检索结果-内蒙古大学图书馆

2024 International Conference on Electronics, Information, and Communication, ICEIC 2024

作者： Wu, Yihong Heng, Yuwen Niranjan, Mahesan Kim, Hansung School of Electronics and Computer Science University of Southampton Vision Learning and Control Research Group Southampton United Kingdom

ISBN: (纸本)9798350371888

In this research, we tackle the task of estimating depth from a single indoor omnidirectional image. Acknowledging gravity's critical influence in artificially constructed indoor environments, we process the input from equirectangular projection by dividing it into vertical slices. These slices are then utilized as patch embeddings for the transformer encoder, a strategy designed to recreate an equirectangular depth map. Our architecture is evaluated against leading models using real-world datasets, namely Stanford2D3D and Matterport3D, demonstrating its superior performance. These results underscore the significance of our gravity-aligned approach for depth estimation in omnidirectional images, especially in man-made settings. © 2024 IEEE.

关键词： Gravitation

来源：评论

学校读者我要写书评

暂无评论

Depth Estimation for a Single Omnidirectional Image with Reversed-Gradient Warming-up Thresholds Discriminator 48

Depth Estimation for a Single Omnidirectional Image with Rev...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Wu, Yihong Heng, Yuwen Niranjan, Mahesan Kim, Hansung University of Southampton Vision Learning and Control Research Group School of Electronics and Computer Science United Kingdom

ISBN: (纸本)9781728163277

Depth estimation for single image using deep learning requires a large labelled depth dataset with various scenes for training. However, currently published omnidirectional depth datasets cover limited types of scenes and are not suitable for depth estimation for various real-world scenes. With the challenge of labelled real-world datasets generation and stability of the performance, we propose an architecture with the Reverse-gradient Warming-up Threshold Discriminator (RWTD) to estimate real-world depth maps from the synthetic ground truth. It takes labelled synthetic scenes of a source domain and unlabelled real-world scenes of a target domain as inputs to predict the corresponding depth maps. Compared with state-of-the-art encoder-decoder models, the proposed architecture shows an 11% points improvement on the testing dataset for depth accuracy. © 2023 IEEE.

关键词： Depth estimation domain adaptation

来源：评论

学校读者我要写书评

暂无评论

On the Implementation of Baselines and Lightweight Conditional Model Extrapolation (LIMES) Under Class-Prior Shift 4th

On the Implementation of Baselines and Lightweight Condit...

引用

Fourth International Workshop on Reproducible Research in Pattern Recognition, RRPR 2022

作者： Tomaszewska, Paulina Lampert, Christoph H. Warsaw University of Technology Faculty of Mathematics and Information Science Warsaw Poland Machine Learning and Computer Vision Group Klosterneuburg Austria

ISBN: (纸本)9783031407727

This paper focuses on the implementation details of the baseline methods and a recent lightweight conditional model extrapolation algorithm LIMES [5] for streaming data under class-prior shift. LIMES achieves superior performance over the baseline methods, especially concerning the minimum-across-day accuracy, which is important for the users of the system. In this work, the key measures to facilitate reproducibility and enhance the credibility of the results are described. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Lime

来源：评论

学校读者我要写书评

暂无评论

Generative Curricula for Multi-Agent Path Finding via Unsupervised and Reinforcement learning

引用

Journal of Artificial Intelligence Research 2025年 82卷 2471-2534页

作者： Phan, Thomy Phan, Timy Koenig, Sven University of Southern California Thomas Lord Department of Computer Science Los AngelesCA90089 United States LMU Munich Computer Vision & Learning Group School of Arts Munich80799 Germany University of California Irvine Department of Computer Science IrvineCA92697 United States

Multi-Agent Path Finding (MAPF) is the challenging problem of finding collision-free paths for multiple agents, which has a wide range of applications, such as automated warehouses, smart manufacturing, and traffic management. Recently, machine learning-based approaches have become popular in addressing MAPF problems in a decentralized and potentially generalizing way. Most learning-based MAPF approaches use reinforcement and imitation learning to train agent policies for decentralized execution under partial observability. However, current state-of-the-art approaches suffer from a prevalent bias to micro-aspects of particular MAPF problems, such as congestions in corridors and potential delays caused by single agents, leading to tight specializations through extensive engineering via oversized models, reward shaping, path finding algorithms, and communication. These specializations are generally detrimental to the sample efficiency, i.e., the learning progress given a certain amount of experience, and generalization to previously unseen scenarios. In contrast, curriculum learning offers an elegant and much simpler way of training agent policies in a step-by-step manner to master all aspects implicitly without extensive engineering. In this paper, we propose a generative curriculum approach to learning-based MAPF using Variational Autoencoder Utilized learning of Terrains (VAULT). We introduce a two-stage framework to (I) train the VAULT via unsupervised learning to obtain a latent space representation of maps and (II) use the VAULT to generate curricula in order to improve sample efficiency and generalization of learning-based MAPF methods. For the second stage, we propose a bi-level curriculum scheme by combining our VAULT curriculum with a low-level curriculum method to improve sample efficiency further. Our framework is designed in a modular and general way, where each proposed component serves its purpose in a black-box manner without considering specific micro

关键词： Curricula

来源：评论

学校读者我要写书评

暂无评论

A Semiautomatic Image Processing-Based Method for Binary Segmentation of Lungs in Computed Tomography Images

引用

SN computer Science 2024年第6期5卷 689页

作者： Ramos, Leo Pineda, Israel School of Mathematical and Computational Sciences Yachay Tech University Deep Learning for Autonomous Driving Robotics and Computer Vision (DeepARC) Research Group Yachay Tech University Kauel Inc. Computer Vision Center Universitat Autònoma de Barcelona College of Sciences and Engineering Universidad San Francisco de Quito

Precise biomedical image segmentation is pivotal in medical diagnosis and treatment. Among various methodologies, image processing-based techniques are useful due to their swift and consistent results, free from the dependency on extensive training data required by deep learning approaches. This study introduces a tri-phase, semi-automated pipeline for lung computed tomography image segmentation, beginning with a preprocessing phase that includes contrast enhancement, noise reduction, and edge detection to improve image quality. This is followed by the application of the region growing method for segmentation and is completed with morphological closing to refine the final output. Comparative tests reveal that our technique surpasses prevalent methods like split and merge, Otsu’s technique, and basic region growing in terms of the dice coefficient (DC) and intersection over union (IoU). Specifically, our approach achieved an average DC of 0.9633, contrasting with 0.4668, 0.005, and 0.4067 recorded by Otsu’s, split and merge, and basic region growing techniques respectively. Similarly, the average IoU for our method was 0.9341, in comparison to 0.3105, 0.0660, and 0.2605 for the aforementioned methods. Additionally, comparative analysis with contemporary segmentation models demonstrates that our approach is competitive, even without relying on large training datasets. These results highlight our method’s efficiency and practicality, distinguishing it as a compelling option in medical scenarios where access to extensive training data is limited. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Image analysis Image processing Image segmentation Medical image Pattern recognition Region growing

来源：评论

学校读者我要写书评

暂无评论

Enhancing Material Features Using Dynamic Backward Attention on Cross-Resolution Patches 33

Enhancing Material Features Using Dynamic Backward Attention...

引用

33rd British Machine vision Conference Proceedings, BMVC 2022

作者： Heng, Yuwen Wu, Yihong Dasmahapatra, Srinandan Kim, Hansung Vision Learning and Control Research Group School of Electronics and Computer Science University of Southampton Southampton United Kingdom

Recent studies in material segmentation crop the image into patches to force the network to learn material features from local visual clues. This design is based on the expectation that the contextually invariant features can generalise the network to unseen images regardless of the object or scene in which the material appears. However, most approaches set a fixed patch resolution for all the images in a dataset, which does not consider the varying areas that materials cover within and across images due to the scene scale. As a consequence, the fixed patch resolution can limit the performance of networks. In consideration of this problem, this paper proposes a Dynamic Backward Attention Transformer (DBAT) to extract features from cross-resolution patches and dynamically aggregate these features based on per-pixel attention masks. Experiments show that DBAT achieves the best performance among state-of-the-art models (86.85% in average pixel accuracy, which is 2.15% higher than the second-best model) that can serve real-time inference. Moreover, we also illustrate the network behaviour through visualisation methods as well as descriptive statistics. The project code is available at https://***/heng-yuwen/Dynamic-Backward-Attention-Transformer. © 2022. The copyright of this document resides with its authors.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Deep learning Approach for High Recall Pneumonia Classification with Swin Transformer and L2 Regularization 23

Deep Learning Approach for High Recall Pneumonia Classificat...

引用

8th International Conference on Sustainable Information Engineering and Technology, SIET 2023

作者： Pinasthika, Krisna Sofyanda, Erika Yussi Ulumiyah, Silfiatul Muflikhah, Lailil Computer Vision Research Group Brawijaya University Indonesia Technology Education Learning Research Group Brawijaya University Indonesia Information System Research Group Brawijaya University Indonesia Department of Informatics Engineering Brawijaya University Indonesia

ISBN: (纸本)9798400708503

Pneumonia is one of the lung infections that can be lethal to people. Pneumonia can be diagnosed by conducting an X-ray scan of the human chest. Even though X-ray scanning is straightforward, the process of identifying pneumonia in X-ray data is still difficult to do even by radiologists. Therefore, a computational algorithm is needed that can be used to analyze X-ray image data. The use of Deep learning (DL) methods for analyzing images has been proven to work well in various cases, especially X-ray data. Based on previous research, the transformer architecture has the advantage of analyzing with a larger receptive area if compared to Convolutional Neural Networks (CNN) which have limited kernel size. In this study, we used the Swin transformer in classifying pneumonia diseases through X-ray images. Through the study conducted, the Swin Transformer Architecture is able to provide a fairly good evaluation metric when compared to the use of convolutional neural networks. The Tiny variant of the Swin Transformer architecture is able to provide evaluation metrics with a precision value of 0.870, recall of 0.995, and F1-Score of 0.928. On the other hand, the use of L2 regularization in stage 3 and stage 4 of the Swin Tiny architecture is able to provide a high recall value of 0.997, but the use of L2 regularization does not provide an increase in precision and F1-Score. In biomedical cases that are only concerned with recall values, the use of L2 regularization on Swin Tiny can provide advantages. © 2023 ACM.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Robust Autonomous Vehicle Pursuit Without Expert Steering Labels

引用

IEEE Robotics and Automation Letters 2023年第10期8卷 6595-6602页

作者： Pan, Jiaxin Zhou, Changyao Gladkova, Mariia Khan, Qadeer Cremers, Daniel Technical University of Munich Computer Vision Group Garching85748 Germany Munich Data Science Institute Garching85748 Germany Munich Center for Machine Learning Munchen80333 Germany University of Oxford OxfordOX1 3AZ United Kingdom

In this work, we present a learning method for both lateral and longitudinal motion control of an ego-vehicle for the task of vehicle pursuit. The car being controlled does not have a pre-defined route, rather it reactively adapts to follow a target vehicle while maintaining a safety distance. To train our model, we do not rely on steering labels recorded from an expert driver, but effectively leverage a classical controller as an offline label generation tool. In addition, we account for the errors in the predicted control values, which can lead to a loss of tracking and catastrophic crashes of the controlled vehicle. To this end, we propose an effective data augmentation approach, which allows to train a network that is capable of handling different views of the target vehicle. During the pursuit, the target vehicle is firstly localized using a Convolutional Neural Network. The network takes a single RGB image along with cars' velocities and estimates target vehicle's pose with respect to the ego-vehicle. This information is then fed to a Multi-Layer Perceptron, which regresses the control commands for the ego-vehicle, namely throttle and steering angle. We extensively validate our approach using the CARLA simulator on a wide range of terrains. Our method demonstrates real-time performance, robustness to different scenarios including unseen trajectories and high route completion. © 2016 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

SliceFormer: Deep Dense Depth Estimation from a Single Indoor Omnidirectional Image Using a Slice-Based Transformer

SliceFormer: Deep Dense Depth Estimation from a Single Indoo...

引用

International Conference on Electronics, Information and Communications (ICEIC)

作者： Yihong Wu Yuwen Heng Mahesan Niranjan Hansung Kim Vision Learning and Control Research Group School of Electronics and Computer Science University of Southampton Southampton United Kingdom

关键词：

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Dissipativity Analysis: Application of the Matrix S-Lemma

引用

IEEE Control Systems 2022年第3期42卷 140-149页

作者： Van Waarde, Henk J. Camlibel, M. Kanat Rapisarda, Paolo Trentelman, Harry L. Bernoulli Institute for Mathematics Computer Science and Artificial Intelligence University of Groningen Groningen9747 AG Netherlands Vision Learning and Control Group of the University of Southampton SouthamptonSO17 1BJ United Kingdom

The concept of dissipativity, as introduced by Jan Willems, is one of the cornerstones of systems and control theory. Typically, dissipativity properties are verified by resorting to a mathematical model of the system under consideration. This article aims to assess dissipativity using computing storage functions for linear systems directly from measured data. As our main contributions, we provide conditions under which dissipativity can be ascertained from a finite collection of noisy data samples. Three different noise models are considered that can capture a variety of situations, including the cases where the data samples are noise-free, the energy of the noise is bounded, or the individual noise samples are bounded. All conditions are phrased in terms of data-based linear matrix inequalities, which can be readily solved using existing software packages. © 1991-2012 IEEE.

关键词： Linear matrix inequalities

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：