检索结果-内蒙古大学图书馆

Proceedings of the Digital Image Computing: Technqiues and applications (DICTA)

作者： Muhammad Abdullah Hafeez Adnan Ul-Hasan Faisal Shafait School of Electrical Engineering and Computer Science (SEECS) National University of Sciences and Technology (NUST) Islamabad Pakistan Deep Learning Laboratory National Center of Artificial Intelligence (NCAI) Islamabad Pakistan

State of the art deep learning models, despite being at par to the human level in some of the challenging tasks, still suffer badly when they are put in the condition where they have to learn with time. This open challenge problem of making deep learning model learn with time is referred in the literature as Lifelong learning, Incremental learning or Continual learning. In each increment, new classes/tasks are introduced to the existing model and trained on them while maintaining the accuracy of the previously learned classes/tasks. But accuracy of the deep learning model on the previously learned classes/tasks decreases with each increment. The main reason behind this accuracy drop is catastrophic forgetting, an inherent flaw in the deep learning models, where weights learned during the past increments, get disturbed while learning the new classes/tasks from new increment. Several approaches have been proposed to mitigate or avoid this catastrophic forgetting, such as the use of knowledge distillation, rehearsal over previous classes, or dedicated paths for different increments, etc. In this work, we have proposed a novel approach based on transfer learning methodology, which uses a combination of pre-trained shared and fixed network as a backbone, along with a dedicated network extension in incremental setting for the learning of new tasks incrementally. The results have shown that our approach has better performance in two ways. First, our model has significantly better overall incremental accuracy than that of the best in class model in different incremental configurations. Second, our approach achieves better results while maintaining properties of true incremental learning algorithm i.e. successful avoidance of the catastrophic forgetting issue and complete eradication of the need of saved exemplars or retraining phases, which are required by the current state of the art model to maintain performance.

关键词： deep learning Training Knowledge engineering Philosophical considerations Digital images Transfer learning Training data

来源：评论

学校读者我要写书评

暂无评论

Enhancing Multimodal Information Extraction from Visually Rich Documents with 2D Positional Embeddings

Enhancing Multimodal Information Extraction from Visually Ri...

引用

Proceedings of the Digital Image Computing: Technqiues and applications (DICTA)

作者： Aresha Arshad Momina Moetesum Adnan Ul Hasan Faisal Shafait School of Electrical Engineering and Computer Science (SEECS) National University of Sciences and Technology (NUST) Islamabad Pakistan Deep Learning Laboratory National Center of Artificial Intelligence (NCAI) Islamabad Pakistan

ISBN: (数字)9798350379037

ISBN: (纸本)9798350379044

Visually rich document understanding involves the interpretation of documents with varied formats and complex layouts, including multi-line entities, presenting a significant challenge. This study addresses these challenges by introducing a document comprehension model based on the LayoutLMv3 architecture, incorporating two-dimensional (2D) positional embeddings to capture both row and column information. Additionally, a multi-stage Transformer network is employed for hierarchical processing of document features. The proposed model is evaluated through extensive experiments on FUNSD dataset, achieving improved performance in both text-centric and image-centric document understanding tasks. Results demonstrate enhanced spatial comprehension and computational efficiency as compared to the state-of-the-art, establishing our approach as a significant contribution to the field of visually rich document understanding.

关键词： Computational modeling Two-dimensional displays Digital images Layout Computer architecture Transformers Information retrieval Encoding Computational efficiency Usability

来源：评论

学校读者我要写书评

暂无评论

Multi-Modal Face Presentation Attack Detection 1

引用

丛书名： Synthesis Lectures on Computer Vision

1000年

作者： Jun Wan Guodong Guo Sergio Escalera Hugo Jair Escalante Stan Z. Li

来源：评论

学校读者我要写书评

暂无评论

Generalizing from a few examples: A survey on few-shot learning

arXiv

引用

arXiv 2019年

作者： WANG, YAQING YAO, QUANMING KWOK, JAMES T. NI, LIONEL M. Department of Computer Science and Engineering Hong Kong University of Science and Technology Business Intelligence Lab National Engineering Laboratory of Deep Learning Technology and Application Baidu Research 4Paradigm Inc.

Machine learning has been highly successful in data-intensive applications, but is often hampered when the data set is small. Recently, Few-Shot learning (FSL) is proposed to tackle this problem. Using prior knowledge, FSL can rapidly generalize to new tasks containing only a few samples with supervised information. In this paper, we conduct a thorough survey to fully understand FSL. Starting from a formal definition of FSL, we distinguish FSL from several relevant machine learning problems. We then point out that the core issue in FSL is that the empirical risk minimizer is unreliable. Based on how prior knowledge can be used to handle this core issue, we categorize FSL methods from three perspectives: (i) data, which uses prior knowledge to augment the supervised experience;(ii) model, which uses prior knowledge to reduce the size of the hypothesis space;and (iii) algorithm, which uses prior knowledge to alter the search for the best hypothesis in the given hypothesis space. With this taxonomy, we review and discuss the pros and cons of each category. Promising directions, in the aspects of the FSL problem setups, techniques, applications and theories, are also proposed to provide insights for future research. Copyright © 2019, The Authors. All rights reserved.

关键词： Surveys

来源：评论

学校读者我要写书评

暂无评论

RBCN: Rectified Binary convolutional networks for enhancing the Performance of 1-bit DCNNs

arXiv

引用

arXiv 2019年

作者： Liu, Chunlei Ding, Wenrui Xia, Xin Hu, Yuan Zhang, Baochang Liu, Jianzhuang Zhuang, Bohan Guo, Guodong School of Electronic and Information Engineering Beihang University Unmanned System Research Institute Beihang University School of Automation Science and Electrical Engineering Beihang University Huawei Noah's Ark Lab University of Adelaide Institute of Deep Learning Baidu Research National Engineering Laboratory for Deep Learning Technology and Application

Binarized convolutional neural networks (BCNNs) are widely used to improve memory and computation efficiency of deep convolutional neural networks (DCNNs) for mobile and AI chips based applications. However, current BCNNs are not able to fully explore their corresponding full-precision models, causing a significant performance gap between them. In this paper, we propose rectified binary convolutional networks (RBCNs), towards optimized BCNNs, by combining full-precision kernels and feature maps to rectify the binarization process in a unified framework. In particular, we use a GAN to train the 1-bit binary network with the guidance of its corresponding full-precision model, which significantly improves the performance of BCNNs. The rectified convolutional layers are generic and flexible, and can be easily incorporated into existing DCNNs such as WideResNets and ResNets. Extensive experiments demonstrate the superior performance of the proposed RBCNs over state-of-the-art BCNNs. In particular, our method shows strong generalization on the object tracking task. Copyright © 2019, The Authors. All rights reserved.

关键词： deep neural networks

来源：评论

学校读者我要写书评

暂无评论

iffDetector: Inference-aware feature filtering for object detection

arXiv

引用

arXiv 2020年

作者： Mao, Mingyuan Tian, Yuxin Zhang, Baochang Ye, Qixiang Liu, Wanquan Guo, Guodong Doermann, David Beihang University Beijing China University of Chinese Academy of Sciences Beijing China Curtin University Perth Australia Institute of Deep Learning Baidu Research Beijing China National Engineering Laboratory for Deep Learning Technology and Application University at Buffalo Buffalo United States

Modern CNN-based object detectors focus on feature configuration during training but often ignore feature optimization during inference. In this paper, we propose a new feature optimization approach to enhance features and suppress background noise in both the training and inference stages. We introduce a generic Inference-aware Feature Filtering (IFF) module that can easily be combined with modern detectors, resulting in our iffDetector. Unlike conventional open-loop feature calculation approaches without feedback, the IFF module performs closed-loop optimization by leveraging high-level semantics to enhance the convolutional features. By applying Fourier transform analysis, we demonstrate that the IFF module acts as a negative feedback that theoretically guarantees the stability of feature learning. IFF can be fused with CNN-based object detectors in a plug-and-play manner with negligible computational cost overhead. Experiments on the PASCAL VOC and MS COCO datasets demonstrate that our iffDetector consistently outperforms state-of-the-art methods by significant margins1. Copyright © 2020, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised hierarchical recurrent graph neural network for city-wide parking availability prediction

arXiv

引用

arXiv 2019年

作者： Zhang, Weijia Liu, Hao Liu, Yanchi Zhou, Jingbo Xiong, Hui University of Science and Technology of China Hefei China Business Intelligence Lab Baidu Research National Engineering Laboratory of Deep Learning Technology and Application Beijing China Rutgers University United States

The ability to predict city-wide parking availability is crucial for the successful development of Parking Guidance and Information (PGI) systems. Indeed, the effective prediction of city-wide parking availability can improve parking efficiency, help urban planning, and ultimately alleviate city congestion. However, it is a non-trivial task for predicting citywide parking availability because of three major challenges: 1) the non-Euclidean spatial autocorrelation among parking lots, 2) the dynamic temporal autocorrelation inside of and between parking lots, and 3) the scarcity of information about real-time parking availability obtained from real-time sensors (e.g., camera, ultrasonic sensor, and GPS). To this end, we propose Semi-supervised Hierarchical Recurrent Graph Neural Network (SHARE) for predicting city-wide parking availability. Specifically, we first propose a hierarchical graph convolution structure to model non-Euclidean spatial autocorrelation among parking lots. Along this line, a contextual graph convolution block and a soft clustering graph convolution block are respectively proposed to capture local and global spatial dependencies between parking lots. Additionally, we adopt a recurrent neural network to incorporate dynamic temporal dependencies of parking lots. Moreover, we propose a parking availability approximation module to estimate missing real-time parking availabilities from both spatial and temporal domain. Finally, experiments on two real-world datasets demonstrate the prediction performance of SHARE outperforms seven state-of-the-art baselines. Copyright © 2019, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Bayesian Optimized 1-Bit CNNs

Bayesian Optimized 1-Bit CNNs

引用

International Conference on Computer Vision (ICCV)

作者： Jiaxin Gu Junhe Zhao Xiaolong Jiang Baochang Zhang Jianzhuang Liu Guodong Guo Rongrong Ji Beihang University Beijing China Institute of Deep Learning Baidu Research Beijing China National Engineering Laboratory for Deep Learning Technology and Application Huawei Noah’s Ark Lab China School of Information Science and Engineering Xiamen University Fujian China Peng Cheng Lab Shenzhen China

ISBN: (数字)9781728148038

ISBN: (纸本)9781728148045

deep convolutional neural networks (DCNNs) have dominated the recent developments in computer vision through making various record-breaking models. However, it is still a great challenge to achieve powerful DCNNs in resource-limited environments, such as on embedded devices and smart phones. Researchers have realized that 1-bit CNNs can be one feasible solution to resolve the issue; however, they are baffled by the inferior performance compared to the full-precision DCNNs. In this paper, we propose a novel approach, called Bayesian optimized 1-bit CNNs (denoted as BONNs), taking the advantage of Bayesian learning, a well-established strategy for hard problems, to significantly improve the performance of extreme 1-bit CNNs. We incorporate the prior distributions of full-precision kernels and features into the Bayesian framework to construct 1-bit CNNs in an end-to-end manner, which have not been considered in any previous related methods. The Bayesian losses are achieved with a theoretical support to optimize the network simultaneously in both continuous and discrete spaces, aggregating different losses jointly to improve the model capacity. Extensive experiments on the ImageNet and CIFAR datasets show that BONNs achieve the best classification performance compared to state-of-the-art 1-bit CNNs.

关键词： Bayes methods Kernel Quantization (signal) Convolution Training Frequency modulation Indexes

来源：评论

学校读者我要写书评

暂无评论

Bayesian optimized 1-Bit CNNs

arXiv

引用

arXiv 2019年

作者： Gu, Jiaxin Zhao, Junhe Jiang, Xiaolong Zhang, Baochang Liu, Jianzhuang Guo, Guodong Ji, Rongrong Beihang University Beijing China Institute of Deep Learning Baidu Research Beijing China National Engineering Laboratory for Deep Learning Technology and Application Huawei Noah's Ark Lab China School of Information Science and Engineering Xiamen University Fujian China Peng Cheng Lab Shenzhen China

deep convolutional neural networks (DCNNs) have dominated the recent developments in computer vision through making various record-breaking models. However, it is still a great challenge to achieve powerful DCNNs in resource-limited environments, such as on embedded devices and smart phones. Researchers have realized that 1-bit CNNs can be one feasible solution to resolve the issue;however, they are baffled by the inferior performance compared to the full-precision DCNNs. In this paper, we propose a novel approach, called Bayesian optimized 1-bit CNNs (denoted as BONNs), taking the advantage of Bayesian learning, a well-established strategy for hard problems, to significantly improve the performance of extreme 1-bit CNNs. We incorporate the prior distributions of full-precision kernels and features into the Bayesian framework to construct 1-bit CNNs in an end-to-end manner, which have not been considered in any previous related methods. The Bayesian losses are achieved with a theoretical support to optimize the network simultaneously in both continuous and discrete spaces, aggregating different losses jointly to improve the model capacity. Extensive experiments on the ImageNet and CIFAR datasets show that BONNs achieve the best classification performance compared to state-of-the-art 1-bit CNNs. Copyright © 2019, The Authors. All rights reserved.

关键词： deep neural networks

来源：评论

学校读者我要写书评

暂无评论

3D Part Guided Image Editing for Fine-Grained Object Understanding

3D Part Guided Image Editing for Fine-Grained Object Underst...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Zongdai Liu Feixiang Lu Peng Wang Hui Miao Liangjun Zhang Ruigang Yang Bin Zhou State Key Laboratory of Virtual Reality Technology and Systems Beihang University Robotics and Autonomous Driving Laboratory Baidu Research National Engineering Laboratory of Deep Learning Technology and Application China ByteDance Research University of Kentucky Peng Cheng Laboratory Shenzhen China

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

Holistically understanding an object with its 3D movable parts is essential for visual models of a robot to interact with the world. For example, only by understanding many possible part dynamics of other vehicles (e.g., door or trunk opening, taillight blinking for changing lane), a self-driving vehicle can be success in dealing with emergency cases. However, existing visual models tackle rarely on these situations, but focus on bounding box detection. In this paper, we fill this important missing piece in autonomous driving by solving two critical issues. First, for dealing with data scarcity, we propose an effective training data generation process by fitting a 3D car model with dynamic parts to cars in real images. This allows us to directly edit the real images using the aligned 3D parts, yielding effective training data for learning robust deep neural networks (DNNs). Secondly, to benchmark the quality of 3D part understanding, we collected a large dataset in real driving scenario with cars in uncommon states (CUS), i.e. with door or trunk opened etc., which demonstrates that our trained network with edited images largely outperforms other baselines in terms of 2D detection and instance segmentation accuracy.

关键词： Three-dimensional displays Automobiles Solid modeling Two dimensional displays Image segmentation Vehicle dynamics Training

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：