scholarly journals CharTeC-Net: An Efficient and Lightweight Character-Based Convolutional Network for Text Classification

2020 ◽  
Vol 2020 ◽  
pp. 1-7 ◽  
Author(s):  
Aboubakar Nasser Samatin Njikam ◽  
Huan Zhao
Keyword(s):  
Text Classification ◽  
Building Block ◽  
Large Scale ◽  
State Of The Art ◽  
Building Blocks ◽  
Training Data ◽  
Superior Performance ◽  
Classification Problems ◽  
Computationally Efficient ◽  
Convolutional Network

This paper introduces an extremely lightweight (with just over around two hundred thousand parameters) and computationally efficient CNN architecture, named CharTeC-Net (Character-based Text Classification Network), for character-based text classification problems. This new architecture is composed of four building blocks for feature extraction. Each of these building blocks, except the last one, uses 1 × 1 pointwise convolutional layers to add more nonlinearity to the network and to increase the dimensions within each building block. In addition, shortcut connections are used in each building block to facilitate the flow of gradients over the network, but more importantly to ensure that the original signal present in the training data is shared across each building block. Experiments on eight standard large-scale text classification and sentiment analysis datasets demonstrate CharTeC-Net’s superior performance over baseline methods and yields competitive accuracy compared with state-of-the-art methods, although CharTeC-Net has only between 181,427 and 225,323 parameters and weighs less than 1 megabyte.

scholarly journals Improving Object Tracking by Added Noise and Channel Attention

Sensors ◽  
2020 ◽  
Vol 20 (13) ◽  
pp. 3780 ◽  
Author(s):  
Mustansar Fiaz ◽  
Arif Mahmood ◽  
Ki Yeol Baek ◽  
Sehar Shahzad Farooq ◽  
Soon Ki Jung
Keyword(s):  
Large Scale ◽  
Data Augmentation ◽  
Feature Fusion ◽  
State Of The Art ◽  
Computational Cost ◽  
Training Data ◽  
Superior Performance ◽  
Input Noise ◽  
Offline Learning ◽  
Benchmark Datasets

CNN-based trackers, especially those based on Siamese networks, have recently attracted considerable attention because of their relatively good performance and low computational cost. For many Siamese trackers, learning a generic object model from a large-scale dataset is still a challenging task. In the current study, we introduce input noise as regularization in the training data to improve generalization of the learned model. We propose an Input-Regularized Channel Attentional Siamese (IRCA-Siam) tracker which exhibits improved generalization compared to the current state-of-the-art trackers. In particular, we exploit offline learning by introducing additive noise for input data augmentation to mitigate the overfitting problem. We propose feature fusion from noisy and clean input channels which improves the target localization. Channel attention integrated with our framework helps finding more useful target features resulting in further performance improvement. Our proposed IRCA-Siam enhances the discrimination of the tracker/background and improves fault tolerance and generalization. An extensive experimental evaluation on six benchmark datasets including OTB2013, OTB2015, TC128, UAV123, VOT2016 and VOT2017 demonstrate superior performance of the proposed IRCA-Siam tracker compared to the 30 existing state-of-the-art trackers.

scholarly journals Multi-Margin based Decorrelation Learning for Heterogeneous Face Recognition

2019 ◽  
Author(s):  
Bing Cao ◽  
Nannan Wang ◽  
Xinbo Gao ◽  
Jie Li ◽  
Zhifeng Li
Keyword(s):  
Face Recognition ◽  
Large Scale ◽  
State Of The Art ◽  
Representation Learning ◽  
Training Data ◽  
Superior Performance ◽  
Neural Network Approach ◽  
Cross Domain ◽  
Face Images ◽  
Heterogeneous Face Recognition

Heterogeneous face recognition (HFR) refers to matching face images acquired from different domains with wide applications in security scenarios. However, HFR is still a challenging problem due to the significant cross-domain discrepancy and the lacking of sufficient training data in different domains. This paper presents a deep neural network approach namely Multi-Margin based Decorrelation Learning (MMDL) to extract decorrelation representations in a hyperspherical space for cross-domain face images. The proposed framework can be divided into two components: heterogeneous representation network and decorrelation representation learning. First, we employ a large scale of accessible visual face images to train heterogeneous representation network. The decorrelation layer projects the output of the first component into decorrelation latent subspace and obtain decorrelation representation. In addition, we design a multi-margin loss (MML), which consists of tetradmargin loss (TML) and heterogeneous angular margin loss (HAML), to constrain the proposed framework. Experimental results on two challenging heterogeneous face databases show that our approach achieves superior performance on both verification and recognition tasks, comparing with state-of-the-art methods.

scholarly journals DANNP: an efficient artificial neural network pruning tool

2017 ◽  
Vol 3 ◽  
pp. e137 ◽  
Author(s):  
Mona Alshahrani ◽  
Othman Soufan ◽  
Arturo Magana-Mora ◽  
Vladimir B. Bajic
Keyword(s):  
Neural Network ◽  
State Of The Art ◽  
Model Performance ◽  
Training Data ◽  
Classification Problems ◽  
Link Type ◽  
On Line ◽  
Pruning Algorithms ◽  
Artificial Neural ◽  
The Impact

Background Artificial neural networks (ANNs) are a robust class of machine learning models and are a frequent choice for solving classification problems. However, determining the structure of the ANNs is not trivial as a large number of weights (connection links) may lead to overfitting the training data. Although several ANN pruning algorithms have been proposed for the simplification of ANNs, these algorithms are not able to efficiently cope with intricate ANN structures required for complex classification problems. Methods We developed DANNP, a web-based tool, that implements parallelized versions of several ANN pruning algorithms. The DANNP tool uses a modified version of the Fast Compressed Neural Network software implemented in C++ to considerably enhance the running time of the ANN pruning algorithms we implemented. In addition to the performance evaluation of the pruned ANNs, we systematically compared the set of features that remained in the pruned ANN with those obtained by different state-of-the-art feature selection (FS) methods. Results Although the ANN pruning algorithms are not entirely parallelizable, DANNP was able to speed up the ANN pruning up to eight times on a 32-core machine, compared to the serial implementations. To assess the impact of the ANN pruning by DANNP tool, we used 16 datasets from different domains. In eight out of the 16 datasets, DANNP significantly reduced the number of weights by 70%–99%, while maintaining a competitive or better model performance compared to the unpruned ANN. Finally, we used a naïve Bayes classifier derived with the features selected as a byproduct of the ANN pruning and demonstrated that its accuracy is comparable to those obtained by the classifiers trained with the features selected by several state-of-the-art FS methods. The FS ranking methodology proposed in this study allows the users to identify the most discriminant features of the problem at hand. To the best of our knowledge, DANNP (publicly available at www.cbrc.kaust.edu.sa/dannp) is the only available and on-line accessible tool that provides multiple parallelized ANN pruning options. Datasets and DANNP code can be obtained at www.cbrc.kaust.edu.sa/dannp/data.php and https://doi.org/10.5281/zenodo.1001086.

scholarly journals Attending to Entities for Better Text Understanding

2020 ◽  
Vol 34 (05) ◽  
pp. 7554-7561
Author(s):  
Pengxiang Cheng ◽  
Katrin Erk
Keyword(s):  
Large Scale ◽  
Human Performance ◽  
State Of The Art ◽  
Syntactic Structure ◽  
Semantic Knowledge ◽  
Training Data ◽  
Language Models ◽  
Long Distance ◽  
Future Directions ◽  
Text Understanding

Recent progress in NLP witnessed the development of large-scale pre-trained language models (GPT, BERT, XLNet, etc.) based on Transformer (Vaswani et al. 2017), and in a range of end tasks, such models have achieved state-of-the-art results, approaching human performance. This clearly demonstrates the power of the stacked self-attention architecture when paired with a sufficient number of layers and a large amount of pre-training data. However, on tasks that require complex and long-distance reasoning where surface-level cues are not enough, there is still a large gap between the pre-trained models and human performance. Strubell et al. (2018) recently showed that it is possible to inject knowledge of syntactic structure into a model through supervised self-attention. We conjecture that a similar injection of semantic knowledge, in particular, coreference information, into an existing model would improve performance on such complex problems. On the LAMBADA (Paperno et al. 2016) task, we show that a model trained from scratch with coreference as auxiliary supervision for self-attention outperforms the largest GPT-2 model, setting the new state-of-the-art, while only containing a tiny fraction of parameters compared to GPT-2. We also conduct a thorough analysis of different variants of model architectures and supervision configurations, suggesting future directions on applying similar techniques to other problems.

scholarly journals Exemplar Guided Neural Dialogue Generation

2020 ◽  
Author(s):  
Hengyi Cai ◽  
Hongshen Chen ◽  
Yonghao Song ◽  
Xiaofang Zhao ◽  
Dawei Yin
Keyword(s):  
Large Scale ◽  
State Of The Art ◽  
Training Data ◽  
Small Subset ◽  
Generation Model ◽  
Retrieval Model ◽  
Training Set ◽  
Dialogue Model ◽  
Quantitative Metrics ◽  
The Given

Humans benefit from previous experiences when taking actions. Similarly, related examples from the training data also provide exemplary information for neural dialogue models when responding to a given input message. However, effectively fusing such exemplary information into dialogue generation is non-trivial: useful exemplars are required to be not only literally-similar, but also topic-related with the given context. Noisy exemplars impair the neural dialogue models understanding the conversation topics and even corrupt the response generation. To address the issues, we propose an exemplar guided neural dialogue generation model where exemplar responses are retrieved in terms of both the text similarity and the topic proximity through a two-stage exemplar retrieval model. In the first stage, a small subset of conversations is retrieved from a training set given a dialogue context. These candidate exemplars are then finely ranked regarding the topical proximity to choose the best-matched exemplar response. To further induce the neural dialogue generation model consulting the exemplar response and the conversation topics more faithfully, we introduce a multi-source sampling mechanism to provide the dialogue model with both local exemplary semantics and global topical guidance during decoding. Empirical evaluations on a large-scale conversation dataset show that the proposed approach significantly outperforms the state-of-the-art in terms of both the quantitative metrics and human evaluations.

scholarly journals AI-Sketcher : A Deep Generative Model for Producing High-Quality Sketches

2019 ◽  
Vol 33 ◽  
pp. 2564-2571 ◽  
Author(s):  
Nan Cao ◽  
Xin Yan ◽  
Yang Shi ◽  
Chaoran Chen
Keyword(s):  
Artificial Intelligence ◽  
Large Scale ◽  
State Of The Art ◽  
Positional Information ◽  
Generative Model ◽  
Training Data ◽  
Creative Design ◽  
High Quality ◽  
User Input ◽  
Variational Autoencoder

Sketch drawings play an important role in assisting humans in communication and creative design since ancient period. This situation has motivated the development of artificial intelligence (AI) techniques for automatically generating sketches based on user input. Sketch-RNN, a sequence-to-sequence variational autoencoder (VAE) model, was developed for this purpose and known as a state-of-the-art technique. However, it suffers from limitations, including the generation of lowquality results and its incapability to support multi-class generations. To address these issues, we introduced AI-Sketcher, a deep generative model for generating high-quality multiclass sketches. Our model improves drawing quality by employing a CNN-based autoencoder to capture the positional information of each stroke at the pixel level. It also introduces an influence layer to more precisely guide the generation of each stroke by directly referring to the training data. To support multi-class sketch generation, we provided a conditional vector that can help differentiate sketches under various classes. The proposed technique was evaluated based on two large-scale sketch datasets, and results demonstrated its power in generating high-quality sketches.

scholarly journals Visual-Semantic Graph Reasoning for Pedestrian Attribute Recognition

2019 ◽  
Vol 33 ◽  
pp. 8634-8641 ◽  
Author(s):  
Qiaozhe Li ◽  
Xin Zhao ◽  
Ran He ◽  
Kaiqi Huang
Keyword(s):  
Large Scale ◽  
State Of The Art ◽  
Relational Learning ◽  
Spatial Relations ◽  
Semantic Relations ◽  
Prediction Problem ◽  
Convolutional Network ◽  
Semantic Graph ◽  
Spatial Graph ◽  
Attribute Recognition

Pedestrian attribute recognition in surveillance is a challenging task due to poor image quality, significant appearance variations and diverse spatial distribution of different attributes. This paper treats pedestrian attribute recognition as a sequential attribute prediction problem and proposes a novel visual-semantic graph reasoning framework to address this problem. Our framework contains a spatial graph and a directed semantic graph. By performing reasoning using the Graph Convolutional Network (GCN), one graph captures spatial relations between regions and the other learns potential semantic relations between attributes. An end-to-end architecture is presented to perform mutual embedding between these two graphs to guide the relational learning for each other. We verify the proposed framework on three large scale pedestrian attribute datasets including PETA, RAP, and PA100k. Experiments show superiority of the proposed method over state-of-the-art methods and effectiveness of our joint GCN structures for sequential attribute prediction.

scholarly journals A New Ensemble Learning Framework for 3D Biomedical Image Segmentation

2019 ◽  
Vol 33 ◽  
pp. 5909-5916 ◽  
Author(s):  
Hao Zheng ◽  
Yizhe Zhang ◽  
Lin Yang ◽  
Peixian Liang ◽  
Zhuo Zhao ◽  
...  
Keyword(s):  
Image Segmentation ◽  
Ensemble Learning ◽  
State Of The Art ◽  
3D Models ◽  
Superior Performance ◽  
3D Image ◽  
Convolutional Network ◽  
Biomedical Image ◽  
Learning Framework ◽  
2D And 3D

3D image segmentation plays an important role in biomedical image analysis. Many 2D and 3D deep learning models have achieved state-of-the-art segmentation performance on 3D biomedical image datasets. Yet, 2D and 3D models have their own strengths and weaknesses, and by unifying them together, one may be able to achieve more accurate results. In this paper, we propose a new ensemble learning framework for 3D biomedical image segmentation that combines the merits of 2D and 3D models. First, we develop a fully convolutional network based meta-learner to learn how to improve the results from 2D and 3D models (base-learners). Then, to minimize over-fitting for our sophisticated meta-learner, we devise a new training method that uses the results of the baselearners as multiple versions of “ground truths”. Furthermore, since our new meta-learner training scheme does not depend on manual annotation, it can utilize abundant unlabeled 3D image data to further improve the model. Extensive experiments on two public datasets (the HVSMR 2016 Challenge dataset and the mouse piriform cortex dataset) show that our approach is effective under fully-supervised, semisupervised, and transductive settings, and attains superior performance over state-of-the-art image segmentation methods.

scholarly journals Zero-Shot Ingredient Recognition by Multi-Relational Graph Convolutional Network

2020 ◽  
Vol 34 (07) ◽  
pp. 10542-10550 ◽  
Author(s):  
Jingjing Chen ◽  
Liangming Pan ◽  
Zhipeng Wei ◽  
Xiang Wang ◽  
Chong-Wah Ngo ◽  
...  
Keyword(s):  
Dietary Assessment ◽  
Training Data ◽  
Superior Performance ◽  
Convolutional Network ◽  
Food Ingredients ◽  
The Core ◽  
Training Samples ◽  
Robust Recognition ◽  
The Common ◽  
Shed Light

Recognizing ingredients for a given dish image is at the core of automatic dietary assessment, attracting increasing attention from both industry and academia. Nevertheless, the task is challenging due to the difficulty of collecting and labeling sufficient training data. On one hand, there are hundred thousands of food ingredients in the world, ranging from the common to rare. Collecting training samples for all of the ingredient categories is difficult. On the other hand, as the ingredient appearances exhibit huge visual variance during the food preparation, it requires to collect the training samples under different cooking and cutting methods for robust recognition. Since obtaining sufficient fully annotated training data is not easy, a more practical way of scaling up the recognition is to develop models that are capable of recognizing unseen ingredients. Therefore, in this paper, we target the problem of ingredient recognition with zero training samples. More specifically, we introduce multi-relational GCN (graph convolutional network) that integrates ingredient hierarchy, attribute as well as co-occurrence for zero-shot ingredient recognition. Extensive experiments on both Chinese and Japanese food datasets are performed to demonstrate the superior performance of multi-relational GCN and shed light on zero-shot ingredients recognition.

scholarly journals Efficient processing of GRU based on word embedding for text classification

2019 ◽  
Vol 3 (4) ◽  
Author(s):  
Muhammad Zulqarnain ◽  
Rozaida Ghazali ◽  
Muhammad Ghulam Ghouse ◽  
Muhammad Faheem Mushtaq
Keyword(s):  
Language Processing ◽  
Text Classification ◽  
Classification Performance ◽  
Word Embedding ◽  
Training Data ◽  
Superior Performance ◽  
Sequential Data ◽  
Online Data ◽  
Benchmark Datasets ◽  
Recurrent Architecture

Text classification has become very serious problem for big organization to manage the large amount of online data and has been extensively applied in the tasks of Natural Language Processing (NLP). Text classification can support users to excellently manage and exploit meaningful information require to be classified into various categories for further use. In order to best classify texts, our research efforts to develop a deep learning approach which obtains superior performance in text classification than other RNNs approaches. However, the main problem in text classification is how to enhance the classification accuracy and the sparsity of the data semantics sensitivity to context often hinders the classification performance of texts. In order to overcome the weakness, in this paper we proposed unified structure to investigate the effects of word embedding and Gated Recurrent Unit (GRU) for text classification on two benchmark datasets included (Google snippets and TREC). GRU is a well-known type of recurrent neural network (RNN), which is ability of computing sequential data over its recurrent architecture. Experimentally, the semantically connected words are commonly near to each other in embedding spaces. First, words in posts are changed into vectors via word embedding technique. Then, the words sequential in sentences are fed to GRU to extract the contextual semantics between words. The experimental results showed that proposed GRU model can effectively learn the word usage in context of texts provided training data. The quantity and quality of training data significantly affected the performance. We evaluated the performance of proposed approach with traditional recurrent approaches, RNN, MV-RNN and LSTM, the proposed approach is obtained better results on two benchmark datasets in the term of accuracy and error rate.

Sign in / Sign up

Export Citation Format

Share Document