PyTorchKR Papers

최신 논문

총 12,350편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1505.03085

Indonesian Social Media Sentiment Analysis With Sarcasm Detection

Sarcasm is considered one of the most difficult problem in sentiment analysis. In our ob-servation on Indonesian social media, for cer-tain topics, people tend to criticize something using sarcasm. Here, we proposed two additional features to detect sarcasm after a common sentiment analysis is conducted. The features are the negativity information and the number of interjection words. We also employed translated SentiWordNet in the sentiment classification. All the classifications were conducted with machine learning algorithms. The experimental results showed that the additional features are quite effective in the sarcasm detection.

arXiv:1505.03084

A Survey of Arabic Dialogues Understanding for Spontaneous Dialogues and Instant Message

Building dialogues systems interaction has recently gained considerable attention, but most of the resources and systems built so far are tailored to English and other Indo-European languages. The need for designing systems for other languages is increasing such as Arabic language. For this reasons, there are more interest for Arabic dialogue acts classification task because it a key player in Arabic language understanding to building this systems. This paper surveys different techniques for dialogue acts classification for Arabic. We describe the main existing techniques for utterances segmentations and classification, annotation schemas, and test corpora for Arabic dialogues understanding that have introduced in the literature

arXiv:1505.02982

Automatic Script Identification in the Wild

With the rapid increase of transnational communication and cooperation, people frequently encounter multilingual scenarios in various situations. In this paper, we are concerned with a relatively new problem: script identification at word or line levels in natural scenes. A large-scale dataset with a great quantity of natural images and 10 types of widely used languages is constructed and released. In allusion to the challenges in script identification in real-world scenarios, a deep learning based algorithm is proposed. The experiments on the proposed dataset demonstrate that our algorithm achieves superior performance, compared with conventional image classification methods, such as the original CNN architecture and LLC.

arXiv:1505.02496

Training Deeper Convolutional Networks with Deep Supervision

One of the most promising ways of improving the performance of deep convolutional neural networks is by increasing the number of convolutional layers. However, adding layers makes training more difficult and computationally expensive. In order to train deeper networks, we propose to add auxiliary supervision branches after certain intermediate layers during training. We formulate a simple rule of thumb to determine where these branches should be added. The resulting deeply supervised structure makes the training much easier and also produces better classification results on ImageNet and the recently released, larger MIT Places dataset

arXiv:1505.02377

Bounded-Distortion Metric Learning

Metric learning aims to embed one metric space into another to benefit tasks like classification and clustering. Although a greatly distorted metric space has a high degree of freedom to fit training data, it is prone to overfitting and numerical inaccuracy. This paper presents {\it bounded-distortion metric learning} (BDML), a new metric learning framework which amounts to finding an optimal Mahalanobis metric space with a bounded-distortion constraint. An efficient solver based on the multiplicative weights update method is proposed. Moreover, we generalize BDML to pseudo-metric learning and devise the semidefinite relaxation and a randomized algorithm to approximately solve it. We further provide theoretical analysis to show that distortion is a key ingredient for stability and generalization ability of our BDML algorithm. Extensive experiments on several benchmark datasets yield promising results.

arXiv:1505.02269

Subset Feature Learning for Fine-Grained Category Classification

Fine-grained categorisation has been a challenging problem due to small inter-class variation, large intra-class variation and low number of training images. We propose a learning system which first clusters visually similar classes and then learns deep convolutional neural network features specific to each subset. Experiments on the popular fine-grained Caltech-UCSD bird dataset show that the proposed method outperforms recent fine-grained categorisation methods under the most difficult setting: no bounding boxes are presented at test time. It achieves a mean accuracy of 77.5%, compared to the previous best performance of 73.2%. We also show that progressive transfer learning allows us to first learn domain-generic features (for bird classification) which can then be adapted to specific set of bird classes, yielding improvements in accuracy.

arXiv:1505.02251

Probabilistic Cascading for Large Scale Hierarchical Classification

Hierarchies are frequently used for the organization of objects. Given a hierarchy of classes, two main approaches are used, to automatically classify new instances: flat classification and cascade classification. Flat classification ignores the hierarchy, while cascade classification greedily traverses the hierarchy from the root to the predicted leaf. In this paper we propose a new approach, which extends cascade classification to predict the right leaf by estimating the probability of each root-to-leaf path. We provide experimental results which indicate that, using the same classification algorithm, one can achieve better results with our approach, compared to the traditional flat and cascade classifications.

arXiv:1505.01802

Optimal Decision-Theoretic Classification Using Non-Decomposable Performance Metrics

We provide a general theoretical analysis of expected out-of-sample utility, also referred to as decision-theoretic classification, for non-decomposable binary classification metrics such as F-measure and Jaccard coefficient. Our key result is that the expected out-of-sample utility for many performance metrics is provably optimized by a classifier which is equivalent to a signed thresholding of the conditional probability of the positive class. Our analysis bridges a gap in the literature on binary classification, revealed in light of recent results for non-decomposable metrics in population utility maximization style classification. Our results identify checkable properties of a performance metric which are sufficient to guarantee a probability ranking principle. We propose consistent estimators for optimal expected out-of-sample classification. As a consequence of the probability ranking principle, computational requirements can be reduced from exponential to cubic complexity in the general case, and further reduced to quadratic complexity in special cases. We provide empirical results on simulated and benchmark datasets evaluating the performance of the proposed algorithms for decision-theoretic classification and comparing them to baseline and state-of-the-art methods in population utility maximization for non-decomposable metrics.

arXiv:1504.05457

Graphlet-based lazy associative graph classification

The paper addresses the graph classification problem and introduces a modification of the lazy associative classification method to efficiently handle intersections of graphs. Graph intersections are approximated with all common subgraphs up to a fixed size similarly to what is done with graphlet kernels. We explain the idea of the algorithm with a toy example and describe our experiments with a predictive toxicology dataset.

arXiv:1503.04144

Exploiting Image-trained CNN Architectures for Unconstrained Video Classification

We conduct an in-depth exploration of different strategies for doing event detection in videos using convolutional neural networks (CNNs) trained for image classification. We study different ways of performing spatial and temporal pooling, feature normalization, choice of CNN layers as well as choice of classifiers. Making judicious choices along these dimensions led to a very significant increase in performance over more naive approaches that have been used till now. We evaluate our approach on the challenging TRECVID MED'14 dataset with two popular CNN architectures pretrained on ImageNet. On this MED'14 dataset, our methods, based entirely on image-trained CNN features, can outperform several state-of-the-art non-CNN models. Our proposed late fusion of CNN- and motion-based features can further increase the mean average precision (mAP) on MED'14 from 34.95% to 38.74%. The fusion approach achieves the state-of-the-art classification performance on the challenging UCF-101 dataset.

arXiv:1503.00269

Contrastive Pessimistic Likelihood Estimation for Semi-Supervised Classification

Improvement guarantees for semi-supervised classifiers can currently only be given under restrictive conditions on the data. We propose a general way to perform semi-supervised parameter estimation for likelihood-based classifiers for which, on the full training set, the estimates are never worse than the supervised solution in terms of the log-likelihood. We argue, moreover, that we may expect these solutions to really improve upon the supervised classifier in particular cases. In a worked-out example for LDA, we take it one step further and essentially prove that its semi-supervised version is strictly better than its supervised counterpart. The two new concepts that form the core of our estimation principle are contrast and pessimism. The former refers to the fact that our objective function takes the supervised estimates into account, enabling the semi-supervised solution to explicitly control the potential improvements over this estimate. The latter refers to the fact that our estimates are conservative and therefore resilient to whatever form the true labeling of the unlabeled data takes on. Experiments demonstrate the improvements in terms of both the log-likelihood and the classification error rate on independent test sets.

arXiv:1406.5667

Correlation Clustering with Noisy Partial Information

In this paper, we propose and study a semi-random model for the Correlation Clustering problem on arbitrary graphs G. We give two approximation algorithms for Correlation Clustering instances from this model. The first algorithm finds a solution of value $(1+ \delta) optcost + O_{\delta}(n\log^3 n)$ with high probability, where $optcost$ is the value of the optimal solution (for every $\delta > 0$). The second algorithm finds the ground truth clustering with an arbitrarily small classification error $\eta$ (under some additional assumptions on the instance).

arXiv:1602.07264

A Multivariate Biomarker for Parkinson's Disease

In this study, we executed a genomic analysis with the objective of selecting a set of genes (possibly small) that would help in the detection and classification of samples from patients affected by Parkinson Disease. We performed a complete data analysis and during the exploratory phase, we selected a list of differentially expressed genes. Despite their association with the diseased state, we could not use them as a biomarker tool. Therefore, our research was extended to include a multivariate analysis approach resulting in the identification and selection of a group of 20 genes that showed a clear potential in detecting and correctly classify Parkinson Disease samples even in the presence of other neurodegenerative disorders.

arXiv:1505.04637

Ensemble of Example-Dependent Cost-Sensitive Decision Trees

Several real-world classification problems are example-dependent cost-sensitive in nature, where the costs due to misclassification vary between examples and not only within classes. However, standard classification methods do not take these costs into account, and assume a constant cost of misclassification errors. In previous works, some methods that take into account the financial costs into the training of different algorithms have been proposed, with the example-dependent cost-sensitive decision tree algorithm being the one that gives the highest savings. In this paper we propose a new framework of ensembles of example-dependent cost-sensitive decision-trees. The framework consists in creating different example-dependent cost-sensitive decision trees on random subsamples of the training set, and then combining them using three different combination approaches. Moreover, we propose two new cost-sensitive combination approaches; cost-sensitive weighted voting and cost-sensitive stacking, the latter being based on the cost-sensitive logistic regression method. Finally, using five different databases, from four real-world applications: credit card fraud detection, churn modeling, credit scoring and direct marketing, we evaluate the proposed method against state-of-the-art example-dependent cost-sensitive techniques, namely, cost-proportionate sampling, Bayes minimum risk and cost-sensitive decision trees. The results show that the proposed algorithms have better results for all databases, in the sense of higher savings.

arXiv:1505.04617

Joint Representation Classification for Collective Face Recognition

Sparse representation based classification (SRC) is popularly used in many applications such as face recognition, and implemented in two steps: representation coding and classification. For a given set of testing images, SRC codes every image over the base images as a sparse representation then classifies it to the class with the least representation error. This scheme utilizes an individual representation rather than the collective one to classify such a set of images, doing so obviously ignores the correlation among the given images. In this paper, a joint representation classification (JRC) for collective face recognition is proposed. JRC takes the correlation of multiple images as well as a single representation into account. Under the assumption that the given face images are generally related to each other, JRC codes all the testing images over the base images simultaneously to facilitate recognition. To this end, the testing inputs are aligned into a matrix and the joint representation coding is formulated to a generalized $l_{2,q}-l_{2,p}$-minimization problem. To uniformly solve the induced optimization problems for any $q\in[1,2]$ and $p\in (0,2]$, an iterative quadratic method (IQM) is developed. IQM is proved to be a strict descent algorithm with convergence to the optimal solution. Moreover, a more practical IQM is proposed for large-scale case. Experimental results on three public databases show that the JRC with practical IQM no only saves much computational cost but also achieves better performance in collective face recognition than the state-of-the-arts.

arXiv:1505.04137

Consistent Algorithms for Multiclass Classification with a Reject Option

We consider the problem of $n$-class classification ($n\geq 2$), where the classifier can choose to abstain from making predictions at a given cost, say, a factor $\alpha$ of the cost of misclassification. Designing consistent algorithms for such $n$-class classification problems with a `reject option' is the main goal of this paper, thereby extending and generalizing previously known results for $n=2$. We show that the Crammer-Singer surrogate and the one vs all hinge loss, albeit with a different predictor than the standard argmax, yield consistent algorithms for this problem when $\alpha=\frac{1}{2}$. More interestingly, we design a new convex surrogate that is also consistent for this problem when $\alpha=\frac{1}{2}$ and operates on a much lower dimensional space ($\log(n)$ as opposed to $n$). We also generalize all three surrogates to be consistent for any $\alpha\in[0, \frac{1}{2}]$.

arXiv:1505.04097

MCODE: Multivariate Conditional Outlier Detection

Outlier detection aims to identify unusual data instances that deviate from expected patterns. The outlier detection is particularly challenging when outliers are context dependent and when they are defined by unusual combinations of multiple outcome variable values. In this paper, we develop and study a new conditional outlier detection approach for multivariate outcome spaces that works by (1) transforming the conditional detection to the outlier detection problem in a new (unconditional) space and (2) defining outlier scores by analyzing the data in the new space. Our approach relies on the classifier chain decomposition of the multi-dimensional classification problem that lets us transform the output space into a probability vector, one probability for each dimension of the output space. Outlier scores applied to these transformed vectors are then used to detect the outliers. Experiments on multiple multi-dimensional classification problems with the different outlier injection rates show that our methodology is robust and able to successfully identify outliers when outliers are either sparse (manifested in one or very few dimensions) or dense (affecting multiple dimensions).

arXiv:1505.04058

A Real Time Facial Expression Classification System Using Local Binary Patterns

Facial expression analysis is one of the popular fields of research in human computer interaction (HCI). It has several applications in next generation user interfaces, human emotion analysis, behavior and cognitive modeling. In this paper, a facial expression classification algorithm is proposed which uses Haar classifier for face detection purpose, Local Binary Patterns (LBP) histogram of different block sizes of a face image as feature vectors and classifies various facial expressions using Principal Component Analysis (PCA). The algorithm is implemented in real time for expression classification since the computational complexity of the algorithm is small. A customizable approach is proposed for facial expression analysis, since the various expressions and intensity of expressions vary from person to person. The system uses grayscale frontal face images of a person to classify six basic emotions namely happiness, sadness, disgust, fear, surprise and anger.

arXiv:1505.04030

Robust Facial Expression Classification Using Shape and Appearance Features

Facial expression recognition has many potential applications which has attracted the attention of researchers in the last decade. Feature extraction is one important step in expression analysis which contributes toward fast and accurate expression recognition. This paper represents an approach of combining the shape and appearance features to form a hybrid feature vector. We have extracted Pyramid of Histogram of Gradients (PHOG) as shape descriptors and Local Binary Patterns (LBP) as appearance features. The proposed framework involves a novel approach of extracting hybrid features from active facial patches. The active facial patches are located on the face regions which undergo a major change during different expressions. After detection of facial landmarks, the active patches are localized and hybrid features are calculated from these patches. The use of small parts of face instead of the whole face for extracting features reduces the computational cost and prevents the over-fitting of the features for classification. By using linear discriminant analysis, the dimensionality of the feature is reduced which is further classified by using the support vector machine (SVM). The experimental results on two publicly available databases show promising accuracy in recognizing all expression classes.

arXiv:1505.04026

Automatic Facial Expression Recognition Using Features of Salient Facial Patches

Extraction of discriminative features from salient facial patches plays a vital role in effective facial expression recognition. The accurate detection of facial landmarks improves the localization of the salient patches on face images. This paper proposes a novel framework for expression recognition by using appearance features of selected facial patches. A few prominent facial patches, depending on the position of facial landmarks, are extracted which are active during emotion elicitation. These active patches are further processed to obtain the salient patches which contain discriminative features for classification of each pair of expressions, thereby selecting different facial patches as salient for different pair of expression classes. One-against-one classification method is adopted using these features. In addition, an automated learning-free facial landmark detection technique has been proposed, which achieves similar performances as that of other state-of-art landmark detection methods, yet requires significantly less execution time. The proposed method is found to perform well consistently in different resolutions, hence, providing a solution for expression recognition in low resolution images. Experiments on CK+ and JAFFE facial expression databases show the effectiveness of the proposed system.