we proposed in-distribution voting (IDV). The OOD detection performance is measured across data sets using the area under the receiver operating characteristic curve (AUC) analysis and compared with Mahalanobis-based OOD detection, MaxLogit, MaxEnergy, self-supervised OOD detection (SS OOD), and ***: Without additional OOD detection, the chest x-ray classifier failed to discard any OOD images, with an AUC of 0.5. The proposed IDV approach trained on ID (chest x-ray 14) and OOD data (IRMA and ImageNet) achieved, on average, 0.999 OOD AUC across the three data sets, surpassing all other OOD detection methods. Mahalanobis-based OOD detection achieved an average OOD detection AUC of 0.982. IDV trained solely with a few thousand ImageNet images had an AUC 0.913, which was considerably higher than MaxLogit (0.726), MaxEnergy (0.724), SS OOD (0.476), and CutMix (0.376).Conclusions: The performance of all tested OOD detection methods did not translate well to radiography data sets, except Mahalanobis-based OOD detection and the proposed IDV method. Consequently, training solely on ID data led to incorrect classification of OOD images as ID, resulting in increased false positive rates. IDV su

关键词： anomaly detection chest x-ray classification out-of-distribution detection

来源：评论

学校读者我要写书评

暂无评论

out-of-distribution detection for SAR imagery using ATR systems 31

Out-of-distribution detection for SAR imagery using ATR syst...

引用

Conference on Algorithms for Synthetic Aperture Radar Imagery XXXI

作者： Hill, Charles Etegent Technol 2601 Mission Point Blvd STE 220 Beavercreek OH 45431 USA

ISBN: (纸本)9781510673830;9781510673823

A typical assumption for deploying machine learning models is that the model training and inference data were drawn from the same distribution. However, this assumption rarely holds true for systems deployed in the open world. Inference data can drift over time for numerous reasons, such as changes in operating conditions, adversarial modifications to targets, or sensor degradation. Despite these changes, deep learning models are especially vulnerable to issuing over-confident predictions on out-of-distribution data. This work seeks to address this issue by proposing a framework for describing out-of-distribution detection pipelines, proposing an out-of-distribution detection algorithm using Gaussian Mixture Models which is well suited for SAR ATR, and by evaluating multiple pipelines which exploit the intermediate states of ATR model deep neural networks. This work studies candidate pipelines with varied amounts of dimensionality reduction and detection algorithms on the SAMPLE+ dataset challenge problems for clutter and confuser rejection. Despite the exclusion of out-of-distribution samples from pipeline training, the presented results demonstrate that these samples can nonetheless be reliably detected, exceeding baseline performance by more than 10 percentage points.

关键词： out-of-distribution detection anomaly detection synthetic aperture radar model trust open set recognition artificial intelligence machine learning

来源：评论

学校读者我要写书评

暂无评论

out-of-distribution detection by Principal Component Correspondence

Out-of-Distribution Detection by Principal Component Corresp...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Guan, Xiaoyuan Gan, Zhiyong Deng, Ling Shi, Wei Chen, Jiankang Bu, Shenshen Zhao, Chunliang Hui, Jianfang Zhou, Yuren Zheng, Wei-Shi Wang, Ruixuan Sun Yat Sen Univ Sch Comp Sci & Engn Guangzhou Peoples R China China Unicom Network Business Grp Guangzhou Peoples R China Pengcheng Lab Dept Network Intelligence Shenzhen Peoples R China MOE Key Lab Machine Intelligence & Adv Comp Guangzhou Peoples R China Qingdao Univ Sci & Technol Sch Data & Sci Qingdao Peoples R China Sun Yat Sen Univ Sch Software Engn Zhuhai Peoples R China

ISBN: (纸本)9798350390155;9798350390162

out-of-distribution (OOD) detection is vital for the safe application of intelligent systems in real-world scenarios. This paper proposes an enhancement to OOD detection by leveraging the consistency in cognition between two models, both pretrained on in-distribution (ID) data. Specifically, for a given test sample, we first apply Principal Component Analysis (PCA)-based projection on the feature vectors from each model. These obtained feature vectors (with correlation between dimensions decoupled by PCA projection) are then aligned using a multiple linear mapping, which is fitted using the least squares method on the training data. We hypothesize that the regression error for OOD data will be larger than that for ID data, making it a useful metric for OOD detection. Our experimental results demonstrate the effectiveness of this method. When combined with existing robust baselines, our approach achieves state-of-the-art performance in OOD detection.

关键词： Principal Component Correspondence Feature Vector Alignment out-of-distribution detection

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：