检索结果-内蒙古大学图书馆

6th International Conference on Green Technology and Sustainable Development, GTSD 2022

作者： Pham, Van Dung Nguyen, Le Quan Pham, Nhat Truong Nguyen, Bao Hung Minh Dang, Due Ngoe Nguyen, Sy Dzung Deep Learning and Application Ho Chi Minh City Viet Nam Sejong University Seoul Korea Republic of Institute for Computational Science Ton Duc Thang University Ho Chi Minh City Viet Nam SK-Global JSC Ho Chi Minh City Viet Nam FPT University Computing Fundamental Department Ho Chi Minh City Viet Nam

ISBN: (数字)9781665466288

ISBN: (纸本)9781665466288

Information extraction and retrieval are growing fields that have a significant role in document parser and analysis systems. Researches and applications developed in recent years show the numerous difficulties and obstacles in extracting key information from documents. Thanks to the raising of graph theory and deep learning, graph representation and graph learning have been widely applied in information extraction to obtain more exact results. In this paper, we propose a solution upon graph neural networks (GNN) for key information extraction (KIE) that aims to extract the key information from mobile-captured Vietnamese receipt images. Firstly, the images are pre-processed using U2-Net, and then a CRAFT model is used to detect texts from the pre-processed images. Next, the implemented TransformerOCR model is employed for text recognition. Finally, a GNN-based model is designed to extract the key information based on the recognized texts. For validating the effectiveness of the proposed solution, the publicly available dataset released from the Mobile-Captured Receipt Recognition (MC-OCR) Challenge 2021 is used to train and evaluate. The experimental results indicate that our proposed solution achieves a character error rate (CER) score of 0.25 on the private test set, which is more comparable with all reported solutions in the MC-OCR Challenge 2021 as mentioned in the literature. For reproducing and knowledge-sharing purposes, our implementation of the proposed solution is publicly available at https://***/ThorPhamlKey_infomation_extraction. © 2022 IEEE.

关键词： Optical character recognition

来源：评论

学校读者我要写书评

暂无评论

Fully transformer networks for semantic image segmentation

arXiv

引用

arXiv 2021年

作者： Wu, Sitong Wu, Tianyi Lin, Fangjian Tian, Shengwei Guo, Guodong Institute of Deep Learning Baidu Research Beijing100085 China National Engineering Laboratory for Deep Learning Technology and Application Beijing100085 China Shengwei Tian are with School of Software XinJiang University Urumqi China

Transformers have shown impressive performance in various natural language processing and computer vision tasks, due to the capability of modeling long-range dependencies. Recent progress has demonstrated that combining such Transformers with CNN-based semantic image segmentation models is very promising. However, it is not well studied yet on how well a pure Transformer based approach can achieve for image segmentation. In this work, we explore a novel framework for semantic image segmentation, which is encoder-decoder based Fully Transformer Networks (FTN). Specifically, we first propose a Pyramid Group Transformer (PGT) as the encoder for progressively learning hierarchical features, meanwhile reducing the computation complexity of the standard Visual Transformer (ViT). Then, we propose a Feature Pyramid Transformer (FPT) to fuse semantic-level and spatial-level information from multiple levels of the PGT encoder for semantic image segmentation. Surprisingly, this simple baseline can achieve better results on multiple challenging semantic segmentation and face parsing benchmarks, including PASCAL Context, ADE20K, COCOStuff, and CelebAMask-HQ. The source code will be released on https://***/BR-IDL/PaddleViT. Copyright © 2021, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Mapfusion: A general framework for 3D object detection with HDMaps

arXiv

引用

arXiv 2021年

作者： Fang, Jin Zhou, Dingfu Song, Xibin Zhang, Liangjun Robotics and Autonomous Driving Laboratory Baidu Research China National Engineering Laboratory of Deep Learning Technology and Application China

3D object detection is a key perception component in autonomous driving. Most recent approaches are based on Lidar sensors only or fused with cameras. Maps (e.g., High Definition Maps), a basic infrastructure for intelligent vehicles, however, have not been well exploited for boosting object detection tasks. In this paper, we propose a simple but effective framework - MapFusion to integrate the map information into modern 3D object detector pipelines. In particular, we design a FeatureAgg module for HD Map feature extraction and fusion, and a MapSeg module as an auxiliary segmentation head for the detection backbone. Our proposed MapFusion is detector independent and can be easily integrated into different detectors. The experimental results of three different baselines on large public autonomous driving dataset demonstrate the superiority of the proposed framework. By fusing the map information, we can achieve 1.27 to 2.79 points improvements for mean Average Precision (mAP) on three strong 3d object detection baselines. © 2021, CC BY-NC-ND.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

TransFER: learning Relation-aware Facial Expression Representations with Transformers

TransFER: Learning Relation-aware Facial Expression Represen...

引用

International Conference on Computer Vision (ICCV)

作者： Fanglei Xue Qiangchang Wang Guodong Guo University of Chinese Academy of Sciences Beijing China Chinese Academy of Sciences Beijing China West Virginia University Morgantown USA Institute of Deep Learning Beijing China National Engineering Laboratory for Deep Learning Technology and Application Beijing China

ISBN: (纸本)9781665428132

Facial expression recognition (FER) has received increasing interest in computer vision. We propose the Trans-FER model which can learn rich relation-aware local representations. It mainly consists of three components: Multi-Attention Dropping (MAD), ViT-FER, and Multi-head Self-Attention Dropping (MSAD). First, local patches play an important role in distinguishing various expressions, however, few existing works can locate discriminative and diverse local patches. This can cause serious problems when some patches are invisible due to pose variations or viewpoint changes. To address this issue, the MAD is proposed to randomly drop an attention map. Consequently, models are pushed to explore diverse local patches adaptively. Second, to build rich relations between different local patches, the Vision Transformers (ViT) are used in FER, called ViT-FER. Since the global scope is used to reinforce each local patch, a better representation is obtained to boost the FER performance. Thirdly, the multi-head self-attention allows ViT to jointly attend to features from different information subspaces at different positions. Given no explicit guidance, however, multiple self-attentions may extract similar relations. To address this, the MSAD is proposed to randomly drop one self-attention module. As a result, models are forced to learn rich relations among diverse local patches. Our proposed TransFER model outperforms the state-of-the-art methods on several FER benchmarks, showing its effectiveness and usefulness.

关键词： Computer vision Adaptation models Face recognition Computational modeling Transfer learning Computer architecture Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

Nested Collaborative learning for Long-Tailed Visual Recognition

arXiv

引用

arXiv 2022年

作者： Li, Jun Tan, Zichang Wan, Jun Lei, Zhen Guo, Guodong CBSR&NLPR Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China Institute of Deep Learning Baidu Research Beijing China National Engineering Laboratory for Deep Learning Technology and Application Beijing China Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science&Innovation Chinese Academy of Sciences Hong Kong

The networks trained on the long-tailed dataset vary remarkably, despite the same training settings, which shows the great uncertainty in long-tailed learning. To alleviate the uncertainty, we propose a Nested Collaborative learning (NCL), which tackles the problem by collaboratively learning multiple experts together. NCL consists of two core components, namely Nested Individual learning (NIL) and Nested Balanced Online Distillation (NBOD), which focus on the individual supervised learning for each single expert and the knowledge transferring among multiple experts, respectively. To learn representations more thoroughly, both NIL and NBOD are formulated in a nested way, in which the learning is conducted on not just all categories from a full perspective but some hard categories from a partial perspective. Regarding the learning in the partial perspective, we specifically select the negative categories with high predicted scores as the hard categories by using a proposed Hard Category Mining (HCM). In the NCL, the learning from two perspectives is nested, highly related and complementary, and helps the network to capture not only global and robust features but also meticulous distinguishing ability. Moreover, self-supervision is further utilized for feature enhancement. Extensive experiments manifest the superiority of our method with outperforming the state-of-the-art whether by using a single model or an ensemble. Code is available at https://***/Bazinga699/NCL Copyright © 2022, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

ProposalContrast: Unsupervised Pre-training for LiDAR-based 3D Object Detection

arXiv

引用

arXiv 2022年

作者： Yin, Junbo Zhou, Dingfu Zhang, Liangjun Fang, Jin Xu, Cheng-Zhong Shen, Jianbing Wang, Wenguan School of Computer Science Beijing Institute of Technology China Baidu Research China National Engineering Laboratory of Deep Learning Technology and Application China SKL-IOTSC CIS University of Macau China ReLER AAII University of Technology Sydney Australia

Existing approaches for unsupervised point cloud pre-training are constrained to either scene-level or point/voxel-level instance discrimination. Scene-level methods tend to lose local details that are crucial for recognizing the road objects, while point/voxel-level methods inherently suffer from limited receptive field that is incapable of perceiving large objects or context environments. Considering region-level representations are more suitable for 3D object detection, we devise a new unsupervised point cloud pre-training framework, called ProposalContrast, that learns robust 3D representations by contrasting region proposals. Specifically, with an exhaustive set of region proposals sampled from each point cloud, geometric point relations within each proposal are modeled for creating expressive proposal representations. To better accommodate 3D detection properties, ProposalContrast optimizes with both inter-cluster and inter-proposal separation, i.e., sharpening the discriminativeness of proposal representations across semantic classes and object instances. The generalizability and transferability of ProposalContrast are verified on various 3D detectors (i.e., PV-RCNN, CenterPoint, PointPillars and PointRCNN) and datasets (i.e., KITTI, Waymo and ONCE). Copyright © 2022, 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 3D Object Detection with Proficient Teachers

arXiv

引用

arXiv 2022年

作者： Yin, Junbo Fang, Jin Zhou, Dingfu Zhang, Liangjun Xu, Cheng-Zhong Shen, Jianbing Wang, Wenguan School of Computer Science Beijing Institute of Technology China Baidu Research United States National Engineering Laboratory of Deep Learning Technology and Application China SKL-IOTSC Cis University of Macau China ReLER Aaii University of Technology Sydney Australia

Dominated point cloud-based 3D object detectors in autonomous driving scenarios rely heavily on the huge amount of accurately labeled samples, however, 3D annotation in the point cloud is extremely tedious, expensive and time-consuming. To reduce the dependence on large supervision, semi-supervised learning (SSL) based approaches have been proposed. The Pseudo-Labeling methodology is commonly used for SSL frameworks, however, the low-quality predictions from the teacher model have seriously limited its performance. In this work, we propose a new Pseudo-Labeling framework for semi-supervised 3D object detection, by enhancing the teacher model to a proficient one with several necessary designs. First, to improve the recall of pseudo labels, a Spatial-temporal Ensemble (STE) module is proposed to generate sufficient seed boxes. Second, to improve the precision of recalled boxes, a Clustering-based Box Voting (CBV) module is designed to get aggregated votes from the clustered seed boxes. This also eliminates the necessity of sophisticated thresholds to select pseudo labels. Furthermore, to reduce the negative influence of wrongly pseudo-labeled samples during the training, a soft supervision signal is proposed by considering Box-wise Contrastive learning (BCL). The effectiveness of our model is verified on both ONCE and Waymo datasets. For example, on ONCE, our approach significantly improves the baseline by 9.51 mAP. Moreover, with half annotations, our model outperforms the oracle model with full annotations on Waymo. Copyright © 2022, 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

Q-ViT: accurate and fully quantized low-bit vision transformer 22

Q-ViT: accurate and fully quantized low-bit vision transform...

引用

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Yanjing Li Sheng Xu Baochang Zhang Xianbin Cao Peng Gao Guodong Guo Beihang University Beijing P.R.China Beihang University Beijing P.R.China and Zhongguancun Laboratory Beijing P.R.China Shanghai Artificial Intelligence Laboratory Shanghai P.R.China Institute of Deep Learning Baidu Research Beijing P.R.China and National Engineering Laboratory for Deep Learning Technology and Application Beijing P.R.China

ISBN: (纸本)9781713871088

The large pre-trained vision transformers (ViTs) have demonstrated remarkable performance on various visual tasks, but suffer from expensive computational and memory cost problems when deployed on resource-constrained devices. Among the powerful compression approaches, quantization extremely reduces the computation and memory consumption by low-bit parameters and bit-wise operations. However, low-bit ViTs remain largely unexplored and usually suffer from a significant performance drop compared with the real-valued counterparts. In this work, through extensive empirical analysis, we first identify the bottleneck for severe performance drop comes from the information distortion of the low-bit quantized self-attention map. We then develop an information rectification module (IRM) and a distribution guided distillation (DGD) scheme for fully quantized vision transformers (Q-ViT) to effectively eliminate such distortion, leading to a fully quantized ViTs. We evaluate our methods on popular DeiT and Swin backbones. Extensive experimental results show that our method achieves a much better performance than the prior arts. For example, our Q-ViT can theoretically accelerates the ViT-S by 6.14 × and achieves about 80.9% Top-1 accuracy, even surpassing the full-precision counterpart by 1.0% on ImageNet dataset.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Vietnamese Scene Text Detection and Recognition using deep learning: An Empirical Study 6

Vietnamese Scene Text Detection and Recognition using Deep L...

引用

6th International Conference on Green Technology and Sustainable Development, GTSD 2022

作者： Pham, Nhat Truong Pham, Van Dung Nguyen-Van, Qui Nguyen, Bao Hung Minh Dang, Duc Ngoc Nguyen, Sy Dzung Institute for Computational Science Ton Duc Thang University Ho Chi Minh City Viet Nam Deep Learning and Application Ho Chi Minh City Viet Nam Ho Chi Minh City University of Technology Department of Telecommunications Engineering Ho Chi Minh City Viet Nam SK-Global JSC Ho Chi Minh City Viet Nam FPT University Computing Fundamental Department Ho Chi Minh City Viet Nam

ISBN: (数字)9781665466288

ISBN: (纸本)9781665466288

Scene text detection and recognition are vital challenging tasks in computer vision, which are to detect and recognize sequences of texts in natural scenes. Recently, researchers have investigated a lot of state-of-The-Art methods to improve the accuracy and efficiency of text detection and recognition. However, there has been little research on text detection and recognition in natural scenes in Vietnam. In this paper, a deep learning-based empirical investigation of Vietnamese scene text detection and recognition is presented. Firstly, four detection models including differentiable binarization network (DBN), pyramid mask text detector (PMTD), pixel aggregation network (PAN), and Fourier contour embedding network (FCEN), are employed to detect text regions from the images. Then, four text recognition models including convolutional recurrent neural network (CRNN), self-Attention text recognition network (SATRN), no-recurrence sequence-To-sequence text recognizer (NRTR), and RobustScanner (RS) are also investigated to recognize the texts. Moreover, data augmentation methods are also applied to enrich data for improving the accuracy and enhancing the performance of scene text detection and recognition. To validate the effectiveness of scene text detection and recognition models, the VinText dataset is employed for evaluation. Empirical results show that PMTD and SATRN achieve the highest scores among the others for text detection and recognition, respectively. For knowledge-sharing, our implementation is publicly available at. © 2022 IEEE.

关键词： Optical character recognition

来源：评论

学校读者我要写书评

暂无评论

LAE : Long-tailed Age Estimation

arXiv

引用

arXiv 2021年

作者： Bao, Zenghao Tan, Zichang Zhu, Yu Wan, Jun Ma, Xibo Lei, Zhen Guo, Guodong CBSR NLPR Institute of Automation Chinese Academy of Sciences School of Artificial Intelligence University of Chinese Academy of Sciences Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science & Innovation Chinese Academy of Sciences Institute of Deep Learning Baidu Research National Engineering Laboratory for Deep Learning Technology and Application

Facial age estimation is an important yet very challenging problem in computer vision. To improve the performance of facial age estimation, we first formulate a simple standard baseline and build a much strong one by collecting the tricks in pre-training, data augmentation, model architecture, and so on. Compared with the standard baseline, the proposed one significantly decreases the estimation errors. Moreover, long-tailed recognition has been an important topic in facial age datasets, where the samples often lack on the elderly and children. To train a balanced age estimator, we propose a two-stage training method named Long-tailed Age Estimation (LAE), which decouples the learning procedure into representation learning and classification. The effectiveness of our approach has been demonstrated on the dataset provided by organizers of Guess The Age Contest 2021. Copyright © 2021, The Authors. All rights reserved.

关键词： deep learning

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：