2020 25th International Conference on Pattern Recognition (ICPR)最新文献_第4页

IBN-STR: A Robust Text Recognizer for Irregular Text in Natural Scenes 自然场景中不规则文本的鲁棒文本识别器

2020 25th International Conference on Pattern Recognition (ICPR) Pub Date : 2021-01-10 DOI: 10.1109/ICPR48806.2021.9412775

Xiaoqian Li, Jie Liu, Guixuan Zhang, Shuwu Zhang

{"title":"IBN-STR: A Robust Text Recognizer for Irregular Text in Natural Scenes","authors":"Xiaoqian Li, Jie Liu, Guixuan Zhang, Shuwu Zhang","doi":"10.1109/ICPR48806.2021.9412775","DOIUrl":"https://doi.org/10.1109/ICPR48806.2021.9412775","url":null,"abstract":"Although text recognition methods based on deep neural networks have promising performance, there are still challenges due to the variety of text styles, perspective distortion, text with large curvature, and so on. To obtain a robust text recognizer, we have improved the performance from two aspects: data aspect and feature representation aspect. In terms of data, we transform the input images into S-shape distorted images in order to increase the diversity of training data. Besides, we explore the effects of different training data. In terms of feature representation, the combination of instance normalization and batch normalization improves the model's capacity and generalization ability. This paper proposes a robust scene text recognizer IBN-STR, which is an attention-based model. Through extensive experiments, the model analysis and comparison have been carried out from the aspects of data and feature representation, and the effectiveness of IBN-STR on both regular and irregular text instances has been verified. Furthermore, IBN-STR is an end-to-end recognition system that can achieve state-of-the-art performance.","PeriodicalId":6783,"journal":{"name":"2020 25th International Conference on Pattern Recognition (ICPR)","volume":"25 1","pages":"9522-9528"},"PeriodicalIF":0.0,"publicationDate":"2021-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85100118","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Attention Based Multi-Instance Thyroid Cytopathological Diagnosis with Multi-Scale Feature Fusion 基于多尺度特征融合的多实例甲状腺细胞病理诊断

2020 25th International Conference on Pattern Recognition (ICPR) Pub Date : 2021-01-10 DOI: 10.1109/ICPR48806.2021.9413184

Shuhao Qiu, Yao Guo, Chuang Zhu, Wenli Zhou, Huang Chen

{"title":"Attention Based Multi-Instance Thyroid Cytopathological Diagnosis with Multi-Scale Feature Fusion","authors":"Shuhao Qiu, Yao Guo, Chuang Zhu, Wenli Zhou, Huang Chen","doi":"10.1109/ICPR48806.2021.9413184","DOIUrl":"https://doi.org/10.1109/ICPR48806.2021.9413184","url":null,"abstract":"In recent years, deep learning has been popular in combining with cytopathology diagnosis. Using the whole slide images (WSI) scanned by electronic scanners at clinics, researchers have developed many algorithms to classify the slide (benign or malignant). However, the key area that support the diagnosis result can be relatively small in a thyroid WSI, and only the global label can be acquired, which make the direct use of the strongly supervised learning framework infeasible. What's more, because the clinical diagnosis of the thyroid cells requires the use of visual features in different scales, a generic feature extraction way may not achieve good performance. In this paper, we propose a weakly supervised multi-instance learning framework based on attention mechanism with multi-scale feature fusion (MSF) using convolutional neural network (CNN) for thyroid cytopathological diagnosis. We take each WSI as a bag, each bag contains multiple instances which are the different regions of the WSI, our framework is trained to learn the key area automatically and make the classification. We also propose a feature fusion structure, merge the low-level features into the final feature map and add an instance-level attention module in it, which improves the classification accuracy. Our model is trained and tested on the collected clinical data, reaches the accuracy of 93.2 %, which outperforms the other existing methods. We also tested our model on a public histopathology dataset and achieves better result than the state-of-the-art deep multi-instance method.","PeriodicalId":6783,"journal":{"name":"2020 25th International Conference on Pattern Recognition (ICPR)","volume":"48 1","pages":"3536-3541"},"PeriodicalIF":0.0,"publicationDate":"2021-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85985026","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Multi-Attribute Regression Network for Face Reconstruction 人脸重构的多属性回归网络

2020 25th International Conference on Pattern Recognition (ICPR) Pub Date : 2021-01-10 DOI: 10.1109/ICPR48806.2021.9412668

Xiangzheng Li, Suping Wu

{"title":"Multi-Attribute Regression Network for Face Reconstruction","authors":"Xiangzheng Li, Suping Wu","doi":"10.1109/ICPR48806.2021.9412668","DOIUrl":"https://doi.org/10.1109/ICPR48806.2021.9412668","url":null,"abstract":"In this paper, we propose a multi-attribute regression network (MARN) to investigate the problem of face reconstruction, especially in challenging cases when faces undergo large variations including severe poses, extreme expressions, and partial occlusions in unconstrained environments. The traditional 3DMM parametric regression method does not distinguish the learning of identity, expression, and attitude attributes, resulting in lacking geometric details in the reconstructed face. We propose to learn a face multi-attribute features during 3D face reconstruction from single 2D images. Our MARN enables the network to better extract the feature information of face identity, expression, and pose attributes. We introduce three loss functions to constrain the above three face attributes respectively. At the same time, we carefully design the geometric contour constraint loss function, using the constraints of sparse 2D face landmarks to improve the reconstructed geometric contour information. The experimental results show that our MARN has achieved significant improvements in 3D face reconstruction and face alignment on the AFLW2000-3D and AFLW datasets.","PeriodicalId":6783,"journal":{"name":"2020 25th International Conference on Pattern Recognition (ICPR)","volume":"463 1","pages":"7226-7233"},"PeriodicalIF":0.0,"publicationDate":"2021-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76609785","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 7

BiLuNet: A Multi-path Network for Semantic Segmentation on X-ray Images BiLuNet:用于x射线图像语义分割的多路径网络

2020 25th International Conference on Pattern Recognition (ICPR) Pub Date : 2021-01-10 DOI: 10.1109/ICPR48806.2021.9412027

V. Tran, Huei-Yung Lin, Hsiao-Wei Liu, Fang-Jie Jang, Chun-Han Tseng

引用次数: 3

AOAM: Automatic Optimization of Adjacency Matrix for Graph Convolutional Network 图卷积网络邻接矩阵的自动优化

2020 25th International Conference on Pattern Recognition (ICPR) Pub Date : 2021-01-10 DOI: 10.1109/ICPR48806.2021.9412046

Yuhang Zhang, Hongshuai Ren, Jiexia Ye, Xitong Gao, Yang Wang, Kejiang Ye, Chengzhong Xu

{"title":"AOAM: Automatic Optimization of Adjacency Matrix for Graph Convolutional Network","authors":"Yuhang Zhang, Hongshuai Ren, Jiexia Ye, Xitong Gao, Yang Wang, Kejiang Ye, Chengzhong Xu","doi":"10.1109/ICPR48806.2021.9412046","DOIUrl":"https://doi.org/10.1109/ICPR48806.2021.9412046","url":null,"abstract":"Graph Convolutional Network (GCN) is adopted to tackle the problem of convolution operation in non-Euclidean space. Previous works on GCN have made some progress, however, one of their limitations is that the design of Adjacency Matrix (AM) as GCN input requires domain knowledge and such process is cumbersome, tedious and error-prone. In addition, entries of a fixed Adjacency Matrix are generally designed as binary values (i.e., ones and zeros) which can not reflect the real relationship between nodes. Meanwhile, many applications require a weighted and dynamic Adjacency Matrix instead of an unweighted and fixed AM, and there are few works focusing on designing a more flexible Adjacency Matrix. To that end, we propose an end-to-end algorithm to improve the GCN performance by focusing on the Adjacency Matrix. We first provide a calculation method called node information entropy to update the matrix. Then, we perform the search strategy in a continuous space and introduce the Deep Deterministic Policy Gradient (DDPG) method to overcome the drawback of the discrete space search. Finally, we integrate the GCN and reinforcement learning into an end-to-end framework. Our method can automatically define the Adjacency Matrix without prior knowledge. At the same time, the proposed approach can deal with any size of the matrix and provide a better AM for network. Four popular datasets are selected to evaluate the capability of our algorithm. The method in this paper achieves the state-of-the-art performance on Cora and Pubmed datasets, with the accuracy of 84.6% and 81.6% respectively.","PeriodicalId":6783,"journal":{"name":"2020 25th International Conference on Pattern Recognition (ICPR)","volume":"223 1","pages":"5130-5136"},"PeriodicalIF":0.0,"publicationDate":"2021-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76992319","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Augmentation of Small Training Data Using GANs for Enhancing the Performance of Image Classification 利用gan增强小训练数据增强图像分类性能

2020 25th International Conference on Pattern Recognition (ICPR) Pub Date : 2021-01-10 DOI: 10.1109/ICPR48806.2021.9412399

S. Hung, J. Q. Gan

{"title":"Augmentation of Small Training Data Using GANs for Enhancing the Performance of Image Classification","authors":"S. Hung, J. Q. Gan","doi":"10.1109/ICPR48806.2021.9412399","DOIUrl":"https://doi.org/10.1109/ICPR48806.2021.9412399","url":null,"abstract":"It is difficult to achieve high performance without sufficient training data for deep convolutional neural networks (DCNNs) to learn. Data augmentation plays an important role in improving robustness and preventing overfitting in machine learning for many applications such as image classification. In this paper, a novel method for data augmentation is proposed to solve the problem of machine learning with small training datasets. The proposed method can synthesise similar images with rich diversity from only a single original training sample to increase the number of training data by using generative adversarial networks (GANs). It is expected that the synthesised images possess class-informative features, which may be in the validation or testing data but not in the training data due to that the training dataset is small, and thus they can be effective as augmented training data to improve the classification accuracy of DCNNs. The experimental results have demonstrated that the proposed method with a novel GAN framework for image training data augmentation can significantly enhance the classification performance of DCNNs for applications where original training data is limited.","PeriodicalId":6783,"journal":{"name":"2020 25th International Conference on Pattern Recognition (ICPR)","volume":"5 1","pages":"3350-3356"},"PeriodicalIF":0.0,"publicationDate":"2021-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80908028","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 4

MEAN: Multi - Element Attention Network for Scene Text Recognition MEAN:用于场景文本识别的多元素注意网络

2020 25th International Conference on Pattern Recognition (ICPR) Pub Date : 2021-01-10 DOI: 10.1109/ICPR48806.2021.9413166

Ruijie Yan, Liangrui Peng, Shanyu Xiao, Gang Yao, Jaesik Min

{"title":"MEAN: Multi - Element Attention Network for Scene Text Recognition","authors":"Ruijie Yan, Liangrui Peng, Shanyu Xiao, Gang Yao, Jaesik Min","doi":"10.1109/ICPR48806.2021.9413166","DOIUrl":"https://doi.org/10.1109/ICPR48806.2021.9413166","url":null,"abstract":"Scene text recognition is a challenging problem due to the wide variances in contents, styles, orientations, and image quality of text instances in natural scene images. To learn the intrinsic representation of scene texts, a novel multi-element attention (MEA) mechanism is proposed to exploit geometric structures from local to global levels in feature maps extracted from a scene text image. The MEA mechanism is a generalized form of self-attention technique. The elements in feature maps are taken as the nodes of an undirected graph, and three kinds of adjacency matrices are designed to aggregate information at local, neighborhood and global levels before calculating the attention weights. A multi-element attention network (MEAN) is implemented, which includes a CNN for feature extraction, an encoder with MEA mechanism and a decoder for predicting text codes. Orientational positional encoding is added to feature maps output by the CNN, and a feature vector sequence transformed from the feature maps is used as the input of the encoder. Experimental results show that MEAN has achieved state-of-the-art or competitive performance on seven public English scene text datasets (IIITSk, SVT, IC03, IC13, IC15, SVTP, and CUTE). Further experiments have been conducted on a selected subset of the RCTW Chinese scene text dataset, demonstrating that MEAN can handle horizontal, vertical, and irregular scene text samples.","PeriodicalId":6783,"journal":{"name":"2020 25th International Conference on Pattern Recognition (ICPR)","volume":"24 1","pages":"1-8"},"PeriodicalIF":0.0,"publicationDate":"2021-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80932868","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Writer Identification Using Deep Neural Networks: Impact of Patch Size and Number of Patches 使用深度神经网络的作者识别:补丁大小和补丁数量的影响

2020 25th International Conference on Pattern Recognition (ICPR) Pub Date : 2021-01-10 DOI: 10.1109/ICPR48806.2021.9412575

Akshay Punjabi, J. R. Prieto, E. Vidal

引用次数: 1

A Deep Learning-Based Method for Predicting Volumes of Nasopharyngeal Carcinoma for Adaptive Radiation Therapy Treatment 基于深度学习的鼻咽癌适应性放疗体积预测方法

2020 25th International Conference on Pattern Recognition (ICPR) Pub Date : 2021-01-10 DOI: 10.1109/ICPR48806.2021.9412924

Bilel Daoud, K. Morooka, Shoko Miyauchi, R. Kurazume, W. Mnejja, L. Farhat, J. Daoud

{"title":"A Deep Learning-Based Method for Predicting Volumes of Nasopharyngeal Carcinoma for Adaptive Radiation Therapy Treatment","authors":"Bilel Daoud, K. Morooka, Shoko Miyauchi, R. Kurazume, W. Mnejja, L. Farhat, J. Daoud","doi":"10.1109/ICPR48806.2021.9412924","DOIUrl":"https://doi.org/10.1109/ICPR48806.2021.9412924","url":null,"abstract":"This paper presents a new system for predicting the spatial change of Nasopharyngeal carcinoma(NPC) and organ-at-risks (OARs) volumes over the course of the radiation therapy (RT) treatment for facilitating the workflow of adaptive radiotherapy. The proposed system, called “Tumor Evolution Prediction (TEP-Net)”, predicts the spatial distributions of NPC and 5 OARs, separately, in response to RT in the coming week, week n. Here, TEP-Net has (n-1)-inputs that are week 1 to week n-1 of CT axial, coronal or sagittal images acquired once the patient complete the planned RT treatment of the corresponding week. As a result, three predicted results of each target region are obtained from the three-view CT images. To determine the final prediction of NPC and 5 OARs, two integration methods, weighted fully connected layers and weighted voting methods, are introduced. From the experiments using weekly CT images of 140 NPC patients, our proposed system achieves the best performance for predicting NPC and OARs compared with conventional methods.","PeriodicalId":6783,"journal":{"name":"2020 25th International Conference on Pattern Recognition (ICPR)","volume":"9 1","pages":"3256-3263"},"PeriodicalIF":0.0,"publicationDate":"2021-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80984587","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A delayed Elastic-Net approach for performing adversarial attacks 执行对抗性攻击的延迟弹性网络方法

2020 25th International Conference on Pattern Recognition (ICPR) Pub Date : 2021-01-10 DOI: 10.1109/ICPR48806.2021.9413170

Brais Cancela, V. Bolón-Canedo, Amparo Alonso-Betanzos

引用次数: 1