检索结果-内蒙古大学图书馆

CrackF-Net: a pixel-level segmentation network for pavement crack detection

JOURNAL OF ELECTRONIC IMAGING 2023年第6期32卷 063002-063002页

作者： Luan, Shen Gao, Xingen Wang, Chen Zhang, Hongyi Chao, Fei Lin, Juqiang Huang, Junqi Jiang, Huali Lin, Feng Xiamen Univ Technol Sch Optoelect & Commun Engn Xiamen Peoples R China Xiamen Univ Sch Informat Dept Artificial Intelligence Xiamen Peoples R China

Detecting pavement cracks from images is a complex computer vision task due to their varying shapes, backgrounds, and sizes. We propose CrackF-Net, an end-to-end convolutional neural network for automatic crack detection in road images. We construct the CrackF-Net network using an encoder-decoder architecture to extract image features in convolutional blocks with residuals and fuse the multiscale convolutional features produced by the decoder. Convolutional blocks with residuals are used to capture the strong semantic features of cracks, and an adaptive filter fusion module is proposed to assist the network make a selection of filter fusion features on the channels. CrackF-Net fuses the multiscale features in decoder to improve crack detection performance. The proposed CrackF-Net is compared to other advanced crack detection methods using three public datasets. The experimental results show that CrackF-Net achieves state-of-the-art performance, which obtains F-measures of 0.866, 0.737, and 0.852 on the three datasets. (c) 2023 SPIE and IS&T

关键词： crack detection encoder-decoder noise processing attention mechanism semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

Microaneurysm detection in fundus images based on a novel end-to-end convolutional neural network

引用

BIOCYBERNETICS AND BIOMEDICAL ENGINEERING 2021年第2期41卷 589-604页

作者： Liao, Yinhan Xia, Haiying Song, Shuxiang Li, Haisheng Guangxi Normal Univ Coll Elect Engn Guilin 541004 Peoples R China

Microaneurysms are the earliest symptom of diabetic retinopathy and play an important role in the screening of diabetic retinopathy. However, because of the complex background, automatic detection microaneurysm in fundus images is a challenging task. Firstly, moti-vated by the characteristics of microaneurysm, a novel deep convolutional encoder-decoder network for microaneurysm detection is designed to locate the MAs by the differ-ences between the skip connection in the network. Then, a weighted dice loss, termed the smooth dice loss, is presented to put more focus on misclassified microaneurysms. Finally, an activation function with a long tail is used to produce an accurate probability map for MA detection. Plenty of experiments, conducted on the Retinopathy Online Challenge data-set and the e-ophtha-MA dataset, demonstrate that the proposed model achieves the com-parable performance to the existing state-of-the-art methods on microaneurysm detection with only one-hundredth the running time compared with its counterparts. The proposed method is simple and effective, guarantees the performance while shortening the test time. It indicates the potential application in the auxiliary diagnosis of diabetic retinopathy screening. (c) 2021 Nalecz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences. Published by Elsevier B.V. All rights reserved.

关键词： Deep learning Computer-aided diagnosis Diabetic retinopathy screening Microaneurysm detection encoder-decoder

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Deep Learning Models for Text Summarization on Hindi Corpus 5th

Comparative Analysis of Deep Learning Models for Text Summar...

引用

5th International Conference on Artificial Intelligence and Speech Technology, AIST 2023

作者： Sowpari, Niranjana Bansal, Poonam Sethi, Nandini Indira Gandhi Delhi Technical University for Women Kashmere Gate Delhi India

ISBN: (纸本)9783031751639

We often come across large texts for example, stories, news articles etc. Sometimes it is required to have a quick summary of the context to save our time in reading the long paragraphs. In literature we often know this process by the name of Text Summarization. Text summarization comes under a field in Data Science called as Natural Language Processing. Over the years, a lot of work towards Text Summarization has been presented on English Corpus, but not much work has been done for our Indian Languages like Hindi. Our goal for this research work is to find a model which is able to generate good Hindi summary out of Hindi texts and is efficient in terms of time and resources. To be able to achieve our goal, we have performed a comparative analysis of the Deep Learning Models for text summarization so that we can compare the models on various parameters and their results. In our paper, we have trained the models BART and T5 on the ‘Hindi Text Short Summarization’ Corpus where T5 performed better than BART and with a rouge-L (f-measure) score of 20.5. For experimentation, we have used the ‘Hindi Text Short Summarization’ Corpus available from Kaggle as not much work has been performed until now on this dataset and we wanted to learn about the essential data transformations or data pre-processing that can be done on a Hindi dataset so that our model yields us good results for the Hindi Corpus as most of times the industrial data are not very clean and understanding the data and performing data-preprocessing becomes a very crucial step. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： BART BERT Deep Learning encoder-decoder IndicBART mT5 Natural Language Processing Neural Networks T5 Transformers

来源：评论

学校读者我要写书评

暂无评论

Explicit estimation of magnitude and phase spectra in parallel for high-quality speech enhancement☆

引用

NEURAL NETWORKS 2025年 189卷 107562页

作者： Lu, Ye-Xin Ai, Yang Ling, Zhen-Hua Univ Sci & Technol China Natl Engn Res Ctr Speech & Language Informat Proc Hefei Peoples R China

Phase information has a significant impact on speech perceptual quality and intelligibility. However, existing speech enhancement methods encounter limitations in explicit phase estimation due to the non-structural nature and wrapping characteristics of the phase, leading to a bottleneck in enhanced speech quality. To overcome the above issue, in this paper, we proposed MP-SENet, a novel Speech Enhancement Network that explicitly enhances Magnitude and Phase spectra in parallel. The proposed MP-SENet comprises a Transformer-embedded encoder-decoder architecture. The encoder aims to encode the input distorted magnitude and phase spectra into time-frequency representations, which are further fed into time-frequency Transformers for alternatively capturing time and frequency dependencies. The decoder comprises a magnitude mask decoder and a phase decoder, directly enhancing magnitude and wrapped phase spectra by incorporating a magnitude masking architecture and a phase parallel estimation architecture, respectively. Multi-level loss functions explicitly defined on the magnitude spectra, wrapped phase spectra, and short-time complex spectra are adopted to jointly train the MP-SENet model. A metric discriminator is further employed to compensate for the incomplete correlation between these losses and human auditory perception. Experimental results demonstrate that our proposed MP-SENet achieves state-of-the-art performance across multiple speech enhancement tasks, including speech denoising, dereverberation, and bandwidth extension. Compared to existing phase-aware speech enhancement methods, it further mitigates the compensation effect between the magnitude and phase by explicit phase estimation, elevating the perceptual quality of enhanced speech. Remarkably, for the speech denoising task, the proposed MP-SENet yields a PESQ of 3.60 on the VoiceBank+DEMAND dataset and 3.62 on the DNS challenge dataset.

关键词： Speech enhancement encoder-decoder Magnitude prediction Phase prediction Explicit estimation

来源：评论

学校读者我要写书评

暂无评论

Pseudo dense counterfactual augmentation for aspect-based sentiment analysis

引用

NEUROCOMPUTING 2023年 561卷

作者： Ouyang, Jihong Feng, Shi Wang, Bing Yang, Zhiyao Jilin Univ Coll Comp Sci & Technol Changchun 130022 Peoples R China Jilin Univ Key Lab Symbol Computat & Knowledge Engn Minist Educ Changchun 130022 Peoples R China

Aspect-based sentiment analysis (ABSA) is a fine-grained text classification task, and the cutting-edge ABSA models have achieved outstanding performance. Unfortunately, the robustness of these ABSA models is neglected. ABSA models must face numerous challenges to be robust, and we concentrate on one of these challenges caused by negation words, such as "not'', "un-". In the actual context, these negation words intuitively result in two problems: negative sensitivity and spurious correlation. First, a negation word tends to reverse the sentiment polarity of a sentence. Meanwhile, in the ABSA datasets, most sentences containing negation words express Negative polarities, which will lead the predictive model to learn the spurious correlation between negation words and polarities. To resolve these ambiguous issues, we are inspired by causal inference and propose a novel data augmentation framework, namely Pseudo Dense Counterfactual Augmentation (PDCaug) for ABSA. Specifically, we initialize a pseudo sequence and employ a multi-head multi layer attention network to achieve counterfactual augmentation for a vanilla sentence in the hidden space. This pseudo sequence will be adversarially trained. PDCaug is a plug-and-play method for various ABSA models, so we evaluate it on discriminative models and generative prompt-based models. Our extensive experiments show that our PDCaug can significantly and consistently outperform several data augmentation methods and ABSA models.

关键词： Aspect-based sentiment analysis encoder-decoder Data augmentation

来源：评论

学校读者我要写书评

暂无评论

MMAG: Mutually Motivated Attention Gates for Simultaneous Extraction of Contextual and Spatial Information from a Monocular Image 23

MMAG: Mutually Motivated Attention Gates for Simultaneous Ex...

引用

Proceedings of the Fourteenth Indian Conference on Computer Vision, Graphics and Image Processing

作者： Aditya Singh Saloni Mohan Vandana Kushwaha G C Nandi IIIT Allahabad IN

ISBN: (纸本)9798400716256

In order to effectively interact with its environment, an agent must possess the ability to comprehend the ’what’ and the ’where.’ Two vision-based approaches, namely semantic segmentation and depth estimation, can be employed to provide this information. This paper introduces a unified model that combines these two tasks and utilizes a shared latent space. The chosen approach for the model involves an encoder-decoder architecture accompanied by a novel attention gate mechanism called MMAG, which has been proven to be highly effective. Furthermore, a common skip connection method, in conjunction with the proposed attention gate, is included to emphasize crucial features for both prediction purposes. By leveraging the complementary information within the shared representations, the model is capable of generating more accurate predictions compared to other joint-prediction models, all while utilizing fewer network parameters. To enhance performance, dilated layers are incorporated, allowing for focused attention through different receptive fields. The model’s performance has been evaluated on the NYU Depth v2 and Camvid datasets, demonstrating improved results on both tasks when compared to other state-of-the-art models. With its reduced parameter count, this model is particularly suitable for low-cost robots and has undergone successful testing for inference on the LoCoBot robot.

关键词： attention gate mechanism encoder-decoder monocular depth estimation semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

The Code Generation Method Based on Gated Attention and InterAction-LSTM 1

引用

18th Web Information Systems and Applications Conference (WISA)

作者： Wang, Yuxuan Wu, Junhua Nanjing Tech Univ Sch Comp Sci & Technol Nanjing 211816 Peoples R China

ISBN: (数字)9783030875718

ISBN: (纸本)9783030875718;9783030875701

Code generation is an important research field of software engineering, aiming to reduce development costs and improve program quality. Nowadays, more and more researchers intend to implement code generation by natural language understanding. In this paper, we propose a generation method to convert natural language descriptions to the program code based on deep learning. We use an encoder-decoder model with gated attention mechanism. Here, the decoder is an InterAction-LSTM. The gated attention combines the previous decoding cell state with source representations to improve the limitation of invariant source representations. The decoder makes the information interact each other before putting them into the gate of the LSTM. The code generation is verified on two datasets, Conala and Django. Compared with known models, our model outperforms the baselines both in Accuracy and Bleu.

关键词： Code generation encoder-decoder Gated attention InterAction-LSTM

来源：评论

学校读者我要写书评

暂无评论

A Transformer-based Radical Analysis Network for Chinese Character Recognition 25

A Transformer-based Radical Analysis Network for Chinese Cha...

引用

25th International Conference on Pattern Recognition (ICPR)

作者： Yang, Chen Wang, Qing Du, Jun Zhang, Jianshu Wu, Changjie Wang, Jiaming Univ Sci & Technol China Natl Engn Lab Speech & Language Informat Proc Hefei Anhui Peoples R China

ISBN: (纸本)9781728188089

Recently, a novel radical analysis network (RAN) has the capability of effectively recognizing unseen Chinese character classes and largely reducing the requirement of training data by treating a Chinese character as a hierarchical composition of radicals rather than a single character class. However, when dealing with more challenging issues, such as the recognition of complicated characters, low-frequency character categories, and characters in natural scenes, RAN still has a lot of room for improvement. In this paper, we explore options to further improve the structure generalization and robustness capability of RAN with the Transformer architecture, which has achieved start-of-the-art results for many sequence-to-sequence tasks. More specifically, we propose to replace the original attention module in RAN with the transformer decoder, which is named as a transformer-based radical analysis network (RTN). The experimental results show that the proposed approach can significantly outperform the RAN on both printed Chinese character database and natural scene Chinese character database. Meanwhile, further analysis proves that RTN can be better generalized to complex samples and low-frequency characters, and has better robustness in recognizing Chinese characters with different attributes.

关键词： Chinese characters Transformer network encoder-decoder Attention

来源：评论

学校读者我要写书评

暂无评论

Transformer Based End-to-End Mispronunciation Detection and Diagnosis 22

Transformer Based End-to-End Mispronunciation Detection and ...

引用

Interspeech Conference

作者： Wu, Minglin Li, Kun Leung, Wai-Kim Meng, Helen Chinese Univ Hong Kong Dept Syst Engn & Engn Management Human Comp Commun Lab Hong Kong Peoples R China SpeechX Ltd Hong Kong Peoples R China Ctr Perceptual & Interact Intelligence CPII Ltd Hong Kong Peoples R China

ISBN: (纸本)9781713836902

This paper introduces two Transformer-based architectures for Mispronunciation Detection and Diagnosis (MDD). The first Transformer architecture (T-1) is a standard setup with an encoder, a decoder, a projection part and the Cross Entropy (CE) loss. T-1 takes in Mel-Frequency Cepstral Coefficients (MFCC) as input. The second architecture (T-2) is based on wav2vec 2.0, a pretraining framework. T-2 is composed of a CNN feature encoder, several Transformer blocks capturing contextual speech representations, a projection part and the Connectionist Temporal Classification (CTC) loss. Unlike T-1, T-2 takes in raw audio data as input. Both models are trained in an end-to-end manner. Experiments are conducted on the CU-CHLOE corpus, where T-1 achieves a Phone Error Rate (PER) of 8.69% and F-measure of 77.23%;and T-2 achieves a PER of 5.97% and F-measure of 80.98 %. Both models significantly outperform the previously proposed AGPM and CNN-RNN-CTC models, with PERs at 11.1% and 12.1% respectively, and F-measures at 72.61% and 74.65 % respectively.

关键词： Mispronunciation Detection and Diagnosis (MDD) Transformer encoder-decoder wav2vec 2.0 CNN feature encoder

来源：评论

学校读者我要写书评

暂无评论

Short-Term Traffic Forecasting using LSTM-based Deep Learning Models 7

Short-Term Traffic Forecasting using LSTM-based Deep Learnin...

引用

Moratuwa Engineering Research Conference (MERCon) / 7th International Multidisciplinary Engineering Research Conference

作者： Haputhanthri, Dilantha Wijayasiri, Adeesha Univ Moratuwa Dept Comp Sci & Engn Moratuwa Sri Lanka

ISBN: (纸本)9781665437530

Accurate short-term traffic volume forecasting has become a component with growing importance in traffic management in intelligent transportation systems (ITS). A significant amount of related works on short-term traffic forecasting has been proposed based on traditional learning approaches, and deep learning-based approaches have also made significant strides in recent years. In this paper, we explore several deep learning models that are based on long-short term memory (LSTM) networks to automatically extract inherent features of traffic volume data for forecasting. A simple LSTM model, LSTM encoder-decoder model, CNN-LSTM model and a Conv-LSTM model were designed and evaluated using a real-world traffic volume dataset for multiple prediction horizons. Finally, the experimental results are analyzed, and the Conv-LSTM model produced the best performance with a MAPE of 9.03% for the prediction horizon of 15 minutes. Also, the paper discusses the behavior of the models with the traffic volume anomalies due to the Covid-19 pandemic.

关键词： CNN-LSTM Conv-LSTM encoder-decoder LSTM traffic volume forecasting

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：