PyTorchKR Papers

최신 논문

총 12,350편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1806.07908

Como funciona o Deep Learning

Deep Learning methods are currently the state-of-the-art in many problems which can be tackled via machine learning, in particular classification problems. However there is still lack of understanding on how those methods work, why they work and what are the limitations involved in using them. In this chapter we will describe in detail the transition from shallow to deep networks, include examples of code on how to implement them, as well as the main issues one faces when training a deep network. Afterwards, we introduce some theoretical background behind the use of deep models, and discuss their limitations.

arXiv:1806.08340

Interpretable Discovery in Large Image Data Sets

Automated detection of new, interesting, unusual, or anomalous images within large data sets has great value for applications from surveillance (e.g., airport security) to science (observations that don't fit a given theory can lead to new discoveries). Many image data analysis systems are turning to convolutional neural networks (CNNs) to represent image content due to their success in achieving high classification accuracy rates. However, CNN representations are notoriously difficult for humans to interpret. We describe a new strategy that combines novelty detection with CNN image features to achieve rapid discovery with interpretable explanations of novel image content. We applied this technique to familiar images from ImageNet as well as to a scientific image collection from planetary science.

arXiv:1806.08279

Don't only Feel Read: Using Scene text to understand advertisements

We propose a framework for automated classification of Advertisement Images, using not just Visual features but also Textual cues extracted from embedded text. Our approach takes inspiration from the assumption that Ad images contain meaningful textual content, that can provide discriminative semantic interpretetion, and can thus aid in classifcation tasks. To this end, we develop a framework using off-the-shelf components, and demonstrate the effectiveness of Textual cues in semantic Classfication tasks.

arXiv:1806.08251공식 코드 · Papers with Code

Learning Multimodal Representations for Unseen Activities

We present a method to learn a joint multimodal representation space that enables recognition of unseen activities in videos. We first compare the effect of placing various constraints on the embedding space using paired text and video data. We also propose a method to improve the joint embedding space using an adversarial formulation, allowing it to benefit from unpaired text and video data. By using unpaired text data, we show the ability to learn a representation that better captures unseen activities. In addition to testing on publicly available datasets, we introduce a new, large-scale text/video dataset. We experimentally confirm that using paired and unpaired data to learn a shared embedding space benefits three difficult tasks (i) zero-shot activity classification, (ii) unsupervised activity discovery, and (iii) unseen activity captioning, outperforming the state-of-the-arts.

arXiv:1806.08247

Log Skeletons: A Classification Approach to Process Discovery

To test the effectiveness of process discovery algorithms, a Process Discovery Contest (PDC) has been set up. This PDC uses a classification approach to measure this effectiveness: The better the discovered model can classify whether or not a new trace conforms to the event log, the better the discovery algorithm is supposed to be. Unfortunately, even the state-of-the-art fully-automated discovery algorithms score poorly on this classification. Even the best of these algorithms, the Inductive Miner, scored only 147 correct classified traces out of 200 traces on the PDC of 2017. This paper introduces the rule-based log skeleton model, which is closely related to the Declare constraint model, together with a way to classify traces using this model. This classification using log skeletons is shown to score better on the PDC of 2017 than state-of-the-art discovery algorithms: 194 out of 200. As a result, one can argue that the fully-automated algorithm to construct (or: discover) a log skeleton from an event log outperforms existing state-of-the-art fully-automated discovery algorithms.

arXiv:1806.07787

Opinion Dynamics Modeling for Movie Review Transcripts Classification with Hidden Conditional Random Fields

In this paper, the main goal is to detect a movie reviewer's opinion using hidden conditional random fields. This model allows us to capture the dynamics of the reviewer's opinion in the transcripts of long unsegmented audio reviews that are analyzed by our system. High level linguistic features are computed at the level of inter-pausal segments. The features include syntactic features, a statistical word embedding model and subjectivity lexicons. The proposed system is evaluated on the ICT-MMMO corpus. We obtain a F1-score of 82\%, which is better than logistic regression and recurrent neural network approaches. We also offer a discussion that sheds some light on the capacity of our system to adapt the word embedding model learned from general written texts data to spoken movie reviews and thus model the dynamics of the opinion.

arXiv:1806.07754

Spatio-Temporal Channel Correlation Networks for Action Classification

The work in this paper is driven by the question if spatio-temporal correlations are enough for 3D convolutional neural networks (CNN)? Most of the traditional 3D networks use local spatio-temporal features. We introduce a new block that models correlations between channels of a 3D CNN with respect to temporal and spatial features. This new block can be added as a residual unit to different parts of 3D CNNs. We name our novel block 'Spatio-Temporal Channel Correlation' (STC). By embedding this block to the current state-of-the-art architectures such as ResNext and ResNet, we improved the performance by 2-3\% on Kinetics dataset. Our experiments show that adding STC blocks to current state-of-the-art architectures outperforms the state-of-the-art methods on the HMDB51, UCF101 and Kinetics datasets. The other issue in training 3D CNNs is about training them from scratch with a huge labeled dataset to get a reasonable performance. So the knowledge learned in 2D CNNs is completely ignored. Another contribution in this work is a simple and effective technique to transfer knowledge from a pre-trained 2D CNN to a randomly initialized 3D CNN for a stable weight initialization. This allows us to significantly reduce the number of training samples for 3D CNNs. Thus, by fine-tuning this network, we beat the performance of generic and recent methods in 3D CNNs, which were trained on large video datasets, e.g. Sports-1M, and fine-tuned on the target datasets, e.g. HMDB51/UCF101.

arXiv:1806.07751

Versatile Auxiliary Classifier with Generative Adversarial Network (VAC+GAN), Multi Class Scenarios

Conditional generators learn the data distribution for each class in a multi-class scenario and generate samples for a specific class given the right input from the latent space. In this work, a method known as "Versatile Auxiliary Classifier with Generative Adversarial Network" for multi-class scenarios is presented. In this technique, the Generative Adversarial Networks (GAN)'s generator is turned into a conditional generator by placing a multi-class classifier in parallel with the discriminator network and backpropagate the classification error through the generator. This technique is versatile enough to be applied to any GAN implementation. The results on two databases and comparisons with other method are provided as well.

arXiv:1806.07745

Deep Learning Classification of 3.5 GHz Band Spectrograms with Applications to Spectrum Sensing

In the United States, the Federal Communications Commission has adopted rules permitting commercial wireless networks to share spectrum with federal incumbents in the 3.5~GHz Citizens Broadband Radio Service band. These rules require commercial systems to vacate the band when sensors detect radars operated by the U.S. military; a key example being the SPN-43 air traffic control radar. Such sensors require highly-accurate detection algorithms to meet their operating requirements. In this paper, using a library of over 14,000 3.5~GHz band spectrograms collected by a recent measurement campaign, we investigate the performance of thirteen methods for SPN-43 radar detection. Namely, we compare classical methods from signal detection theory and machine learning to several deep learning architectures. We demonstrate that machine learning algorithms appreciably outperform classical signal detection methods. Specifically, we find that a three-layer convolutional neural network offers a superior tradeoff between accuracy and computational complexity. Last, we apply this three-layer network to generate descriptive statistics for the full 3.5~GHz spectrogram library. Our findings highlight potential weaknesses of classical methods and strengths of modern machine learning algorithms for radar detection in the 3.5~GHz band.

arXiv:1806.07721

Semantic Relation Classification: Task Formalisation and Refinement

The identification of semantic relations between terms within texts is a fundamental task in Natural Language Processing which can support applications requiring a lightweight semantic interpretation model. Currently, semantic relation classification concentrates on relations which are evaluated over open-domain data. This work provides a critique on the set of abstract relations used for semantic relation classification with regard to their ability to express relationships between terms which are found in a domain-specific corpora. Based on this analysis, this work proposes an alternative semantic relation model based on reusing and extending the set of abstract relations present in the DOLCE ontology. The resulting set of relations is well grounded, allows to capture a wide range of relations and could thus be used as a foundation for automatic classification of semantic relations.

arXiv:1806.07697

Self-weighted Multiple Kernel Learning for Graph-based Clustering and Semi-supervised Classification

Multiple kernel learning (MKL) method is generally believed to perform better than single kernel method. However, some empirical studies show that this is not always true: the combination of multiple kernels may even yield an even worse performance than using a single kernel. There are two possible reasons for the failure: (i) most existing MKL methods assume that the optimal kernel is a linear combination of base kernels, which may not hold true; and (ii) some kernel weights are inappropriately assigned due to noises and carelessly designed algorithms. In this paper, we propose a novel MKL framework by following two intuitive assumptions: (i) each kernel is a perturbation of the consensus kernel; and (ii) the kernel that is close to the consensus kernel should be assigned a large weight. Impressively, the proposed method can automatically assign an appropriate weight to each kernel without introducing additional parameters, as existing methods do. The proposed framework is integrated into a unified framework for graph-based clustering and semi-supervised classification. We have conducted experiments on multiple benchmark datasets and our empirical results verify the superiority of the proposed framework.

arXiv:1806.07690

Non-Parametric Calibration of Probabilistic Regression

The task of calibration is to retrospectively adjust the outputs from a machine learning model to provide better probability estimates on the target variable. While calibration has been investigated thoroughly in classification, it has not yet been well-established for regression tasks. This paper considers the problem of calibrating a probabilistic regression model to improve the estimated probability densities over the real-valued targets. We propose to calibrate a regression model through the cumulative probability density, which can be derived from calibrating a multi-class classifier. We provide three non-parametric approaches to solve the problem, two of which provide empirical estimates and the third providing smooth density estimates. The proposed approaches are experimentally evaluated to show their ability to improve the performance of regression models on the predictive likelihood.

arXiv:1806.07688

DEFRAG: Deep Euclidean Feature Representations through Adaptation on the Grassmann Manifold

We propose a novel technique for training deep networks with the objective of obtaining feature representations that exist in a Euclidean space and exhibit strong clustering behavior. Our desired features representations have three traits: they can be compared using a standard Euclidian distance metric, samples from the same class are tightly clustered, and samples from different classes are well separated. However, most deep networks do not enforce such feature representations. The DEFRAG training technique consists of two steps: first good feature clustering behavior is encouraged though an auxiliary loss function based on the Silhouette clustering metric. Then the feature space is retracted onto a Grassmann manifold to ensure that the L_2 Norm forms a similarity metric. The DEFRAG technique achieves state of the art results on standard classification datasets using a relatively small network architecture with significantly fewer parameters than many standard networks.

arXiv:1806.07506

A Simple Fusion of Deep and Shallow Learning for Acoustic Scene Classification

In the past, Acoustic Scene Classification systems have been based on hand crafting audio features that are input to a classifier. Nowadays, the common trend is to adopt data driven techniques, e.g., deep learning, where audio representations are learned from data. In this paper, we propose a system that consists of a simple fusion of two methods of the aforementioned types: a deep learning approach where log-scaled mel-spectrograms are input to a convolutional neural network, and a feature engineering approach, where a collection of hand-crafted features is input to a gradient boosting machine. We first show that both methods provide complementary information to some extent. Then, we use a simple late fusion strategy to combine both methods. We report classification accuracy of each method individually and the combined system on the TUT Acoustic Scenes 2017 dataset. The proposed fused system outperforms each of the individual methods and attains a classification accuracy of 72.8% on the evaluation set, improving the baseline system by 11.8%.

arXiv:1806.07489

Towards the identification of Parkinson's Disease using only T1 MR Images

Parkinson's Disease (PD) is one of the most common types of neurological diseases caused by progressive degeneration of dopamin- ergic neurons in the brain. Even though there is no fixed cure for this neurodegenerative disease, earlier diagnosis followed by earlier treatment can help patients have a better quality of life. Magnetic Resonance Imag- ing (MRI) has been one of the most popular diagnostic tool in recent years because it avoids harmful radiations. In this paper, we investi- gate the plausibility of using MRIs for automatically diagnosing PD. Our proposed method has three main steps : 1) Preprocessing, 2) Fea- ture Extraction, and 3) Classification. The FreeSurfer library is used for the first and the second steps. For classification, three main types of classifiers, including Logistic Regression (LR), Random Forest (RF) and Support Vector Machine (SVM), are applied and their classification abil- ity is compared. The Parkinsons Progression Markers Initiative (PPMI) data set is used to evaluate the proposed method. The proposed system prove to be promising in assisting the diagnosis of PD.

arXiv:1806.07470

Contrastive Explanations with Local Foil Trees

Recent advances in interpretable Machine Learning (iML) and eXplainable AI (XAI) construct explanations based on the importance of features in classification tasks. However, in a high-dimensional feature space this approach may become unfeasible without restraining the set of important features. We propose to utilize the human tendency to ask questions like "Why this output (the fact) instead of that output (the foil)?" to reduce the number of features to those that play a main role in the asked contrast. Our proposed method utilizes locally trained one-versus-all decision trees to identify the disjoint set of rules that causes the tree to classify data points as the foil and not as the fact. In this study we illustrate this approach on three benchmark classification tasks.

arXiv:1806.07416

Fast CapsNet for Lung Cancer Screening

Lung cancer is the leading cause of cancer-related deaths in the past several years. A major challenge in lung cancer screening is the detection of lung nodules from computed tomography (CT) scans. State-of-the-art approaches in automated lung nodule classification use deep convolutional neural networks (CNNs). However, these networks require a large number of training samples to generalize well. This paper investigates the use of capsule networks (CapsNets) as an alternative to CNNs. We show that CapsNets significantly outperforms CNNs when the number of training samples is small. To increase the computational efficiency, our paper proposes a consistent dynamic routing mechanism that results in $3\times$ speedup of CapsNet. Finally, we show that the original image reconstruction method of CapNets performs poorly on lung nodule data. We propose an efficient alternative, called convolutional decoder, that yields lower reconstruction error and higher classification accuracy.

arXiv:1806.07379

DeepTerramechanics: Terrain Classification and Slip Estimation for Ground Robots via Deep Learning

Terramechanics plays a critical role in the areas of ground vehicles and ground mobile robots since understanding and estimating the variables influencing the vehicle-terrain interaction may mean the success or the failure of an entire mission. This research applies state-of-the-art algorithms in deep learning to two key problems: estimating wheel slip and classifying the terrain being traversed by a ground robot. Three data sets collected by ground robotic platforms (MIT single-wheel testbed, MSL Curiosity rover, and tracked robot Fitorobot) are employed in order to compare the performance of traditional machine learning methods (i.e. Support Vector Machine (SVM) and Multi-layer Perceptron (MLP)) against Deep Neural Networks (DNNs) and Convolutional Neural Networks (CNNs). This work also shows the impact that certain tuning parameters and the network architecture (MLP, DNN and CNN) play on the performance of those methods. This paper also contributes a deep discussion with the lessons learned in the implementation of DNNs and CNNs and how these methods can be extended to solve other problems.

arXiv:1806.07073

Transfer Learning with Human Corneal Tissues: An Analysis of Optimal Cut-Off Layer

Transfer learning is a powerful tool to adapt trained neural networks to new tasks. Depending on the similarity of the original task to the new task, the selection of the cut-off layer is critical. For medical applications like tissue classification, the last layers of an object classification network might not be optimal. We found that on real data of human corneal tissues the best feature representation can be found in the middle layers of the Inception-v3 and in the rear layers of the VGG-19 architecture.

arXiv:1806.07039

EmotionX-DLC: Self-Attentive BiLSTM for Detecting Sequential Emotions in Dialogue

In this paper, we propose a self-attentive bidirectional long short-term memory (SA-BiLSTM) network to predict multiple emotions for the EmotionX challenge. The BiLSTM exhibits the power of modeling the word dependencies, and extracting the most relevant features for emotion classification. Building on top of BiLSTM, the self-attentive network can model the contextual dependencies between utterances which are helpful for classifying the ambiguous emotions. We achieve 59.6 and 55.0 unweighted accuracy scores in the \textit{Friends} and the \textit{EmotionPush} test sets, respectively.