scholarly journals Domain Agnostic Real-Valued Specificity Prediction

2019 ◽  
Vol 33 ◽  
pp. 6610-6617 ◽  
Author(s):  
Wei-Jen Ko ◽  
Greg Durrett ◽  
Junyi Jessy Li
Keyword(s):  
Domain Adaptation ◽  
State Of The Art ◽  
Mean Absolute Error ◽  
Absolute Error ◽  
Error Reduction ◽  
Level Of Detail ◽  
Reference Distribution ◽  
Unsupervised Domain Adaptation ◽  
Current State ◽  
Prediction Systems

Sentence specificity quantifies the level of detail in a sentence, characterizing the organization of information in discourse. While this information is useful for many downstream applications, specificity prediction systems predict very coarse labels (binary or ternary) and are trained on and tailored toward specific domains (e.g., news). The goal of this work is to generalize specificity prediction to domains where no labeled data is available and output more nuanced realvalued specificity ratings.We present an unsupervised domain adaptation system for sentence specificity prediction, specifically designed to output real-valued estimates from binary training labels. To calibrate the values of these predictions appropriately, we regularize the posterior distribution of the labels towards a reference distribution. We show that our framework generalizes well to three different domains with 50%-68% mean absolute error reduction than the current state-of-the-art system trained for news sentence specificity. We also demonstrate the potential of our work in improving the quality and informativeness of dialogue generation systems.

scholarly journals Distributional Correspondence Indexing for Cross-Lingual and Cross-Domain Sentiment Classification (Extended Abstract)

2018 ◽  
Author(s):  
Alejandro Moreo Fernández ◽  
Andrea Esuli ◽  
Fabrizio Sebastiani
Keyword(s):  
Domain Adaptation ◽  
State Of The Art ◽  
Sentiment Classification ◽  
Training Data ◽  
Target Domain ◽  
Source Domain ◽  
Machine Learning Methods ◽  
Cross Domain ◽  
Current State ◽  
Cross Lingual

Domain Adaptation (DA) techniques aim at enabling machine learning methods learn effective classifiers for a “target” domain when the only available training data belongs to a different “source” domain. In this extended abstract, we briefly describe our new DA method called Distributional Correspondence Indexing (DCI) for sentiment classification. DCI derives term representations in a vector space common to both domains where each dimension reflects its distributional correspondence to a pivot, i.e., to a highly predictive term that behaves similarly across domains. The experiments we have conducted show that DCI obtains better performance than current state-of-the-art techniques for cross-lingual and cross-domain sentiment classification.

scholarly journals Hajj pilgrimage video analytics using CNN

2021 ◽  
Vol 10 (5) ◽  
pp. 2598-2606
Author(s):  
Md Roman Bhuiyan ◽  
Junaidi Abdullah ◽  
Noramiza Hashim ◽  
Fahmid Al Farid ◽  
Mohd Ali Samsudin ◽  
...  
Keyword(s):  
Small Area ◽  
State Of The Art ◽  
Mean Absolute Error ◽  
Traditional Approach ◽  
Absolute Error ◽  
Video Analytics ◽  
Crowd Analysis ◽  
Special Event ◽  
Density Map ◽  
The Mean

This paper advances video analytics with a focus on crowd analysis for Hajj and Umrah pilgrimages. In recent years, there has been an increased interest in the advancement of video analytics and visible surveillance to improve the safety and security of pilgrims during their stay in Makkah. It is mainly because Hajj is an entirely special event that involve hundreds of thousands of people being clustered in a small area. This paper proposed a convolutional neural network (CNN) system for performing multitude analysis, in particular for crowd counting. In addition, it also proposes a new algorithm for applications in Hajj and Umrah. We create a new dataset based on the Hajj pilgrimage scenario in order to address this challenge. The proposed algorithm outperforms the state-of-the-art approach with a significant reduction of the mean absolute error (MAE) result: 240.0 (177.5 improvement) and the mean square error (MSE) result: 260.5 (280.1 improvement) when used with the latest dataset (HAJJ-Crowd dataset). We present density map and prediction of traditional approach in our novel HAJJ-crowd dataset for the purpose of evaluation with our proposed method.

scholarly journals Adversarial Training Based Multi-Source Unsupervised Domain Adaptation for Sentiment Analysis

2020 ◽  
Vol 34 (05) ◽  
pp. 7618-7625
Author(s):  
Yong Dai ◽  
Jian Liu ◽  
Xiancong Ren ◽  
Zenglin Xu
Keyword(s):  
Sentiment Analysis ◽  
Domain Adaptation ◽  
State Of The Art ◽  
Weak Assumption ◽  
Target Domain ◽  
Smoothness Assumption ◽  
Unsupervised Domain Adaptation ◽  
Good Target ◽  
Adversarial Training ◽  
Learning Frameworks

Multi-source unsupervised domain adaptation (MS-UDA) for sentiment analysis (SA) aims to leverage useful information in multiple source domains to help do SA in an unlabeled target domain that has no supervised information. Existing algorithms of MS-UDA either only exploit the shared features, i.e., the domain-invariant information, or based on some weak assumption in NLP, e.g., smoothness assumption. To avoid these problems, we propose two transfer learning frameworks based on the multi-source domain adaptation methodology for SA by combining the source hypotheses to derive a good target hypothesis. The key feature of the first framework is a novel Weighting Scheme based Unsupervised Domain Adaptation framework ((WS-UDA), which combine the source classifiers to acquire pseudo labels for target instances directly. While the second framework is a Two-Stage Training based Unsupervised Domain Adaptation framework (2ST-UDA), which further exploits these pseudo labels to train a target private extractor. Importantly, the weights assigned to each source classifier are based on the relations between target instances and source domains, which measured by a discriminator through the adversarial training. Furthermore, through the same discriminator, we also fulfill the separation of shared features and private features.Experimental results on two SA datasets demonstrate the promising performance of our frameworks, which outperforms unsupervised state-of-the-art competitors.

scholarly journals MH-MetroNet—A Multi-Head CNN for Passenger-Crowd Attendance Estimation

2020 ◽  
Vol 6 (7) ◽  
pp. 62
Author(s):  
Pier Luigi Mazzeo ◽  
Riccardo Contino ◽  
Paolo Spagnolo ◽  
Cosimo Distante ◽  
Ettore Stella ◽  
...  
Keyword(s):  
Network Architecture ◽  
Network Performance ◽  
State Of The Art ◽  
Mean Absolute Error ◽  
Absolute Error ◽  
Input Image ◽  
Mean Square ◽  
Metro Station ◽  
Crowd Counting ◽  
Density Map

Knowing an accurate passengers attendance estimation on each metro car contributes to the safely coordination and sorting the crowd-passenger in each metro station. In this work we propose a multi-head Convolutional Neural Network (CNN) architecture trained to infer an estimation of passenger attendance in a metro car. The proposed network architecture consists of two main parts: a convolutional backbone, which extracts features over the whole input image, and a multi-head layers able to estimate a density map, needed to predict the number of people within the crowd image. The network performance is first evaluated on publicly available crowd counting datasets, including the ShanghaiTech part_A, ShanghaiTech part_B and UCF_CC_50, and then trained and tested on our dataset acquired in subway cars in Italy. In both cases a comparison is made against the most relevant and latest state of the art crowd counting architectures, showing that our proposed MH-MetroNet architecture outperforms in terms of Mean Absolute Error (MAE) and Mean Square Error (MSE) and passenger-crowd people number prediction.

scholarly journals Threshold-Based Hierarchical Clustering for Person Re-Identification

Entropy ◽  
2021 ◽  
Vol 23 (5) ◽  
pp. 522
Author(s):  
Minhui Hu ◽  
Kaiwei Zeng ◽  
Yaohua Wang ◽  
Yang Guo
Keyword(s):  
Hierarchical Clustering ◽  
Domain Adaptation ◽  
State Of The Art ◽  
Fine Tuning ◽  
Single Sample ◽  
Clustering Methods ◽  
Clustering Method ◽  
Cluster Number ◽  
Unsupervised Domain Adaptation ◽  
And Training

Unsupervised domain adaptation is a challenging task in person re-identification (re-ID). Recently, cluster-based methods achieve good performance; clustering and training are two important phases in these methods. For clustering, one major issue of existing methods is that they do not fully exploit the information in outliers by either discarding outliers in clusters or simply merging outliers. For training, existing methods only use source features for pretraining and target features for fine-tuning and do not make full use of all valuable information in source datasets and target datasets. To solve these problems, we propose a Threshold-based Hierarchical clustering method with Contrastive loss (THC). There are two features of THC: (1) it regards outliers as single-sample clusters to participate in training. It well preserves the information in outliers without setting cluster number and combines advantages of existing clustering methods; (2) it uses contrastive loss to make full use of all valuable information, including source-class centroids, target-cluster centroids and single-sample clusters, thus achieving better performance. We conduct extensive experiments on Market-1501, DukeMTMC-reID and MSMT17. Results show our method achieves state of the art.

scholarly journals Distributional Correspondence Indexing for Cross-Lingual and Cross-Domain Sentiment Classification.

2016 ◽  
Vol 55 ◽  
pp. 131-163 ◽  
Author(s):  
Alejandro Moreo Fernández ◽  
Andrea Esuli ◽  
Fabrizio Sebastiani
Keyword(s):  
Domain Adaptation ◽  
State Of The Art ◽  
Computational Cost ◽  
Sentiment Classification ◽  
Training Data ◽  
Target Domain ◽  
Machine Learning Methods ◽  
Cross Domain ◽  
Current State ◽  
Cross Lingual

Domain Adaptation (DA) techniques aim at enabling machine learning methods learn effective classifiers for a "target'' domain when the only available training data belongs to a different "source'' domain. In this paper we present the Distributional Correspondence Indexing (DCI) method for domain adaptation in sentiment classification. DCI derives term representations in a vector space common to both domains where each dimension reflects its distributional correspondence to a pivot, i.e., to a highly predictive term that behaves similarly across domains. Term correspondence is quantified by means of a distributional correspondence function (DCF). We propose a number of efficient DCFs that are motivated by the distributional hypothesis, i.e., the hypothesis according to which terms with similar meaning tend to have similar distributions in text. Experiments show that DCI obtains better performance than current state-of-the-art techniques for cross-lingual and cross-domain sentiment classification. DCI also brings about a significantly reduced computational cost, and requires a smaller amount of human intervention. As a final contribution, we discuss a more challenging formulation of the domain adaptation problem, in which both the cross-domain and cross-lingual dimensions are tackled simultaneously.

scholarly journals Bidirectional Adversarial Training for Semi-Supervised Domain Adaptation

2020 ◽  
Author(s):  
Pin Jiang ◽  
Aming Wu ◽  
Yahong Han ◽  
Yunfeng Shao ◽  
Meiyu Qi ◽  
...  
Keyword(s):  
Additional Data ◽  
Domain Adaptation ◽  
State Of The Art ◽  
Powerful Method ◽  
Target Domain ◽  
Unsupervised Domain Adaptation ◽  
Benchmark Datasets ◽  
Adversarial Examples ◽  
Adversarial Training ◽  
Effective Use

Semi-supervised domain adaptation (SSDA) is a novel branch of machine learning that scarce labeled target examples are available, compared with unsupervised domain adaptation. To make effective use of these additional data so as to bridge the domain gap, one possible way is to generate adversarial examples, which are images with additional perturbations, between the two domains and fill the domain gap. Adversarial training has been proven to be a powerful method for this purpose. However, the traditional adversarial training adds noises in arbitrary directions, which is inefficient to migrate between domains, or generate directional noises from the source to target domain and reverse. In this work, we devise a general bidirectional adversarial training method and employ gradient to guide adversarial examples across the domain gap, i.e., the Adaptive Adversarial Training (AAT) for source to target domain and Entropy-penalized Virtual Adversarial Training (E-VAT) for target to source domain. Particularly, we devise a Bidirectional Adversarial Training (BiAT) network to perform diverse adversarial trainings jointly. We evaluate the effectiveness of BiAT on three benchmark datasets and experimental results demonstrate the proposed method achieves the state-of-the-art.

Big Data Analytics for Train Delay Prediction

2018 ◽  
pp. 320-348 ◽  
Author(s):  
Emanuele Fumeo ◽  
Luca Oneto ◽  
Giorgio Clerico ◽  
Renzo Canepa ◽  
Federico Papa ◽  
...  
Keyword(s):  
Big Data ◽  
Large Scale ◽  
Learning Algorithm ◽  
State Of The Art ◽  
Fast Learning ◽  
Current State ◽  
Big Data Technologies ◽  
Large Scale Data Processing ◽  
Prediction Systems ◽  
Delay Prediction

Current Train Delay Prediction Systems (TDPSs) do not take advantage of state-of-the-art tools and techniques for extracting useful insights from large amounts of historical data collected by the railway information systems. Instead, these systems rely on static rules, based on classical univariate statistic, built by experts of the railway infrastructure. The purpose of this book chapter is to build a data-driven TDPS for large-scale railway networks, which exploits the most recent big data technologies, learning algorithms, and statistical tools. In particular, we propose a fast learning algorithm for Shallow and Deep Extreme Learning Machines that fully exploits the recent in-memory large-scale data processing technologies for predicting train delays. Proposal has been compared with the current state-of-the-art TDPSs. Results on real world data coming from the Italian railway network show that our proposal is able to improve over the current state-of-the-art TDPSs.

Automatic Age Estimation Based on LBP and GLCM Features Using SVM

2017 ◽  
Vol 7 (11) ◽  
pp. 186
Author(s):  
VENKATARAO RAMPAY
Keyword(s):  
Age Estimation ◽  
Local Binary Pattern ◽  
State Of The Art ◽  
Mean Absolute Error ◽  
Absolute Error ◽  
Support Vector ◽  
Facial Features ◽  
State Of Mind ◽  
Occurrence Matrix ◽  
The Mind

Face is generally considered as the reference frame of mind. Therefore, to estimate the feeling of the mind, many authors have considered the emotions from the facial expressions into consideration to identify the state of mind of an individual. Hence in this article we proposed a methodology for automatic age estimation based on Local Binary Pattern (LBP) and Grey Level Co- Occurrence Matrix (GLCM). The facial features are extracted using LBP and GLCM and these features are given as input’s to the Support Vector Machine (SVM) for age estimation. The experimentation on proposed method is carried out using FG-NET database and Mean Absolute Error (MAE) is calculated to compare the proposed method with state-of-the-art algorithms. Finally, the proposed methodology demonstrates the classification accuracy above 88%. 

scholarly journals An Adversarial Perturbation Oriented Domain Adaptation Approach for Semantic Segmentation

2020 ◽  
Vol 34 (07) ◽  
pp. 12613-12620 ◽  
Author(s):  
Jihan Yang ◽  
Ruijia Xu ◽  
Ruiyu Li ◽  
Xiaojuan Qi ◽  
Xiaoyong Shen ◽  
...  
Keyword(s):  
Marginal Distribution ◽  
Domain Adaptation ◽  
State Of The Art ◽  
Feature Space ◽  
Semantic Segmentation ◽  
The State ◽  
Object Size ◽  
Feature Maps ◽  
Feature Representations ◽  
Unsupervised Domain Adaptation

We focus on Unsupervised Domain Adaptation (UDA) for the task of semantic segmentation. Recently, adversarial alignment has been widely adopted to match the marginal distribution of feature representations across two domains globally. However, this strategy fails in adapting the representations of the tail classes or small objects for semantic segmentation since the alignment objective is dominated by head categories or large objects. In contrast to adversarial alignment, we propose to explicitly train a domain-invariant classifier by generating and defensing against pointwise feature space adversarial perturbations. Specifically, we firstly perturb the intermediate feature maps with several attack objectives (i.e., discriminator and classifier) on each individual position for both domains, and then the classifier is trained to be invariant to the perturbations. By perturbing each position individually, our model treats each location evenly regardless of the category or object size and thus circumvents the aforementioned issue. Moreover, the domain gap in feature space is reduced by extrapolating source and target perturbed features towards each other with attack on the domain discriminator. Our approach achieves the state-of-the-art performance on two challenging domain adaptation tasks for semantic segmentation: GTA5 → Cityscapes and SYNTHIA → Cityscapes.

Sign in / Sign up

Export Citation Format

Share Document