检索结果-内蒙古大学图书馆

IEEE International Conference on Image Processing (ICIP)

作者： Cho, Suhwan Cho, MyeongAh Chung, Tae-young Lee, Heansung Lee, Sangyoun Yonsei Univ Seoul South Korea

ISBN: (纸本)9781728163956

The encoder-decoder based methods for semi-supervised video object segmentation (Semi-VOS) have received extensive attention due to their superior performances. However, most of them have complex intermediate networks which generate strong specifiers to be robust against challenging scenarios, and this is quite inefficient when dealing with relatively simple scenarios. To solve this problem, we propose a real-time network, Clue Refining Network for Video Object Segmentation (CRVOS), that does not have any intermediate network to efficiently deal with these scenarios. In this work, we propose a simple specifier, referred to as the Clue, which consists of the previous frame's coarse mask and coordinates information. We also propose a novel refine module which shows the better performance compared with the general ones by using a deconvolution layer instead of a bilinear upsampling layer. Our proposed method shows the fastest speed among the existing methods with a competitive accuracy. On DAVIS 2016 validation set, our method achieves 63.5 fps and J&F score of 81.6%.

关键词： Video object segmentation Real-time tracker encoder-decoder architecture

来源：评论

学校读者我要写书评

暂无评论

Exploring the Interactions between Target Positive and Negative Information for Acoustic Echo Cancellation 24

Exploring the Interactions between Target Positive and Negat...

引用

Interspeech Conference

作者： Han, Chang Xu, Xinmeng Tu, Weiping Yang, Yuhong Liu, Yajie Wuhan Univ Sch Comp Sci NERCMS Wuhan Peoples R China Hubei Luojia Lab Wuhan Peoples R China Wuhan Univ Hubei Key Lab Multimedia & Network Commun Engn Wuhan Peoples R China

Acoustic echo cancellation (AEC) aims to remove interference signals while leaving near-end speech least distorted. As the indistinguishable patterns between near-end speech and interference signals, near-end speech can't be separated completely, causing speech distortion and interference signals residual. We observe that besides target positive information, e.g., ground-truth speech and features, the target negative information, such as interference signals and features, helps make pattern of target speech and interference signals more discriminative. Therefore, we present a novel AEC model encoder-decoder architecture with the guidance of negative information termed as CMNet. A collaboration module (CM) is designed to establish the correlation between the target positive and negative information in a learnable manner via three blocks: target positive, target negative, and interactive block. Experimental results demonstrate our CMNet achieves superior performance than recent methods.

关键词： acoustic echo cancellation encoder-decoder architecture target positive and negative information

来源：评论

学校读者我要写书评

暂无评论

Image to LaTeX with Graph Neural Network for Mathematical Formula Recognition 16th

Image to LaTeX with Graph Neural Network for Mathematical Fo...

引用

16th IAPR International Conference on Document Analysis and Recognition (ICDAR)

作者： Peng, Shuai Gao, Liangcai Yuan, Ke Tang, Zhi Peking Univ Wangxuan Inst Comp Technol Beijing Peoples R China

ISBN: (纸本)9783030863319

Mathematical formula recognition aims to automatically convert formula images into their structured description formats. Recently, some encoder-decoder models have been presented for this task, while they seldom explicitly consider spatial relationship among symbols. In this paper, we proposed a novel encoder-decoder model with Graph Neural Network (GNN) to translate mathematical formula images into LaTeX codes. In the proposed model, the symbols segmented from the raw image are used to build graphs based on their spatial connection. The encoder consists of Convolutional Neural Network (CNN) and GNN. CNN is utilized to extract the visual features from the whole formula or symbols, and GNN is used to transmit the spatial information embedded in the built graphs. The adopted decoder is a Recurrent Neural Network (RNN) model, which implements a language model to generate the output sentences based on the encoded features with attention mechanism. The experimental results on IM2LATEX-100K dataset demonstrated that the proposed model obtained a better performance than state-of-the-art approaches.

关键词： Mathematical formula recognition Graph neural network encoder-decoder architecture image to LaTeX

来源：评论

学校读者我要写书评

暂无评论

Triple-Branch Asymmetric Network for Real-time Semantic Segmentation of Road Scenes

引用

Instrumentation 2024年第2期11卷 72-82页

作者： Yazhi Zhang Xuguang Zhang Hui Yu The Communication Engineering Department Hangzhou Dianzi UniversityZhejiang 310020China The School of Creative Technologies University of PorsmouthUK

As the field of autonomous driving evolves, real-time semantic segmentation has become a crucial part of computer vision tasks. However, most existing methods use lightweight convolution to reduce the computational effort, resulting in lower accuracy. To address this problem, we construct TBANet, a network with an encoder-decoder structure for efficient feature extraction. In the encoder part, the TBA module is designed to extract details and the ETBA module is used to learn semantic representations in a high-dimensional space. In the decoder part, we design a combination of multiple upsampling methods to aggregate features with less computational overhead. We validate the efficiency of TBANet on the Cityscapes dataset. It achieves 75.1% mean Intersection over Union(mIoU) with only 2.07 million parameters and can reach 90.3 Frames Per Second(FPS).

关键词： encoder-decoder architecture lightweight convolution real-time semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

LocalBins: Improving Depth Estimation by Learning Local Distributions 17th

LocalBins: Improving Depth Estimation by Learning Local Dist...

引用

17th European Conference on Computer Vision (ECCV)

作者： Bhat, Shariq Farooq Alhashim, Ibraheem Wonka, Peter KAUST Thuwal Saudi Arabia Saudi Data & Artificial Intelligence Authority SD Natl Ctr Artificial Intelligence NCAI Riyadh Saudi Arabia

ISBN: (纸本)9783031197680;9783031197697

We propose a novel architecture for depth estimation from a single image. The architecture itself is based on the popular encoder-decoder architecture that is frequently used as a starting point for all dense regression tasks. We build on AdaBins which estimates a global distribution of depth values for the input image and evolve the architecture in two ways. First, instead of predicting global depth distributions, we predict depth distributions of local neighborhoods at every pixel. Second, instead of predicting depth distributions only towards the end of the decoder, we involve all layers of the decoder. We call this new architecture LocalBins. Our results demonstrate a clear improvement over the state-of-the-art in all metrics on the NYU-Depth V2 dataset. Code and pretrained models will be made publicly available (https://***/sharigfarooq123/LocalBins).

关键词： Single image depth estimation encoder-decoder architecture Deep learning Dense regression Histogram prediction

来源：评论

学校读者我要写书评

暂无评论

ATU-NET: AN ADAPTIVE TRANSFORMATION-BASED U-NET FOR MEDICAL IMAGE SEGMENTATION 31

ATU-NET: AN ADAPTIVE TRANSFORMATION-BASED U-NET FOR MEDICAL ...

引用

2024 International Conference on Image Processing

作者： Du, Qianyu Zhong, Baojiang Ma, Kai-Kuang Soochow Univ Sch Comp Sci & Technol Suzhou Peoples R China Nanjing Univ Aeronaut & Astronaut Coll Elect & Informat Engn Coll Integrated Circuits Nanjing Peoples R China

ISBN: (纸本)9798350349405;9798350349399

Both the U-Net and its variants, which produce the state-of-the-art performance in the field of medical image segmentation, are founded on an encoder-decoder architecture. However, this architecture generally processes the input image in the spatial domain only, overlooking potential insights that could be gained from other transform domains. For that, an adaptive transformation-based U-Net (ATU-Net) is proposed in this paper. Our ATU-Net is based on a novel network architecture called the adaptive transformation-encoder-decoder (ATU), which adaptively transforms the input image into a more suitable domain by training the transformation kernel for processing to make it easier for the encoder and decoder to extract key features of the image. Extensive experimental results obtained on benchmark datasets have shown that our proposed ATU-Net can deliver superior performance to the existing methods.

关键词： Deep learning medical image segmentation transform domain encoder-decoder architecture

来源：评论

学校读者我要写书评

暂无评论

Enhancing E-commerce Spelling Correction with Fine-Tuned Transformer Models 24

Enhancing E-commerce Spelling Correction with Fine-Tuned Tra...

引用

30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining

作者： Dutta, Arnab Polushin, Gleb Zhang, Xiaoshuang Stein, Daniel eBay GmbH Dreilinden Germany eBay Inc Shanghai Peoples R China eBay GmbH Aachen Germany

ISBN: (纸本)9798400704901

In the realm of e-commerce, the process of search stands as the primary point of interaction for users, wielding a profound influence on the platform's revenue generation. Notably, spelling correction assumes a pivotal role in shaping the user's search experience by rectifying erroneous query inputs, thus facilitating more accurate retrieval outcomes. Within the scope of this research paper, our aim is to enhance the existing state-of-the-art discriminative model performance with generative modelling strategies while concurrently addressing the engineering concerns associated with real-time online latency, inherent to models of this category. We endeavor to refine LSTM-based classification models for spelling correction through a generative fine-tuning approach hinged upon pre-trained language models. Our comprehensive offline assessments have yielded compelling results, showcasing that transformer-based architectures, such as BART (developed by Facebook) and T5 (a product of Google), have achieved a 4% enhancement in F1 score compared to baseline models for the English language sites. Furthermore, to mitigate the challenges posed by latency, we have incorporated model pruning techniques like no-teacher distillation. We have undertaken the deployment of our model (English only) as an A/B test candidate for real-time e-commerce traffic, encompassing customers from the US and the UK. The model attest to a 100% successful request service rate within real-time scenarios, with median, 90th percentile, and 99th percentile (p90/p99) latencies comfortably falling below production service level agreements. Notably, these achievements are further reinforced by positive customer engagement, transactional and search page metrics, including a significant reduction in instances of search results page with low or almost zero recall. Moreover, we have also extended our efforts into fine-tuning a multilingual model, which, notably, exhibits substantial accuracy enhancements, amounti

关键词： Transformers encoder-decoder architecture Fine-Tuning Spelling Correction Knowledge Distillation BART T5 Multilingual Online Inference

来源：评论

学校读者我要写书评

暂无评论

Upsampling Matters for Road Marking Segmentation of Autonomous Driving 3rd

Upsampling Matters for Road Marking Segmentation of Autonomo...

引用

3rd IFAC Workshop pn Cyber-Physical and Human Systems (CPHS)

作者： Liu, Ye Zhang, Xi Liu, Lei Zhang, Lei Shanghai Jiao Tong Univ Sch Mech Engn Shanghai Peoples R China CSSC Beijing Peoples R China

Although autonomous driving have become applicable to the industry, the prevalent application of key techniques to the autonomous vehicles still needs to be refined. For instance, how to fast and accurately segment road markings in order to assist the next pedestrian path prediction and the creation of high-definition (HD) map respectively is useful for autonomous driving to be more practical. Current road marking segmentation mainly rely on the techniques of semantic segmentation of computer vision with encoder-decoder architecture. However, as demonstrated in this paper, the upsampling layer of convolutional neural networks with encoder-decoder architecture plays a significant role in the efficiency and accuracy of the road marking segmentation. The bilinear upsampling layer is fast due to its intrinsic simple interpolation but with less accuracy;on the contrary, the upsampling layer with offsets is relatively accurate but with more computational cost. Therefore, at least, in terms of prevalent application, efficiency, and accuracy, the upsampling layer of decoder of convolution neural networks should be paid more attention to for the next research work of autonomous driving. Copyright (C) 2020 The Authors.

关键词： Semantic Segmentation Upsampling encoder-decoder architecture Road Marking Autonomous Driving

来源：评论

学校读者我要写书评

暂无评论

SIMULTANEOUS SEGMENTATION AND CLASSIFICATION OF BIRD SONG USING CNN

SIMULTANEOUS SEGMENTATION AND CLASSIFICATION OF BIRD SONG US...

引用

IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Narasimhan, Revathy Fern, Xiaoli Z. Raich, Raviv Oregon State Univ Sch EECS Corvallis OR 97331 USA

ISBN: (纸本)9781509041176

In bioacoustics, automatic animal voice detection and recognition from audio recordings is an emerging topic for animal preservation. Our research focuses on bird bioacoustics, where the goal is to segment bird syllables from the recording and predict the bird species for the syllables. Traditional methods for this task addresses the segmentation and species prediction separately, leading to propagated errors. This work presents a new approach that performs simultaneous segmentation and classification of bird species using a Convolutional Neural Network (CNN) with encoder-decoder architecture. Experimental results on bird recordings show significant improvement compared to recent state-of-the-art methods for both segmentation and species classification.

关键词： Convolutional Neural Network encoder-decoder architecture bioacoustic species classification

来源：评论

学校读者我要写书评

暂无评论

Can We Make A More Efficient UNet for Blood Vessel Segmentation?

Can We Make A More Efficient UNet for Blood Vessel Segmentat...

引用

Conference on Applications of Machine Learning

作者： Liu, Qiong Zhong, Ziming Sengupta, Sourya Lakshminarayanan, Vasudevan Huazhong Univ Sci & Technol Dept Biomed Engn Wuhan Peoples R China Dalian Univ Technol Dept Elect Informat & Elect Engn Dalian Peoples R China Univ Waterloo Sch Optometry & Vis Sci Theoret & Expt Epistemol Lab Waterloo ON Canada Univ Waterloo Dept Syst Design Engn Waterloo ON Canada

ISBN: (纸本)9781510638297

Blood vessel segmentation is an important step in the automated diagnosis of ophthalmic disease from retinal fundus images. The UNet is a popular encoder-decoder architecture widely used in biomedical pixel-wise segmentation problems. In this paper, we analyze how the UNet can be used in a more computationally efficient way. Pre-trained weights are used to initialize the network and 3 different architectures are used to compare and analyze the efficacy of the models in terms of both computational cost and performance. Three different deep architectures (VGG16, ResNet34, DenseNet121) are discussed and their efficiencies are compared for the blood vessel segmentation task. Resnet34 architecture achieved highest sensitivity of 0.849 and accuracy and specificity of 0.961, 0.9843 with number of parameters as low as 510178 compared to normal UNet with 34525168 parameters and a sensitivity of 0.756.

关键词： image segmentation ophthalmology retina encoder-decoder architecture biomedical image processing U-Net diabetic retinopathy glaucoma

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：