PyTorchKR Papers

최신 논문

총 12,350편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1703.05235

Transfer Learning for Melanoma Detection: Participation in ISIC 2017 Skin Lesion Classification Challenge

This manuscript describes our participation in the International Skin Imaging Collaboration's 2017 Skin Lesion Analysis Towards Melanoma Detection competition. We participated in Part 3: Lesion Classification. The two stated goals of this binary image classification challenge were to distinguish between (a) melanoma and (b) nevus and seborrheic keratosis, followed by distinguishing between (a) seborrheic keratosis and (b) nevus and melanoma. We chose a deep neural network approach with a transfer learning strategy, using a pre-trained Inception V3 network as both a feature extractor to provide input for a multi-layer perceptron as well as fine-tuning an augmented Inception network. This approach yielded validation set AUC's of 0.84 on the second task and 0.76 on the first task, for an average AUC of 0.80. We joined the competition unfortunately late, and we look forward to improving on these results.

arXiv:1703.04101

Evaluating Deep Convolutional Neural Networks for Material Classification

Determining the material category of a surface from an image is a demanding task in perception that is drawing increasing attention. Following the recent remarkable results achieved for image classification and object detection utilising Convolutional Neural Networks (CNNs), we empirically study material classification of everyday objects employing these techniques. More specifically, we conduct a rigorous evaluation of how state-of-the art CNN architectures compare on a common ground over widely used material databases. Experimental results on three challenging material databases show that the best performing CNN architectures can achieve up to 94.99\% mean average precision when classifying materials.

arXiv:1701.04224

Auxiliary Multimodal LSTM for Audio-visual Speech Recognition and Lipreading

The Aduio-visual Speech Recognition (AVSR) which employs both the video and audio information to do Automatic Speech Recognition (ASR) is one of the application of multimodal leaning making ASR system more robust and accuracy. The traditional models usually treated AVSR as inference or projection but strict prior limits its ability. As the revival of deep learning, Deep Neural Networks (DNN) becomes an important toolkit in many traditional classification tasks including ASR, image classification, natural language processing. Some DNN models were used in AVSR like Multimodal Deep Autoencoders (MDAEs), Multimodal Deep Belief Network (MDBN) and Multimodal Deep Boltzmann Machine (MDBM) that actually work better than traditional methods. However, such DNN models have several shortcomings: (1) They don't balance the modal fusion and temporal fusion, or even haven't temporal fusion; (2)The architecture of these models isn't end-to-end, the training and testing getting cumbersome. We propose a DNN model, Auxiliary Multimodal LSTM (am-LSTM), to overcome such weakness. The am-LSTM could be trained and tested once, moreover easy to train and preventing overfitting automatically. The extensibility and flexibility are also take into consideration. The experiments show that am-LSTM is much better than traditional methods and other DNN models in three datasets.

arXiv:1611.06013

Improving training of deep neural networks via Singular Value Bounding

Deep learning methods achieve great success recently on many computer vision problems, with image classification and object detection as the prominent examples. In spite of these practical successes, optimization of deep networks remains an active topic in deep learning research. In this work, we focus on investigation of the network solution properties that can potentially lead to good performance. Our research is inspired by theoretical and empirical results that use orthogonal matrices to initialize networks, but we are interested in investigating how orthogonal weight matrices perform when network training converges. To this end, we propose to constrain the solutions of weight matrices in the orthogonal feasible set during the whole process of network training, and achieve this by a simple yet effective method called Singular Value Bounding (SVB). In SVB, all singular values of each weight matrix are simply bounded in a narrow band around the value of 1. Based on the same motivation, we also propose Bounded Batch Normalization (BBN), which improves Batch Normalization by removing its potential risk of ill-conditioned layer transform. We present both theoretical and empirical results to justify our proposed methods. Experiments on benchmark image classification datasets show the efficacy of our proposed SVB and BBN. In particular, we achieve the state-of-the-art results of 3.06% error rate on CIFAR10 and 16.90% on CIFAR100, using off-the-shelf network architectures (Wide ResNets). Our preliminary results on ImageNet also show the promise in large-scale learning.

arXiv:1608.04348

Anomaly detection and classification for streaming data using PDEs

Nondominated sorting, also called Pareto Depth Analysis (PDA), is widely used in multi-objective optimization and has recently found important applications in multi-criteria anomaly detection. Recently, a partial differential equation (PDE) continuum limit was discovered for nondominated sorting leading to a very fast approximate sorting algorithm called PDE-based ranking. We propose in this paper a fast real-time streaming version of the PDA algorithm for anomaly detection that exploits the computational advantages of PDE continuum limits. Furthermore, we derive new PDE continuum limits for sorting points within their nondominated layers and show how the new PDEs can be used to classify anomalies based on which criterion was more significantly violated. We also prove statistical convergence rates for PDE-based ranking, and present the results of numerical experiments with both synthetic and real data.

arXiv:1608.03542

WikiReading: A Novel Large-scale Language Understanding Task over Wikipedia

We present WikiReading, a large-scale natural language understanding task and publicly-available dataset with 18 million instances. The task is to predict textual values from the structured knowledge base Wikidata by reading the text of the corresponding Wikipedia articles. The task contains a rich variety of challenging classification and extraction sub-tasks, making it well-suited for end-to-end models such as deep neural networks (DNNs). We compare various state-of-the-art DNN-based architectures for document classification, information extraction, and question answering. We find that models supporting a rich answer space, such as word or character sequences, perform best. Our best-performing model, a word-level sequence to sequence model with a mechanism to copy out-of-vocabulary words, obtains an accuracy of 71.8%.

arXiv:1607.03476

End-to-end training of object class detectors for mean average precision

We present a method for training CNN-based object class detectors directly using mean average precision (mAP) as the training loss, in a truly end-to-end fashion that includes non-maximum suppression (NMS) at training time. This contrasts with the traditional approach of training a CNN for a window classification loss, then applying NMS only at test time, when mAP is used as the evaluation metric in place of classification accuracy. However, mAP following NMS forms a piecewise-constant structured loss over thousands of windows, with gradients that do not convey useful information for gradient descent. Hence, we define new, general gradient-like quantities for piecewise constant functions, which have wide applicability. We describe how to calculate these efficiently for mAP following NMS, enabling to train a detector based on Fast R-CNN directly for mAP. This model achieves equivalent performance to the standard Fast R-CNN on the PASCAL VOC 2007 and 2012 datasets, while being conceptually more appealing as the very same model and loss are used at both training and test time.

arXiv:1703.09800

Disruptive Event Classification using PMU Data in Distribution Networks

Proliferation of advanced metering devices with high sampling rates in distribution grids, e.g., micro-phasor measurement units ({\mu}PMU), provides unprecedented potentials for wide-area monitoring and diagnostic applications, e.g., situational awareness, health monitoring of distribution assets. Unexpected disruptive events interrupting the normal operation of assets in distribution grids can eventually lead to permanent failure with expensive replacement cost over time. Therefore, disruptive event classification provides useful information for preventive maintenance of the assets in distribution networks. Preventive maintenance provides wide range of benefits in terms of time, avoiding unexpected outages, maintenance crew utilization, and equipment replacement cost. In this paper, a PMU-data-driven framework is proposed for classification of disruptive events in distribution networks. The two disruptive events, i.e., malfunctioned capacitor bank switching and malfunctioned regulator on-load tap changer (OLTC) switching are considered and distinguished from the normal abrupt load change in distribution grids. The performance of the proposed framework is verified using the simulation of the events in the IEEE 13-bus distribution network. The event classification is formulated using two different algorithms as; i) principle component analysis (PCA) together with multi-class support vector machine (SVM), and ii) autoencoder along with softmax classifier. The results demonstrate the effectiveness of the proposed algorithms and satisfactory classification accuracies.

arXiv:1703.07131

Knowledge distillation using unlabeled mismatched images

Current approaches for Knowledge Distillation (KD) either directly use training data or sample from the training data distribution. In this paper, we demonstrate effectiveness of 'mismatched' unlabeled stimulus to perform KD for image classification networks. For illustration, we consider scenarios where this is a complete absence of training data, or mismatched stimulus has to be used for augmenting a small amount of training data. We demonstrate that stimulus complexity is a key factor for distillation's good performance. Our examples include use of various datasets for stimulating MNIST and CIFAR teachers.

arXiv:1703.06990

Metalearning for Feature Selection

A general formulation of optimization problems in which various candidate solutions may use different feature-sets is presented, encompassing supervised classification, automated program learning and other cases. A novel characterization of the concept of a "good quality feature" for such an optimization problem is provided; and a proposal regarding the integration of quality based feature selection into metalearning is suggested, wherein the quality of a feature for a problem is estimated using knowledge about related features in the context of related problems. Results are presented regarding extensive testing of this "feature metalearning" approach on supervised text classification problems; it is demonstrated that, in this context, feature metalearning can provide significant and sometimes dramatic speedup over standard feature selection heuristics.

arXiv:1703.06777

On the Use of Default Parameter Settings in the Empirical Evaluation of Classification Algorithms

We demonstrate that, for a range of state-of-the-art machine learning algorithms, the differences in generalisation performance obtained using default parameter settings and using parameters tuned via cross-validation can be similar in magnitude to the differences in performance observed between state-of-the-art and uncompetitive learning systems. This means that fair and rigorous evaluation of new learning algorithms requires performance comparison against benchmark methods with best-practice model selection procedures, rather than using default parameter settings. We investigate the sensitivity of three key machine learning algorithms (support vector machine, random forest and rotation forest) to their default parameter settings, and provide guidance on determining sensible default parameter values for implementations of these algorithms. We also conduct an experimental comparison of these three algorithms on 121 classification problems and find that, perhaps surprisingly, rotation forest is significantly more accurate on average than both random forest and a support vector machine.

arXiv:1703.06514

Recurrent Collective Classification

We propose a new method for training iterative collective classifiers for labeling nodes in network data. The iterative classification algorithm (ICA) is a canonical method for incorporating relational information into classification. Yet, existing methods for training ICA models rely on the assumption that relational features reflect the true labels of the nodes. This unrealistic assumption introduces a bias that is inconsistent with the actual prediction algorithm. In this paper, we introduce recurrent collective classification (RCC), a variant of ICA analogous to recurrent neural network prediction. RCC accommodates any differentiable local classifier and relational feature functions. We provide gradient-based strategies for optimizing over model parameters to more directly minimize the loss function. In our experiments, this direct loss minimization translates to improved accuracy and robustness on real network data. We demonstrate the robustness of RCC in settings where local classification is very noisy, settings that are particularly challenging for ICA.

arXiv:1703.00311

Multi-stage Neural Networks with Single-sided Classifiers for False Positive Reduction and its Evaluation using Lung X-ray CT Images

Lung nodule classification is a class imbalanced problem because nodules are found with much lower frequency than non-nodules. In the class imbalanced problem, conventional classifiers tend to be overwhelmed by the majority class and ignore the minority class. We therefore propose cascaded convolutional neural networks to cope with the class imbalanced problem. In the proposed approach, multi-stage convolutional neural networks that perform as single-sided classifiers filter out obvious non-nodules. Successively, a convolutional neural network trained with a balanced data set calculates nodule probabilities. The proposed method achieved the sensitivity of 92.4\% and 94.5% at 4 and 8 false positives per scan in Free Receiver Operating Characteristics (FROC) curve analysis, respectively.

arXiv:1606.07006

Using Word Embeddings in Twitter Election Classification

Word embeddings and convolutional neural networks (CNN) have attracted extensive attention in various classification tasks for Twitter, e.g. sentiment classification. However, the effect of the configuration used to train and generate the word embeddings on the classification performance has not been studied in the existing literature. In this paper, using a Twitter election classification task that aims to detect election-related tweets, we investigate the impact of the background dataset used to train the embedding models, the context window size and the dimensionality of word embeddings on the classification performance. By comparing the classification results of two word embedding models, which are trained using different background corpora (e.g. Wikipedia articles and Twitter microposts), we show that the background data type should align with the Twitter classification dataset to achieve a better performance. Moreover, by evaluating the results of word embeddings models trained using various context window sizes and dimensionalities, we found that large context window and dimension sizes are preferable to improve the performance. Our experimental results also show that using word embeddings and CNN leads to statistically significant improvements over various baselines such as random, SVM with TF-IDF and SVM with word embeddings.

arXiv:1703.08089공식 코드 · Papers with Code

A Bag-of-Words Equivalent Recurrent Neural Network for Action Recognition

The traditional bag-of-words approach has found a wide range of applications in computer vision. The standard pipeline consists of a generation of a visual vocabulary, a quantization of the features into histograms of visual words, and a classification step for which usually a support vector machine in combination with a non-linear kernel is used. Given large amounts of data, however, the model suffers from a lack of discriminative power. This applies particularly for action recognition, where the vast amount of video features needs to be subsampled for unsupervised visual vocabulary generation. Moreover, the kernel computation can be very expensive on large datasets. In this work, we propose a recurrent neural network that is equivalent to the traditional bag-of-words approach but enables for the application of discriminative training. The model further allows to incorporate the kernel computation into the neural network directly, solving the complexity issue and allowing to represent the complete classification system within a single network. We evaluate our method on four recent action recognition benchmarks and show that the conventional model as well as sparse coding methods are outperformed.

arXiv:1703.08033

Generative Adversarial Residual Pairwise Networks for One Shot Learning

Deep neural networks achieve unprecedented performance levels over many tasks and scale well with large quantities of data, but performance in the low-data regime and tasks like one shot learning still lags behind. While recent work suggests many hypotheses from better optimization to more complicated network structures, in this work we hypothesize that having a learnable and more expressive similarity objective is an essential missing component. Towards overcoming that, we propose a network design inspired by deep residual networks that allows the efficient computation of this more expressive pairwise similarity objective. Further, we argue that regularization is key in learning with small amounts of data, and propose an additional generator network based on the Generative Adversarial Networks where the discriminator is our residual pairwise network. This provides a strong regularizer by leveraging the generated data samples. The proposed model can generate plausible variations of exemplars over unseen classes and outperforms strong discriminative baselines for few shot classification tasks. Notably, our residual pairwise network design outperforms previous state-of-theart on the challenging mini-Imagenet dataset for one shot learning by getting over 55% accuracy for the 5-way classification task over unseen classes.

arXiv:1703.07910공식 코드 · Papers with Code

Bidirectional-Convolutional LSTM Based Spectral-Spatial Feature Learning for Hyperspectral Image Classification

This paper proposes a novel deep learning framework named bidirectional-convolutional long short term memory (Bi-CLSTM) network to automatically learn the spectral-spatial feature from hyperspectral images (HSIs). In the network, the issue of spectral feature extraction is considered as a sequence learning problem, and a recurrent connection operator across the spectral domain is used to address it. Meanwhile, inspired from the widely used convolutional neural network (CNN), a convolution operator across the spatial domain is incorporated into the network to extract the spatial feature. Besides, to sufficiently capture the spectral information, a bidirectional recurrent connection is proposed. In the classification phase, the learned features are concatenated into a vector and fed to a softmax classifier via a fully-connected operator. To validate the effectiveness of the proposed Bi-CLSTM framework, we compare it with several state-of-the-art methods, including the CNN framework, on three widely used HSIs. The obtained results show that Bi-CLSTM can improve the classification performance as compared to other methods.

arXiv:1703.07841

Classification-based RNN machine translation using GRUs

We report the results of our classification-based machine translation model, built upon the framework of a recurrent neural network using gated recurrent units. Unlike other RNN models that attempt to maximize the overall conditional log probability of sentences against sentences, our model focuses a classification approach of estimating the conditional probability of the next word given the input sequence. This simpler approach using GRUs was hoped to be comparable with more complicated RNN models, but achievements in this implementation were modest and there remains a lot of room for improving this classification approach.

arXiv:1703.07830

Randomized Kernel Methods for Least-Squares Support Vector Machines

The least-squares support vector machine is a frequently used kernel method for non-linear regression and classification tasks. Here we discuss several approximation algorithms for the least-squares support vector machine classifier. The proposed methods are based on randomized block kernel matrices, and we show that they provide good accuracy and reliable scaling for multi-class classification problems with relatively large data sets. Also, we present several numerical experiments that illustrate the practical applicability of the proposed methods.

arXiv:1703.07771공식 코드 · Papers with Code

Multitask learning and benchmarking with clinical time series data

Health care is one of the most exciting frontiers in data mining and machine learning. Successful adoption of electronic health records (EHRs) created an explosion in digital clinical data available for analysis, but progress in machine learning for healthcare research has been difficult to measure because of the absence of publicly available benchmark data sets. To address this problem, we propose four clinical prediction benchmarks using data derived from the publicly available Medical Information Mart for Intensive Care (MIMIC-III) database. These tasks cover a range of clinical problems including modeling risk of mortality, forecasting length of stay, detecting physiologic decline, and phenotype classification. We propose strong linear and neural baselines for all four tasks and evaluate the effect of deep supervision, multitask training and data-specific architectural modifications on the performance of neural models.