PyTorchKR Papers

최신 논문

총 12,350편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1810.02229공식 코드 · Papers with Code

Italian Event Detection Goes Deep Learning

This paper reports on a set of experiments with different word embeddings to initialize a state-of-the-art Bi-LSTM-CRF network for event detection and classification in Italian, following the EVENTI evaluation exercise. The net- work obtains a new state-of-the-art result by improving the F1 score for detection of 1.3 points, and of 6.5 points for classification, by using a single step approach. The results also provide further evidence that embeddings have a major impact on the performance of such architectures.

arXiv:1810.02180

Improved Generalization Bounds for Adversarially Robust Learning

We consider a model of robust learning in an adversarial environment. The learner gets uncorrupted training data with access to possible corruptions that may be affected by the adversary during testing. The learner's goal is to build a robust classifier, which will be tested on future adversarial examples. The adversary is limited to $k$ possible corruptions for each input. We model the learner-adversary interaction as a zero-sum game. This model is closely related to the adversarial examples model of Schmidt et al. (2018); Madry et al. (2017). Our main results consist of generalization bounds for the binary and multiclass classification, as well as the real-valued case (regression). For the binary classification setting, we both tighten the generalization bound of Feige et al. (2015), and are also able to handle infinite hypothesis classes. The sample complexity is improved from $O(\frac{1}{\epsilon^4}\log(\frac{|H|}{\delta}))$ to $O\big(\frac{1}{\epsilon^2}(kVC(H)\log^{\frac{3}{2}+\alpha}(kVC(H))+\log(\frac{1}{\delta})\big)$ for any $\alpha > 0$. Additionally, we extend the algorithm and generalization bound from the binary to the multiclass and real-valued cases. Along the way, we obtain results on fat-shattering dimension and Rademacher complexity of $k$-fold maxima over function classes; these may be of independent interest. For binary classification, the algorithm of Feige et al. (2015) uses a regret minimization algorithm and an ERM oracle as a black box; we adapt it for the multiclass and regression settings. The algorithm provides us with near-optimal policies for the players on a given training sample.

arXiv:1810.02027

Polar Feature Based Deep Architectures for Automatic Modulation Classification Considering Channel Fading

To develop intelligent receivers, automatic modulation classification (AMC) plays an important role for better spectrum utilization. The emerging deep learning (DL) technique has received much attention in AMC due to its superior performance in classifying data with deep structure. In this work, a novel polar-based deep learning architecture with channel compensation network (CCN) is proposed. Our test results show that learning features from polar domain (r-theta) can improve recognition accuracy by 5% and reduce training overhead by 48%. Besides, the proposed CCN is also robust to channel fading, such as amplitude and phase offsets, and can improve the recognition accuracy by 14% under practical channel environments.

arXiv:1810.02001공식 코드 · Papers with Code

Image and Encoded Text Fusion for Multi-Modal Classification

Multi-modal approaches employ data from multiple input streams such as textual and visual domains. Deep neural networks have been successfully employed for these approaches. In this paper, we present a novel multi-modal approach that fuses images and text descriptions to improve multi-modal classification performance in real-world scenarios. The proposed approach embeds an encoded text onto an image to obtain an information-enriched image. To learn feature representations of resulting images, standard Convolutional Neural Networks (CNNs) are employed for the classification task. We demonstrate how a CNN based pipeline can be used to learn representations of the novel fusion approach. We compare our approach with individual sources on two large-scale multi-modal classification datasets while obtaining encouraging results. Furthermore, we evaluate our approach against two famous multi-modal strategies namely early fusion and late fusion.

arXiv:1810.01989

Verification for Machine Learning, Autonomy, and Neural Networks Survey

This survey presents an overview of verification techniques for autonomous systems, with a focus on safety-critical autonomous cyber-physical systems (CPS) and subcomponents thereof. Autonomy in CPS is enabling by recent advances in artificial intelligence (AI) and machine learning (ML) through approaches such as deep neural networks (DNNs), embedded in so-called learning enabled components (LECs) that accomplish tasks from classification to control. Recently, the formal methods and formal verification community has developed methods to characterize behaviors in these LECs with eventual goals of formally verifying specifications for LECs, and this article presents a survey of many of these recent approaches.

arXiv:1810.01656

A Comparative Study of Neural Network Models for Sentence Classification

This paper presents an extensive comparative study of four neural network models, including feed-forward networks, convolutional networks, recurrent networks and long short-term memory networks, on two sentence classification datasets of English and Vietnamese text. We show that on the English dataset, the convolutional network models without any feature engineering outperform some competitive sentence classifiers with rich hand-crafted linguistic features. We demonstrate that the GloVe word embeddings are consistently better than both Skip-gram word embeddings and word count vectors. We also show the superiority of convolutional neural network models on a Vietnamese newspaper sentence dataset over strong baseline models. Our experimental results suggest some good practices for applying neural network models in sentence classification.

arXiv:1810.01545

A Generalized Neyman-Pearson Criterion for Optimal Domain Adaptation

In the problem of domain adaptation for binary classification, the learner is presented with labeled examples from a source domain, and must correctly classify unlabeled examples from a target domain, which may differ from the source. Previous work on this problem has assumed that the performance measure of interest is the expected value of some loss function. We introduce a new Neyman-Pearson-like criterion and argue that, for this optimality criterion, stronger domain adaptation results are possible than what has previously been established. In particular, we study a class of domain adaptation problems that generalizes both the covariate shift assumption and a model for feature-dependent label noise, and establish optimal classification on the target domain despite not having access to labelled data from this domain.

arXiv:1810.01270

META-DES: A Dynamic Ensemble Selection Framework using Meta-Learning

Dynamic ensemble selection systems work by estimating the level of competence of each classifier from a pool of classifiers. Only the most competent ones are selected to classify a given test sample. This is achieved by defining a criterion to measure the level of competence of a base classifier, such as, its accuracy in local regions of the feature space around the query instance. However, using only one criterion about the behavior of a base classifier is not sufficient to accurately estimate its level of competence. In this paper, we present a novel dynamic ensemble selection framework using meta-learning. We propose five distinct sets of meta-features, each one corresponding to a different criterion to measure the level of competence of a classifier for the classification of input samples. The meta-features are extracted from the training data and used to train a meta-classifier to predict whether or not a base classifier is competent enough to classify an input instance. During the generalization phase, the meta-features are extracted from the query instance and passed down as input to the meta-classifier. The meta-classifier estimates, whether a base classifier is competent enough to be added to the ensemble. Experiments are conducted over several small sample size classification problems, i.e., problems with a high degree of uncertainty due to the lack of training data. Experimental results show the proposed meta-learning framework greatly improves classification accuracy when compared against current state-of-the-art dynamic ensemble selection techniques.

arXiv:1810.00396

Benchmarks of ResNet Architecture for Atrial Fibrillation Classification

In this work we apply variations of ResNet architecture to the task of atrial fibrillation classification. Variations differ in number of filter after first convolution, ResNet block layout, number of filters in block convolutions and number of ResNet blocks between downsampling operations. We have found a range of model size in which models with quite different configurations show similar performance. It is likely that overall number of parameters plays dominant role in model performance. However, configuration parameters like layout have values that constantly lead to better results, which allows to suggest that these parameters should be defined and fixed in the first place, while others may be varied in a reasonable range to satisfy any existing constraints.

arXiv:1810.00360

Improving Bag-of-Visual-Words Towards Effective Facial Expressive Image Classification

Bag-of-Visual-Words (BoVW) approach has been widely used in the recent years for image classification purposes. However, the limitations regarding optimal feature selection, clustering technique, the lack of spatial organization of the data and the weighting of visual words are crucial. These factors affect the stability of the model and reduce performance. We propose to develop an algorithm based on BoVW for facial expression analysis which goes beyond those limitations. Thus the visual codebook is built by using k-Means++ method to avoid poor clustering. To exploit reliable low level features, we search for the best feature detector that avoids locating a large number of keypoints which do not contribute to the classification process. Then, we propose to compute the relative conjunction matrix in order to preserve the spatial order of the data by coding the relationships among visual words. In addition, a weighting scheme that reflects how important a visual word is with respect to a given image is introduced. We speed up the learning process by using histogram intersection kernel by Support Vector Machine to learn a discriminative classifier. The efficiency of the proposed algorithm is compared with standard bag of visual words method and with bag of visual words method with spatial pyramid. Extensive experiments on the CK+, the MMI and the JAFFE databases show good average recognition rates. Likewise, the ability to recognize spontaneous and non-basic expressive states is investigated using the DynEmo database.

arXiv:1810.00207

Non-local NetVLAD Encoding for Video Classification

This paper describes our solution for the 2$^\text{nd}$ YouTube-8M video understanding challenge organized by Google AI. Unlike the video recognition benchmarks, such as Kinetics and Moments, the YouTube-8M challenge provides pre-extracted visual and audio features instead of raw videos. In this challenge, the submitted model is restricted to 1GB, which encourages participants focus on constructing one powerful single model rather than incorporating of the results from a bunch of models. Our system fuses six different sub-models into one single computational graph, which are categorized into three families. More specifically, the most effective family is the model with non-local operations following the NetVLAD encoding. The other two family models are Soft-BoF and GRU, respectively. In order to further boost single models performance, the model parameters of different checkpoints are averaged. Experimental results demonstrate that our proposed system can effectively perform the video classification task, achieving 0.88763 on the public test set and 0.88704 on the private set in terms of GAP@20, respectively. We finally ranked at the fourth place in the YouTube-8M video understanding challenge.

arXiv:1810.00162공식 코드 · Papers with Code

NICE: Noise Injection and Clamping Estimation for Neural Network Quantization

Convolutional Neural Networks (CNN) are very popular in many fields including computer vision, speech recognition, natural language processing, to name a few. Though deep learning leads to groundbreaking performance in these domains, the networks used are very demanding computationally and are far from real-time even on a GPU, which is not power efficient and therefore does not suit low power systems such as mobile devices. To overcome this challenge, some solutions have been proposed for quantizing the weights and activations of these networks, which accelerate the runtime significantly. Yet, this acceleration comes at the cost of a larger error. The \uniqname method proposed in this work trains quantized neural networks by noise injection and a learned clamping, which improve the accuracy. This leads to state-of-the-art results on various regression and classification tasks, e.g., ImageNet classification with architectures such as ResNet-18/34/50 with low as 3-bit weights and activations. We implement the proposed solution on an FPGA to demonstrate its applicability for low power real-time applications. The implementation of the paper is available at https://github.com/Lancer555/NICE

arXiv:1810.00031

Active Fairness in Algorithmic Decision Making

Society increasingly relies on machine learning models for automated decision making. Yet, efficiency gains from automation have come paired with concern for algorithmic discrimination that can systematize inequality. Recent work has proposed optimal post-processing methods that randomize classification decisions for a fraction of individuals, in order to achieve fairness measures related to parity in errors and calibration. These methods, however, have raised concern due to the information inefficiency, intra-group unfairness, and Pareto sub-optimality they entail. The present work proposes an alternative active framework for fair classification, where, in deployment, a decision-maker adaptively acquires information according to the needs of different groups or individuals, towards balancing disparities in classification performance. We propose two such methods, where information collection is adapted to group- and individual-level needs respectively. We show on real-world datasets that these can achieve: 1) calibration and single error parity (e.g., equal opportunity); and 2) parity in both false positive and false negative rates (i.e., equal odds). Moreover, we show that by leveraging their additional degree of freedom, active approaches can substantially outperform randomization-based classifiers previously considered optimal, while avoiding limitations such as intra-group unfairness.

arXiv:1810.01140공식 코드 · Papers with Code

Training compact deep learning models for video classification using circulant matrices

In real world scenarios, model accuracy is hardly the only factor to consider. Large models consume more memory and are computationally more intensive, which makes them difficult to train and to deploy, especially on mobile devices. In this paper, we build on recent results at the crossroads of Linear Algebra and Deep Learning which demonstrate how imposing a structure on large weight matrices can be used to reduce the size of the model. We propose very compact models for video classification based on state-of-the-art network architectures such as Deep Bag-of-Frames, NetVLAD and NetFisherVectors. We then conduct thorough experiments using the large YouTube-8M video classification dataset. As we will show, the circulant DBoF embedding achieves an excellent trade-off between size and accuracy.

arXiv:1810.01114

Who is Addressed in this Comment? Automatically Classifying Meta-Comments in News Comments

User comments have become an essential part of online journalism. However, newsrooms are often overwhelmed by the vast number of diverse comments, for which a manual analysis is barely feasible. Identifying meta-comments that address or mention newsrooms, individual journalists, or moderators and that may call for reactions is particularly critical. In this paper, we present an automated approach to identify and classify meta-comments. We compare comment classification based on manually extracted features with an end-to-end learning approach. We develop, optimize, and evaluate multiple classifiers on a comment dataset of the large German online newsroom SPIEGEL Online and the 'One Million Posts' corpus of DER STANDARD, an Austrian newspaper. Both optimized classification approaches achieved encouraging $F_{0.5}$ values between 76% and 91%. We report on the most significant classification features with the results of a qualitative analysis and discuss how our work contributes to making participation in online journalism more constructive.

arXiv:1810.01091

Ancient Coin Classification Using Graph Transduction Games

Recognizing the type of an ancient coin requires theoretical expertise and years of experience in the field of numismatics. Our goal in this work is automatizing this time consuming and demanding task by a visual classification framework. Specifically, we propose to model ancient coin image classification using Graph Transduction Games (GTG). GTG casts the classification problem as a non-cooperative game where the players (the coin images) decide their strategies (class labels) according to the choices made by the others, which results with a global consensus at the final labeling. Experiments are conducted on the only publicly available dataset which is composed of 180 images of 60 types of Roman coins. We demonstrate that our approach outperforms the literature work on the same dataset with the classification accuracy of 73.6% and 87.3% when there are one and two images per class in the training set, respectively.

arXiv:1810.01061

Feature Selection Approach with Missing Values Conducted for Statistical Learning: A Case Study of Entrepreneurship Survival Dataset

In this article, we investigate the features which enhanced discriminate the survival in the micro and small business (MSE) using the approach of data mining with feature selection. According to the complexity of the data set, we proposed a comparison of three data imputation methods such as mean imputation (MI), k-nearest neighbor (KNN) and expectation maximization (EM) using mutually the selection of variables technique, whereby t-test, then through the data mining process using logistic regression classification methods, naive Bayes algorithm, linear discriminant analysis and support vector machine hence comparing their respective performances. The experimental results will be spread in developing a model to predict the MSE survival, providing a better understanding in the topic once it is a significant part of the Brazilian' GPA and macroeconomy.

arXiv:1810.01015

Convergence Rates for Empirical Estimation of Binary Classification Bounds

Bounding the best achievable error probability for binary classification problems is relevant to many applications including machine learning, signal processing, and information theory. Many bounds on the Bayes binary classification error rate depend on information divergences between the pair of class distributions. Recently, the Henze-Penrose (HP) divergence has been proposed for bounding classification error probability. We consider the problem of empirically estimating the HP-divergence from random samples. We derive a bound on the convergence rate for the Friedman-Rafsky (FR) estimator of the HP-divergence, which is related to a multivariate runs statistic for testing between two distributions. The FR estimator is derived from a multicolored Euclidean minimal spanning tree (MST) that spans the merged samples. We obtain a concentration inequality for the Friedman-Rafsky estimator of the Henze-Penrose divergence. We validate our results experimentally and illustrate their application to real datasets.

arXiv:1810.00974

Neural Regression Trees

Regression-via-Classification (RvC) is the process of converting a regression problem to a classification one. Current approaches for RvC use ad-hoc discretization strategies and are suboptimal. We propose a neural regression tree model for RvC. In this model, we employ a joint optimization framework where we learn optimal discretization thresholds while simultaneously optimizing the features for each node in the tree. We empirically show the validity of our model by testing it on two challenging regression tasks where we establish the state of the art.

arXiv:1810.00968

Utilizing a Transparency-driven Environment toward Trusted Automatic Genre Classification: A Case Study in Journalism History

With the growing abundance of unlabeled data in real-world tasks, researchers have to rely on the predictions given by black-boxed computational models. However, it is an often neglected fact that these models may be scoring high on accuracy for the wrong reasons. In this paper, we present a practical impact analysis of enabling model transparency by various presentation forms. For this purpose, we developed an environment that empowers non-computer scientists to become practicing data scientists in their own research field. We demonstrate the gradually increasing understanding of journalism historians through a real-world use case study on automatic genre classification of newspaper articles. This study is a first step towards trusted usage of machine learning pipelines in a responsible way.