检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Srivastava, Abhishek Chanda, Sukalpa Pal, Umapada Computer Vision and Pattern Recognition Unit Indian Statistical Institute West Bengal Kolkata700108 India Department of Computer Science and Communication Østfold University College Halden Norway

The performance of facial super-resolution methods relies on their ability to recover facial structures and salient features effectively. Even though the convolutional neural network and generative adversarial network-based methods deliver impressive performances on face hallucination tasks, the ability to use attributes associated with the low-resolution images to improve performance is unsatisfactory. In this paper, we propose an Attribute Guided Attention Generative Adversarial Network which employs novel attribute guided attention (AGA) modules to identify and focus the generation process on various facial features in the image. Stacking multiple AGA modules enables the recovery of both high and low-level facial structures. We design the discriminator to learn discriminative features exploiting the relationship between the high-resolution image and their corresponding facial attribute annotations. We then explore the use of U-Net based architecture to refine existing predictions and synthesize further facial details. Extensive experiments across several metrics show that our AGA-GAN and AGA-GAN+U-Net framework outperforms several other cutting-edge face hallucination state-of-the-art methods. We also demonstrate the viability of our method when every attribute descriptor is not known and thus, establishing its application in real-world scenarios. © 2021, CC BY.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

DE3-BERT: Distance-Enhanced Early Exiting for BERT based on Prototypical Networks

arXiv

引用

arXiv 2024年

作者： He, Jianing Zhang, Qi Ding, Weiping Miao, Duoqian Zhao, Jun Hu, Liang Cao, Longbing The School of Computer Science Tongji University Shanghai201804 China The School of Information Science and Technology Nantong University Nantong226019 China The National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing100190 China The DataX Research Centre School of Computing Macquarie University SydneyNSW2109 Australia

Early exiting has demonstrated its effectiveness in accelerating the inference of pre-trained language models like BERT by dynamically adjusting the number of layers executed. However, most existing early exiting methods only consider local information from an individual test sample to determine their exiting indicators, failing to leverage the global information offered by sample population. This leads to suboptimal estimation of prediction correctness, resulting in erroneous exiting decisions. To bridge the gap, we explore the necessity of effectively combining both local and global information to ensure reliable early exiting during inference. Purposefully, we leverage prototypical networks to learn class prototypes and devise a distance metric between samples and class prototypes. This enables us to utilize global information for estimating the correctness of early predictions. On this basis, we propose a novel Distance-Enhanced Early Exiting framework for BERT (DE3-BERT). DE3-BERT implements a hybrid exiting strategy that supplements classic entropy-based local information with distance-based global information to enhance the estimation of prediction correctness for more reliable early exiting decisions. Extensive experiments on the GLUE benchmark demonstrate that DE3-BERT consistently outperforms state-of-the-art models under different speed-up ratios with minimal storage or computational overhead, yielding a better trade-off between model performance and inference efficiency. Additionally, an in-depth analysis further validates the generality and interpretability of our method. © 2024, CC BY.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

The Devil is in the Conflict: Disentangled Information Graph Neural Networks for Fraud Detection

The Devil is in the Conflict: Disentangled Information Graph...

引用

IEEE International Conference on Data Mining (ICDM)

作者： Zhixun Li Dingshuo Chen Qiang Liu Shu Wu School of Computer Science and Technology Beijing Institute of Technology Center for Research on Intelligent Perception and Computing National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences School of Artificial Intelligence University of Chinese Academy of Sciences

Graph-based fraud detection has heretofore received considerable attention. Owning to the great success of Graph Neural Networks (GNNs), many approaches adopting GNNs for fraud detection has been gaining momentum. However, most existing methods are based on the strong inductive bias of homophily, which indicates that the context neighbors tend to have same labels or similar features. In real scenarios, fraudsters often engage in camouflage behaviors in order to avoid detection system. Therefore, the homophilic assumption no longer holds, which is known as the inconsistency problem. In this paper, we argue that the performance degradation is mainly attributed to the inconsistency between topology and attribute. To address this problem, we propose to disentangle the fraud network into two views, each corresponding to topology and attribute respectively. Then we propose a simple and effective method that uses the attention mechanism to adaptively fuse two views which captures data-specific preference. In addition, we further improve it by introducing mutual information constraints for topology and attribute. To this end, we propose a Disentangled Information Graph Neural Network (DIGNN) model, which utilizes variational bounds to find an approximate solution to our proposed optimization objective function. Extensive experiments demonstrate that our model can significantly outperform state-of-the-art baselines on real-world fraud detection datasets.

关键词： Adaptation models Network topology Fuses Semantics Graph neural networks Fraud Topology

来源：评论

学校读者我要写书评

暂无评论

Hybrid Multi-Task Learning for End-To-End Multimodal Emotion recognition

Hybrid Multi-Task Learning for End-To-End Multimodal Emotion...

引用

Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)

作者： Junjie Chen Yongwei Li Ziping Zhao Xuefei Liu Zhengqi Wen Jianhua Tao College of Computer and Information Engineering Tianjin Normal University Tianjin China National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing China Department of Automation Tsinghua University Beijing China Beijing National Research Center for Information Science and Technology Tsinghua University Beijing China

Multimodal emotion recognition plays a pivotal role in the advancement of natural human-computer interaction systems. Recent studies have attempted to apply multi-task learning to emotion recognition. However, the multi-task shared feature extractor of traditional methods needs to integrate the feature representations of different tasks, which may lead to the feature extractor failing to focus on the learning of emotion representations. To address this problem, we propose a hybrid multi-task learning framework for end-to-end multimodal emotion recognition, in which the primary task is emotion classification, and the auxiliary tasks are emotion regression and gender classification. This framework consists of two networks specialized in gender and emotion recognition, where the latter transfers knowledge from the former through our proposed Deep Aggregation LSTM (DA-LSTM). The DA-LSTM could more precisely capture emotional information in discourse by aggregating emotion and gender feature extractors. Experimental results on a commonly used dataset IEMOCAP demonstrate the effectiveness of our proposed method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A method to generate synthetically warped document image 4th

A method to generate synthetically warped document image

引用

4th International Conference on computer vision and Image Processing, CVIP 2019

作者： Garai, Arpan Biswas, Samit Mandal, Sekhar Chaudhuri, Bidyut B. Department of Computer Science and Technology Indian Institute of Engineering Sciences and Technology Shibpur HowrahWest Bengal711103 India Techno India University Kolkata India Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India

ISBN: (纸本)9789811540141

The digital camera captured document images may often be warped and distorted due to different camera angles or document surfaces. A robust technique is needed to solve this kind of distortion. The research on dewarping of the document suffers due to the limited availability of benchmark public dataset. In recent times, deep learning based approaches are used to solve the problems accurately. To train most of the deep neural networks a large number of document images is required and generating such a large volume of document images manually is difficult. In this paper, we propose a technique to generate a synthetic warped image from a flat-bedded scanned document image. It is done by calculating warping factors for each pixel position using two warping position parameters (WPP) and eight warping control parameters (WCP). These parameters can be specified as needed depending upon the desired warping. The results are compared with similar real captured images both qualitative and quantitative way. © Springer Nature Singapore Pte Ltd 2020.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

A New Defect Detection Method for Improving Text Detection and recognition Performances in Natural Scene Images

A New Defect Detection Method for Improving Text Detection a...

引用

2020 Swedish Workshop on Data Science, SweDS 2020

作者： Mokayed, Hamam Shivakumara, Palaiahnakote Liwicki, Marcus Pal, Umapada University of Malaya Faculty of Computer Science and Information Technology Kuala Lumpur Malaysia Lulea University of Technology Department of Computer Science Electrical and Space Engineering Sweden Indian Statistical Institute Computer Vision and Pattern Recognition Unit Kolkata India

ISBN: (纸本)9781728192048

This paper presents a new idea for improving text detection and recognition performances by detecting defects in the text detection results. Despite the rapid development of powerful deep learning based models for scene text detection and recognition in the wild, in complex situations (logos or decorated components connected with text), existing methods do not yield satisfactory results. In this paper, we propose to use post-processing method to improve the text detection and recognition performance. The proposed method extracts features, namely phase congruency, entropy and compactness for the text detection results. To strengthen discriminative power for feature extraction, we explore the combination of SVM classifier and Gaussian distribution of text components to determine proper weight, which represents true text component. The weights are multiplied with the features to detect defect components though clustering. The bounding boxes are redrawn, which results proper bounding box without defects components. Experimental results show that the proposed defect detection reports satisfactory results. To validate the effectiveness of defect detection, we conduct experiments on benchmark datasets of MSRA-TD-500 and SVT for detection and recognition before and after defect detection. The result shows that the performance of text detection and recognition improves significantly after defect detection. © 2020 IEEE.

关键词： Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

CoCoNet: A Collaborative Convolutional Network applied to fine-grained bird species classification

CoCoNet: A Collaborative Convolutional Network applied to fi...

引用

International Conference on Image and vision Computing New Zealand, IVCNZ

作者： Tapabrata Chakraborti Brendan McCane Steven Mills Umapada Pal University of Otago Computer Vision and Pattern recognition Unit Indian Statistical Institute

The following topics are dealt with: convolutional neural nets; learning (artificial intelligence); image classification; computer vision; feature extraction; video signal processing; deep learning (artificial intelli... 详细信息

ISBN: (数字)9781728185798

ISBN: (纸本)9781728185804

关键词： Training Visualization Image recognition Collaboration computer architecture Birds Task analysis

来源：评论

学校读者我要写书评

暂无评论

Reprogramming pretrained target-specific diffusion models for dual-target drug design 24

Reprogramming pretrained target-specific diffusion models fo...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Xiangxin Zhou Jiaqi Guan Yijia Zhang Xingang Peng Liang Wang Jianzhu Ma School of Artificial Intelligence University of Chinese Academy of Sciences and New Laboratory of Pattern Recognition (NLPR) State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS) Institute of Automation Chinese Academy of Sciences (CASIA) Department of Computer Science University of Illinois Urbana-Champaign Department of Electronic Engineering Tsinghua University Institute for Artificial Intelligence Peking University Department of Electronic Engineering Tsinghua University and Institute for AI Industry Research Tsinghua University

ISBN: (纸本)9798331314385

Dual-target therapeutic strategies have become a compelling approach and attracted significant attention due to various benefits, such as their potential in overcoming drug resistance in cancer therapy. Considering the tremendous success that deep generative models have achieved in structure-based drug design in recent years, we formulate dual-target drug design as a generative task and curate a novel dataset of potential target pairs based on synergistic drug combinations. We propose to design dual-target drugs with diffusion models that are trained on single-target protein-ligand complex pairs. Specifically, we align two pockets in 3D space with protein-ligand binding priors and build two complex graphs with shared ligand nodes for SE(3)-equivariant composed message passing, based on which we derive a composed drift in both 3D and categorical probability space in the generative process. Our algorithm can well transfer the knowledge gained in single-target pretraining to dual-target scenarios in a zero-shot manner. We also repurpose linker design methods as strong baselines for this task. Extensive experiments demonstrate the effectiveness of our method compared with various baselines.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Recognizing Bengali Word Images - A Zero-Shot Learning Perspective

Recognizing Bengali Word Images - A Zero-Shot Learning Persp...

引用

International Conference on pattern recognition

作者： Sukalpa Chanda Daniël Haitink Prashant Kumar Prasad Jochem Baas Umapada Pal Lambert Schomaker Østfold University College Norway Faculty of Science and Engineering. Bernoulli Institute for Mathematics Computer Science and Artificial Intelligence University of Groningen The Netherlands Computer Vision and Pattern Recognition Unit Indian Statistical Institute India

Zero-Shot Learning(ZSL) techniques could classify a completely unseen class, which it has never seen before during training. Thus, making it more apt for any real-life classification problem, where it is not possible to train a system with annotated data for all possible class types. This work investigates recognition of word images written in Bengali Script in a ZSL framework. The proposed approach performs Zero-Shot word recognition by coupling deep learned features procured from various CNN architectures along with 13 basic shapes/stroke primitives commonly observed in Bengali script characters. As per the notion of ZSL framework those 13 basic shapes are termed as “Signature/Semantic Attributes”. The obtained results are promising while evaluation was carried out in a Five-Fold cross-validation setup dealing with samples from 250 word classes.

关键词： Training Couplings Image recognition Shape Character recognition

来源：评论

学校读者我要写书评

暂无评论

Activating More Pixels in Image Super-Resolution Transformer

arXiv

引用

arXiv 2022年

作者： Chen, Xiangyu Wang, Xintao Zhou, Jiantao Qiao, Yu Dong, Chao State Key Laboratory of Internet of Things for Smart City University of Macau China Shenzhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences China Shanghai Artificial Intelligence Laboratory China ARC Lab Tencent PCG China

Transformer-based methods have shown impressive performance in low-level vision tasks, such as image super-resolution. However, we find that these networks can only utilize a limited spatial range of input information through attribution analysis. This implies that the potential of Transformer is still not fully exploited in existing networks. In order to activate more input pixels for better reconstruction, we propose a novel Hybrid Attention Transformer (HAT). It combines both channel attention and window-based self-attention schemes, thus making use of their complementary advantages of being able to utilize global statistics and strong local fitting capability. Moreover, to better aggregate the cross-window information, we introduce an overlapping cross-attention module to enhance the interaction between neighboring window features. In the training stage, we additionally adopt a same-task pre-training strategy to exploit the potential of the model for further improvement. Extensive experiments show the effectiveness of the proposed modules, and we further scale up the model to demonstrate that the performance of this task can be greatly improved. Our overall method significantly outperforms the state-of-the-art methods by more than 1dB. Copyright © 2022, The Authors. All rights reserved.

关键词： Pixels

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：