检索结果-内蒙古大学图书馆

Predicting the Settlement of Shallow Foundation Using Metaheuristic SVR Approaches

GEOTECHNICAL AND GEOLOGICAL ENGINEERING 2023年第8期41卷 4795-4805页

作者： Wan, Xiaoqi Nanchang Inst Technol Sch Architectural Engn Nanchang 330044 Jiangxi Peoples R China

Because cohesive soil structure is so complicated, settlement modelling is, in some ways, essential. The goal of this study is to identify settlement (S-m) of shallow foundations using newly developed machine learning methods, such as hybridized support vector regression ( SVR) with sine-cosine algorithm ( SCA) and Bat-inspired algorithm ( BAT). Footing width, pressure, geometry, number of standard penetration tests, and footing embedment ratio are among the estimated variables. The application of optimization methods served the objective of identifying the optimal value for the primary variables of the researched model. The SCA-SVR is thought to be the best framework with the highest classification when compared to BAT-SVR and ANFIS-PSO. During the process of learning, the values of R-2 and MAE are 0.9629 and 1.5354, which is preferable to ANFIS-PSO by 0.9025 and 4.92, and 0.9823 and 1.3787 in the evaluating portion, which is superior to ANFIS-PSO at 0.739 and 9.88. By looking at PI indicator, the SCA-SVR network does better than the BAT-SVR in both the education and evaluating datasets. The SCA-SVR model dropped 0.0262 and 0.0435 points in the education and evaluating data sets, respectively. Likewise, the A(10-index) index exhibits a similar tendency. In conclusion, after analyzing the accuracy and taking into account the definitions, it is completely obvious that the SVR combined with SCA can work better than BAT, as well as by literature, that could be referred to as the proposed system in the forecasting model of S-m.

关键词： Shallow foundation Settlement Simulation Hybridized and algorithms

来源：评论

学校读者我要写书评

暂无评论

SimA: Simple Softmax-free Attention for Vision Transformers

SimA: Simple Softmax-free Attention for Vision Transformers

引用

IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

作者： Koohpayegani, Soroush Abbasi Pirsiavash, Hamed Univ Calif Davis Davis CA 95616 USA

ISBN: (纸本)9798350318920;9798350318937

Recently, vision transformers have become very popular. However, deploying them in many applications is computationally expensive partly due to the Softmax layer in the attention block. We introduce a simple yet effective, Softmax-free attention block, SimA, which normalizes query and key matrices with simple l(1)-norm instead of using Softmax layer. Then, the attention block in SimA is a simple multiplication of three matrices, so SimA can dynamically change the ordering of the computation at the test time to achieve linear computation on the number of tokens or the number of channels. We empirically show that SimA applied to three SOTA variations of transformers, DeiT, XCiT, and CvT, results in on-par accuracy compared to the SOTA models, without any need for Softmax layer. Interestingly, changing SimA from multi-head to single-head has only a small effect on the accuracy, which further simplifies the attention block. Moreover, we show that SimA is much faster on small edge devices, e.g., Raspberry Pi, which we believe is due to higher complexity of Softmax layer on those devices. The code is available here: https://***/UCDvision/sima

关键词： algorithms algorithms and algorithms formulations Image recognition and understanding Machine learning architectures

来源：评论

学校读者我要写书评

暂无评论

Active Batch Sampling for Multi-label Classification with Binary User Feedback

Active Batch Sampling for Multi-label Classification with Bi...

引用

IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

作者： Goswami, Debanjan Chakraborty, Shayok Florida State Univ Dept Comp Sci Tallahassee FL 32306 USA

ISBN: (纸本)9798350318920;9798350318937

Multi-label classification is a generalization of multi-class classification, where a single data sample can have multiple labels. While deep neural networks have depicted commendable performance for multi-label learning, they require a large amount of manually annotated training data to attain good generalization capability. However, annotating a multi-label data sample requires a human oracle to consider the presence/absence of every single class individually, which is extremely laborious. Active learning algorithms automatically identify the salient and exemplar instances from large amounts of unlabeled data and are effective in reducing human annotation effort in inducing a machine learning model. In this paper, we propose a novel active learning framework for multi-label learning, which queries a batch of (image-label) pairs and for each pair, poses the question whether the queried label is present in the corresponding image;the human annotators merely need to provide a binary feedback ("yes/no") in response to each query, which involves much less manual work. We pose the image and label selection as a constrained optimization problem and derive a linear programming relaxation to select a batch of (image-label) pairs, which are maximally informative to the underlying deep neural network. Our extensive empirical studies on three challenging datasets corroborate the potential of our method for real-world multi-label classification applications.

关键词： algorithms algorithms and algorithms formulations Image recognition and understanding Machine learning architectures

来源：评论

学校读者我要写书评

暂无评论

Face Presentation Attack Detection by Excavating Causal Clues and Adapting Embedding Statistics

Face Presentation Attack Detection by Excavating Causal Clue...

引用

IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

作者： Fang, Meiling Damer, Naser Fraunhofer Inst Comp Graph Res IGD Darmstadt Germany Tech Univ Darmstadt Dept Comp Sci Darmstadt Germany

ISBN: (纸本)9798350318920;9798350318937

Recent face presentation attack detection (PAD) leverages domain adaptation (DA) and domain generalization (DG) techniques to address performance degradation on unknown domains. However, DA-based PAD methods require access to unlabeled target data, while most DG-based PAD solutions rely on a priori, i.e., known domain labels. Moreover, most DA-/DG-based methods are computationally intensive, demanding complex model architectures and/or multi-stage training processes. This paper proposes to model face PAD as a compound DG task from a causal perspective, linking it to model optimization. We excavate the causal factors hidden in the high-level representation via counterfactual intervention. Moreover, we introduce a class-guided MixStyle to enrich feature-level data distribution within classes instead of focusing on domain information. Both class-guided MixStyle and counterfactual intervention components introduce no extra trainable parameters and negligible computational resources. Extensive cross-dataset and analytic experiments demonstrate the effectiveness and efficiency of our method compared to state-of-the-art PADs. The implementation and the trained weights are publicly available(1).

关键词： algorithms algorithms and algorithms Biometrics body pose face formulations gesture Machine learning architectures

来源：评论

学校读者我要写书评

暂无评论

An Analysis of Initial Training Strategies for Exemplar-Free Class-Incremental Learning

An Analysis of Initial Training Strategies for Exemplar-Free...

引用

IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

作者： Petit, Gregoire Soumm, Michael Feillet, Eva Popescu, Adrian Delezoide, Bertrand Picard, David Hudelot, Celine Univ Paris Saclay LIST CEA F-91120 Palaiseau France Univ Gustave Eiffel LIGM CNRS Ecole Ponts Marne La Vallee France Amanda 34 Ave Champs Elysees F-75008 Paris France Univ Paris Saclay MICS Cent Supelec Paris France

ISBN: (纸本)9798350318920;9798350318937

Class-Incremental Learning (CIL) aims to build classification models from data streams. At each step of the CIL process, new classes must be integrated into the model. Due to catastrophic forgetting, CIL is particularly challenging when examples from past classes cannot be stored, the case on which we focus here. To date, most approaches are based exclusively on the target dataset of the CIL process. However, the use of models pre-trained in a self-supervised way on large amounts of data has recently gained momentum. The initial model of the CIL process may only use the first batch of the target dataset, or also use pre-trained weights obtained on an auxiliary dataset. The choice between these two initial learning strategies can significantly influence the performance of the incremental learning model, but has not yet been studied in depth. Performance is also influenced by the choice of the CIL algorithm, the neural architecture, the nature of the target task, the distribution of classes in the stream and the number of examples available for learning. We conduct a comprehensive experimental study to assess the roles of these factors. We present a statistical analysis framework that quantifies the relative contribution of each factor to incremental performance. Our main finding is that the initial training strategy is the dominant factor influencing the average incremental accuracy, but that the choice of CIL algorithm is more important in preventing forgetting. Based on this analysis, we propose practical recommendations for choosing the right initial training strategy for a given incremental learning use case. These recommendations are intended to facilitate the practical deployment of incremental learning.

关键词： algorithms algorithms and algorithms Applications Embedded sensing / real-time techniques formulations Machine learning architectures Vision + language and/or other modalities

来源：评论

学校读者我要写书评

暂无评论

Evidential Uncertainty Quantification: A Variance-Based Perspective

Evidential Uncertainty Quantification: A Variance-Based Pers...

引用

IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

作者： Duan, Ruxiao Caffo, Brian Bai, Harrison X. Sair, Haris I. Jones, Craig Johns Hopkins Univ Baltimore MD 21218 USA Johns Hopkins Univ Sch Med Baltimore MD USA

ISBN: (纸本)9798350318920;9798350318937

Uncertainty quantification of deep neural networks has become an active field of research and plays a crucial role in various downstream tasks such as active learning. Recent advances in evidential deep learning shed light on the direct quantification of aleatoric and epistemic uncertainties with a single forward pass of the model. Most traditional approaches adopt an entropy-based method to derive evidential uncertainty in classification, quantifying uncertainty at the sample level. However, the variance-based method that has been widely applied in regression problems is seldom used in the classification setting. In this work, we adapt the variance-based approach from regression to classification, quantifying classification uncertainty at the class level. The variance decomposition technique in regression is extended to class covariance decomposition in classification based on the law of total covariance, and the class correlation is also derived from the covariance. Experiments on cross-domain datasets are conducted to illustrate that the variance-based approach not only results in similar accuracy as the entropy-based one in active domain adaptation but also brings information about class-wise uncertainties as well as between-class correlations. The code is available at https://***/KerryDRX/EvidentialADA. This alternative means of evidential uncertainty quantification will give researchers more options when class uncertainties and correlations are important in their applications.

关键词： algorithms algorithms and algorithms formulations Image recognition and understanding Machine learning architectures

来源：评论

学校读者我要写书评

暂无评论

ICF-SRSR: Invertible scale-Conditional Function for Self-Supervised Real-world Single Image Super-Resolution

ICF-SRSR: Invertible scale-Conditional Function for Self-Sup...

引用

IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

作者： Neshatavar, Reyhaneh Yavartanoo, Mohsen Sony, Sanghyun Lee, Kyoung Mu Seoul Natl Univ Dept ECE & ASRI Seoul South Korea Seoul Natl Univ IPAI Seoul South Korea

ISBN: (纸本)9798350318920;9798350318937

Single image super-resolution (SISR) is a challenging ill-posed problem that aims to up-sample a given low-resolution (LR) image to a high-resolution (HR) counterpart. Due to the difficulty in obtaining real LR-HR training pairs, recent approaches are trained on simulated LR images degraded by simplified down-sampling operators, e.g., bicubic. Such an approach can be problematic in practice due to the large gap between the synthesized and real-world LR images. To alleviate the issue, we propose a novel Invertible scale-Conditional Function (ICF), which can scale an input image and then restore the original input with different scale conditions. Using the proposed ICF, we construct a novel self-supervised SISR framework (ICF-SRSR) to handle the real-world SR task without using any paired/unpaired training data. Furthermore, our ICF-SRSR can generate realistic and feasible LR-HR pairs, which can make existing supervised SISR networks more robust. Extensive experiments demonstrate the effectiveness of our method in handling SISR in a fully self-supervised manner. Our ICF-SRSR demonstrates superior performance compared to the existing methods trained on synthetic paired images in real-world scenarios and exhibits comparable performance compared to state-of-the-art supervised/unsupervised methods on public benchmark datasets. The code is available from this link.

关键词： algorithms algorithms and algorithms formulations Low-level and physics-based vision Machine learning architectures

来源：评论

学校读者我要写书评

暂无评论

Contextual Affinity Distillation for Image Anomaly Detection

Contextual Affinity Distillation for Image Anomaly Detection

引用

IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

作者： Zhang, Jie Suganuma, Masanori Okatani, Takayuki Tohoku Univ Grad Sch Informat Sci Sendai Miyagi Japan RIKEN Ctr AIP Tokyo Japan

ISBN: (纸本)9798350318920;9798350318937

Previous studies on unsupervised industrial anomaly detection mainly focus on 'structural' types of anomalies such as cracks and color contamination by matching or learning local feature representations. While achieving significantly high detection performance on this kind of anomaly, they are faced with 'logical' types of anomalies that violate the long-range dependencies such as a normal object placed in the wrong position. Noting the reverse distillation approaches that are under the encoder-decoder paradigm could learn from the high abstract level knowledge, we propose to use two students (local and global) to better mimic the teacher's local and global behavior in reverse distillation. The local student, which is used in previous studies mainly focuses on accurate local feature learning while the global student pays attention to learning global correlations. To further encourage the global student's learning to capture long-range dependencies, we design the global context condensing block (GCCB) and propose a contextual affinity loss for the student training and anomaly scoring. Experimental results show that the proposed method sets a new state-of-the-art performance on the MVTec LOCO AD dataset without using complex training techniques.

关键词： algorithms algorithms and algorithms formulations Image recognition and understanding Machine learning architectures

来源：评论

学校读者我要写书评

暂无评论

C-CLIP: Contrastive Image-Text Encoders to Close the Descriptive-Commentative Gap

C-CLIP: Contrastive Image-Text Encoders to Close the Descrip...

引用

IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

作者： Theisen, William Scheirer, Walter Univ Notre Dame Notre Dame IN 46556 USA

ISBN: (纸本)9798350318920;9798350318937

The interplay between the image and comment on a social media post is one of high importance for understanding its overall message. Recent strides in multimodal embedding models, namely CLIP, have provided an avenue forward in relating image and text. However the current training regime for CLIP models is insufficient for matching content found on social media, regardless of site or language. Current CLIP training data is based on what we call "descriptive" text: text in which an image is merely described. This is something rarely seen on social media, where the vast majority of text content is "commentative" in nature. The captions provide commentary and broader context related to the image, rather than describing what is in it. Current CLIP models perform poorly on retrieval tasks where image-caption pairs display a commentative relationship. Closing this gap would be beneficial for several important application areas related to social media. For instance, it would allow groups focused on Open-Source Intelligence Operations (OSINT) to further aid efforts during disaster events, such as the ongoing Russian invasion of Ukraine, by easily exposing data to non-technical users for discovery and analysis. In order to close this gap we demonstrate that training contrastive image-text encoders on explicitly commentative pairs results in large improvements in retrieval results, with the results extending across a variety of non-English languages.

关键词： algorithms and algorithms Applications Arts / games / social media formulations Machine learning architectures

来源：评论

学校读者我要写书评

暂无评论

ARNIQA: Learning Distortion Manifold for Image Quality Assessment

ARNIQA: Learning Distortion Manifold for Image Quality Asses...

引用

IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

作者： Agnolucci, Lorenzo Galteri, Leonardo Bertini, Marco Del Bimbo, Alberto Univ Florence Media Integrat & Commun Ctr MICC Florence Italy

ISBN: (纸本)9798350318920;9798350318937

No-Reference Image Quality Assessment (NR-IQA) aims to develop methods to measure image quality in alignment with human perception without the need for a high-quality reference image. In this work, we propose a self-supervised approach named ARNIQA (leArning distoRtion maNifold for Image Quality Assessment) for modeling the image distortion manifold to obtain quality representations in an intrinsic manner. First, we introduce an image degradation model that randomly composes ordered sequences of consecutively applied distortions. In this way, we can synthetically degrade images with a large variety of degradation patterns. Second, we propose to train our model by maximizing the similarity between the representations of patches of different images distorted equally, despite varying content. Therefore, images degraded in the same manner correspond to neighboring positions within the distortion manifold. Finally, we map the image representations to the quality scores with a simple linear regressor, thus without fine-tuning the encoder weights. The experiments show that our approach achieves state-of-the-art performance on several datasets. In addition, ARNIQA demonstrates improved data efficiency, generalization capabilities, and robustness compared to competing methods. The code and the model are publicly available at https://***/miccunifi/ARNIQA.

关键词： algorithms algorithms and algorithms formulations Low-level and physics-based vision Machine learning architectures

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：