PyTorchKR Papers

최신 논문

총 11,809편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1608.07441

Hard Negative Mining for Metric Learning Based Zero-Shot Classification

Zero-Shot learning has been shown to be an efficient strategy for domain adaptation. In this context, this paper builds on the recent work of Bucher et al. [1], which proposed an approach to solve Zero-Shot classification problems (ZSC) by introducing a novel metric learning based objective function. This objective function allows to learn an optimal embedding of the attributes jointly with a measure of similarity between images and attributes. This paper extends their approach by proposing several schemes to control the generation of the negative pairs, resulting in a significant improvement of the performance and giving above state-of-the-art results on three challenging ZSC datasets.

arXiv:1608.08435

Multi-Label Classification Method Based on Extreme Learning Machines

In this paper, an Extreme Learning Machine (ELM) based technique for Multi-label classification problems is proposed and discussed. In multi-label classification, each of the input data samples belongs to one or more than one class labels. The traditional binary and multi-class classification problems are the subset of the multi-label problem with the number of labels corresponding to each sample limited to one. The proposed ELM based multi-label classification technique is evaluated with six different benchmark multi-label datasets from different domains such as multimedia, text and biology. A detailed comparison of the results is made by comparing the proposed method with the results from nine state of the arts techniques for five different evaluation metrics. The nine methods are chosen from different categories of multi-label methods. The comparative results shows that the proposed Extreme Learning Machine based multi-label classification technique is a better alternative than the existing state of the art methods for multi-label problems.

arXiv:1609.00843

An Online Universal Classifier for Binary, Multi-class and Multi-label Classification

Classification involves the learning of the mapping function that associates input samples to corresponding target label. There are two major categories of classification problems: Single-label classification and Multi-label classification. Traditional binary and multi-class classifications are sub-categories of single-label classification. Several classifiers are developed for binary, multi-class and multi-label classification problems, but there are no classifiers available in the literature capable of performing all three types of classification. In this paper, a novel online universal classifier capable of performing all the three types of classification is proposed. Being a high speed online classifier, the proposed technique can be applied to streaming data applications. The performance of the developed classifier is evaluated using datasets from binary, multi-class and multi-label problems. The results obtained are compared with state-of-the-art techniques from each of the classification types.

arXiv:1609.00514

On Horizontal and Vertical Separation in Hierarchical Text Classification

Hierarchy is a common and effective way of organizing data and representing their relationships at different levels of abstraction. However, hierarchical data dependencies cause difficulties in the estimation of "separable" models that can distinguish between the entities in the hierarchy. Extracting separable models of hierarchical entities requires us to take their relative position into account and to consider the different types of dependencies in the hierarchy. In this paper, we present an investigation of the effect of separability in text-based entity classification and argue that in hierarchical classification, a separation property should be established between entities not only in the same layer, but also in different layers. Our main findings are the followings. First, we analyse the importance of separability on the data representation in the task of classification and based on that, we introduce a "Strong Separation Principle" for optimizing expected effectiveness of classifiers decision based on separation property. Second, we present Hierarchical Significant Words Language Models (HSWLM) which capture all, and only, the essential features of hierarchical entities according to their relative position in the hierarchy resulting in horizontally and vertically separable models. Third, we validate our claims on real-world data and demonstrate that how HSWLM improves the accuracy of classification and how it provides transferable models over time. Although discussions in this paper focus on the classification problem, the models are applicable to any information access tasks on data that has, or can be mapped to, a hierarchical structure.

arXiv:1609.00435

Citation Classification for Behavioral Analysis of a Scientific Field

Citations are an important indicator of the state of a scientific field, reflecting how authors frame their work, and influencing uptake by future scholars. However, our understanding of citation behavior has been limited to small-scale manual citation analysis. We perform the largest behavioral study of citations to date, analyzing how citations are both framed and taken up by scholars in one entire field: natural language processing. We introduce a new dataset of nearly 2,000 citations annotated for function and centrality, and use it to develop a state-of-the-art classifier and label the entire ACL Reference Corpus. We then study how citations are framed by authors and use both papers and online traces to track how citations are followed by readers. We demonstrate that authors are sensitive to discourse structure and publication venue when citing, that online readers follow temporal links to previous and future work rather than methodological links, and that how a paper cites related work is predictive of its citation count. Finally, we use changes in citation roles to show that the field of NLP is undergoing a significant increase in consensus.

arXiv:1609.00344

Deep Learning Human Mind for Automated Visual Classification

What if we could effectively read the mind and transfer human visual capabilities to computer vision methods? In this paper, we aim at addressing this question by developing the first visual object classifier driven by human brain signals. In particular, we employ EEG data evoked by visual object stimuli combined with Recurrent Neural Networks (RNN) to learn a discriminative brain activity manifold of visual categories. Afterwards, we train a Convolutional Neural Network (CNN)-based regressor to project images onto the learned manifold, thus effectively allowing machines to employ human brain-based features for automated visual classification. We use a 32-channel EEG to record brain activity of seven subjects while looking at images of 40 ImageNet object classes. The proposed RNN based approach for discriminating object classes using brain signals reaches an average accuracy of about 40%, which outperforms existing methods attempting to learn EEG visual object representations. As for automated object categorization, our human brain-driven approach obtains competitive performance, comparable to those achieved by powerful CNN models, both on ImageNet and CalTech 101, thus demonstrating its classification and generalization capabilities. This gives us a real hope that, indeed, human mind can be read and transferred to machines.

arXiv:1609.00086

A novel online multi-label classifier for high-speed streaming data applications

In this paper, a high-speed online neural network classifier based on extreme learning machines for multi-label classification is proposed. In multi-label classification, each of the input data sample belongs to one or more than one of the target labels. The traditional binary and multi-class classification where each sample belongs to only one target class forms the subset of multi-label classification. Multi-label classification problems are far more complex than binary and multi-class classification problems, as both the number of target labels and each of the target labels corresponding to each of the input samples are to be identified. The proposed work exploits the high-speed nature of the extreme learning machines to achieve real-time multi-label classification of streaming data. A new threshold-based online sequential learning algorithm is proposed for high speed and streaming data classification of multi-label problems. The proposed method is experimented with six different datasets from different application domains such as multimedia, text, and biology. The hamming loss, accuracy, training time and testing time of the proposed technique is compared with nine different state-of-the-art methods. Experimental studies shows that the proposed technique outperforms the existing multi-label classifiers in terms of performance and speed.

arXiv:1608.08905

A Novel Online Real-time Classifier for Multi-label Data Streams

In this paper, a novel extreme learning machine based online multi-label classifier for real-time data streams is proposed. Multi-label classification is one of the actively researched machine learning paradigm that has gained much attention in the recent years due to its rapidly increasing real world applications. In contrast to traditional binary and multi-class classification, multi-label classification involves association of each of the input samples with a set of target labels simultaneously. There are no real-time online neural network based multi-label classifier available in the literature. In this paper, we exploit the inherent nature of high speed exhibited by the extreme learning machines to develop a novel online real-time classifier for multi-label data streams. The developed classifier is experimented with datasets from different application domains for consistency, performance and speed. The experimental studies show that the proposed method outperforms the existing state-of-the-art techniques in terms of speed and accuracy and can classify multi-label data streams in real-time.

arXiv:1608.08898

A High Speed Multi-label Classifier based on Extreme Learning Machines

In this paper a high speed neural network classifier based on extreme learning machines for multi-label classification problem is proposed and dis-cussed. Multi-label classification is a superset of traditional binary and multi-class classification problems. The proposed work extends the extreme learning machine technique to adapt to the multi-label problems. As opposed to the single-label problem, both the number of labels the sample belongs to, and each of those target labels are to be identified for multi-label classification resulting in in-creased complexity. The proposed high speed multi-label classifier is applied to six benchmark datasets comprising of different application areas such as multi-media, text and biology. The training time and testing time of the classifier are compared with those of the state-of-the-arts methods. Experimental studies show that for all the six datasets, our proposed technique have faster execution speed and better performance, thereby outperforming all the existing multi-label clas-sification methods.

arXiv:1608.08574

Applying Naive Bayes Classification to Google Play Apps Categorization

There are over one million apps on Google Play Store and over half a million publishers. Having such a huge number of apps and developers can pose a challenge to app users and new publishers on the store. Discovering apps can be challenging if apps are not correctly published in the right category, and, in turn, reduce earnings for app developers. Additionally, with over 41 categories on Google Play Store, deciding on the right category to publish an app can be challenging for developers due to the number of categories they have to choose from. Machine Learning has been very useful, especially in classification problems such sentiment analysis, document classification and spam detection. These strategies can also be applied to app categorization on Google Play Store to suggest appropriate categories for app publishers using details from their application. In this project, we built two variations of the Naive Bayes classifier using open metadata from top developer apps on Google Play Store in other to classify new apps on the store. These classifiers are then evaluated using various evaluation methods and their results compared against each other. The results show that the Naive Bayes algorithm performs well for our classification problem and can potentially automate app categorization for Android app publishers on Google Play Store

arXiv:1609.01933

Sentiment Classification of Food Reviews

Sentiment analysis of reviews is a popular task in natural language processing. In this work, the goal is to predict the score of food reviews on a scale of 1 to 5 with two recurrent neural networks that are carefully tuned. As for baseline, we train a simple RNN for classification. Then we extend the baseline to GRU. In addition, we present two different methods to deal with highly skewed data, which is a common problem for reviews. Models are evaluated using accuracies.

arXiv:1609.01829

Animal Classification System: A Block Based Approach

In this work, we propose a method for the classification of animal in images. Initially, a graph cut based method is used to perform segmentation in order to eliminate the background from the given image. The segmented animal images are partitioned in to number of blocks and then the color texture moments are extracted from different blocks. Probabilistic neural network and K-nearest neighbors are considered here for classification. To corroborate the efficacy of the proposed method, an experiment was conducted on our own data set of 25 classes of animals, which consisted of 4000 sample images. The experiment was conducted by picking images randomly from the database to study the effect of classification accuracy, and the results show that the K-nearest neighbors classifier achieves good performance.

arXiv:1609.01828

Delaunay Triangulation on Skeleton of Flowers for Classification

In this work, we propose a Triangle based approach to classify flower images. Initially, flowers are segmented using whorl based region merging segmentation. Skeleton of a flower is obtained from the segmented flower using a skeleton pruning method. The Delaunay triangulation is obtained from the endpoints and junction points detected on the skeleton. The length and angle features are extracted from the obtained Delaunay triangles and then are aggregated to represent in the form of interval-valued type data. A suitable classifier has been explored for the purpose of classification. To corroborate the efficacy of the proposed method, an experiment is conducted on our own data set of 30 classes of flowers, containing 3000 samples.

arXiv:1609.01414

Features Fusion for Classification of Logos

In this paper, a logo classification system based on the appearance of logo images is proposed. The proposed classification system makes use of global characteristics of logo images for classification. Color, texture, and shape of a logo wholly describe the global characteristics of logo images. The various combinations of these characteristics are used for classification. The combination contains only with single feature or with fusion of two features or fusion of all three features considered at a time respectively. Further, the system categorizes the logo image into: a logo image with fully text or with fully symbols or containing both symbols and texts.. The K-Nearest Neighbour (K-NN) classifier is used for classification. Due to the lack of color logo image dataset in the literature, the same is created consisting 5044 color logo images. Finally, the performance of the classification system is evaluated through accuracy, precision, recall and F-measure computed from the confusion matrix. The experimental results show that the most promising results are obtained for fusion of features.

arXiv:1609.01228

Towards Automated Melanoma Screening: Exploring Transfer Learning Schemes

Deep learning is the current bet for image classification. Its greed for huge amounts of annotated data limits its usage in medical imaging context. In this scenario transfer learning appears as a prominent solution. In this report we aim to clarify how transfer learning schemes may influence classification results. We are particularly focused in the automated melanoma screening problem, a case of medical imaging in which transfer learning is still not widely used. We explored transfer with and without fine-tuning, sequential transfers and usage of pre-trained models in general and specific datasets. Although some issues remain open, our findings may drive future researches.

arXiv:1609.01100

A max-cut approach to heterogeneity in cryo-electron microscopy

The field of cryo-electron microscopy has made astounding advancements in the past few years, mainly due to advancements in electron detectors' technology. Yet, one of the key open challenges of the field remains the processing of heterogeneous data sets, produced from samples containing particles at several different conformational states. For such data sets, the algorithms must include some classification procedure to identify homogeneous groups within the data, so that the images in each group correspond to the same underlying structure. The fundamental importance of the heterogeneity problem in cryo-electron microscopy has drawn many research efforts, and resulted in significant progress in classification algorithms for heterogeneous data sets. While these algorithms are extremely useful and effective in practice, they lack rigorous mathematical analysis and performance guarantees. In this paper, we attempt to make the first steps towards rigorous mathematical analysis of the heterogeneity problem in cryo-electron microscopy. To that end, we present an algorithm for processing heterogeneous data sets, and prove accuracy and stability bounds for it. We also suggest an extension of this algorithm that combines the classification and reconstruction steps. We demonstrate it on simulated data, and compare its performance to the state-of-the-art algorithm in RELION.

arXiv:1609.00878

A Probabilistic Optimum-Path Forest Classifier for Binary Classification Problems

Probabilistic-driven classification techniques extend the role of traditional approaches that output labels (usually integer numbers) only. Such techniques are more fruitful when dealing with problems where one is not interested in recognition/identification only, but also into monitoring the behavior of consumers and/or machines, for instance. Therefore, by means of probability estimates, one can take decisions to work better in a number of scenarios. In this paper, we propose a probabilistic-based Optimum Path Forest (OPF) classifier to handle with binary classification problems, and we show it can be more accurate than naive OPF in a number of datasets. In addition to being just more accurate or not, probabilistic OPF turns to be another useful tool to the scientific community.

arXiv:1606.08051

Training LDCRF model on unsegmented sequences using Connectionist Temporal Classification

Many machine learning problems such as speech recognition, gesture recognition, and handwriting recognition are concerned with simultaneous segmentation and labeling of sequence data. Latent-dynamic conditional random field (LDCRF) is a well-known discriminative method that has been successfully used for this task. However, LDCRF can only be trained with pre-segmented data sequences in which the label of each frame is available apriori. In the realm of neural networks, the invention of connectionist temporal classification (CTC) made it possible to train recurrent neural networks on unsegmented sequences with great success. In this paper, we use CTC to train an LDCRF model on unsegmented sequences. Experimental results on two gesture recognition tasks show that the proposed method outperforms LDCRFs, hidden Markov models, and conditional random fields.

arXiv:1609.02976

An Integrated Classification Model for Financial Data Mining

Nowadays, financial data analysis is becoming increasingly important in the business market. As companies collect more and more data from daily operations, they expect to extract useful knowledge from existing collected data to help make reasonable decisions for new customer requests, e.g. user credit category, churn analysis, real estate analysis, etc. Financial institutes have applied different data mining techniques to enhance their business performance. However, simple ap-proach of these techniques could raise a performance issue. Besides, there are very few general models for both understanding and forecasting different finan-cial fields. We present in this paper a new classification model for analyzing fi-nancial data. We also evaluate this model with different real-world data to show its performance.

arXiv:1609.02781공식 코드 · Papers with Code

An empirical study on the effects of different types of noise in image classification tasks

Image classification is one of the main research problems in computer vision and machine learning. Since in most real-world image classification applications there is no control over how the images are captured, it is necessary to consider the possibility that these images might be affected by noise (e.g. sensor noise in a low-quality surveillance camera). In this paper we analyse the impact of three different types of noise on descriptors extracted by two widely used feature extraction methods (LBP and HOG) and how denoising the images can help to mitigate this problem. We carry out experiments on two different datasets and consider several types of noise, noise levels, and denoising methods. Our results show that noise can hinder classification performance considerably and make classes harder to separate. Although denoising methods were not able to reach the same performance of the noise-free scenario, they improved classification results for noisy data.