July 27, 2019

3259 words 16 mins read

Paper Group ANR 563

Logo Synthesis and Manipulation with Clustered Generative Adversarial Networks. CT Image Denoising with Perceptive Deep Neural Networks. Self-paced Convolutional Neural Network for Computer Aided Detection in Medical Imaging Analysis. Early Experiences with Crowdsourcing Airway Annotations in Chest CT. A User-Study on Online Adaptation of Neural Ma …

Logo Synthesis and Manipulation with Clustered Generative Adversarial Networks


Title	Logo Synthesis and Manipulation with Clustered Generative Adversarial Networks
Authors	Alexander Sage, Eirikur Agustsson, Radu Timofte, Luc Van Gool
Abstract	Designing a logo for a new brand is a lengthy and tedious back-and-forth process between a designer and a client. In this paper we explore to what extent machine learning can solve the creative task of the designer. For this, we build a dataset – LLD – of 600k+ logos crawled from the world wide web. Training Generative Adversarial Networks (GANs) for logo synthesis on such multi-modal data is not straightforward and results in mode collapse for some state-of-the-art methods. We propose the use of synthetic labels obtained through clustering to disentangle and stabilize GAN training. We are able to generate a high diversity of plausible logos and we demonstrate latent space exploration techniques to ease the logo design task in an interactive manner. Moreover, we validate the proposed clustered GAN training on CIFAR 10, achieving state-of-the-art Inception scores when using synthetic labels obtained via clustering the features of an ImageNet classifier. GANs can cope with multi-modal data by means of synthetic labels achieved through clustering, and our results show the creative potential of such techniques for logo synthesis and manipulation. Our dataset and models will be made publicly available at https://data.vision.ee.ethz.ch/cvl/lld/.
Tasks
Published	2017-12-12
URL	http://arxiv.org/abs/1712.04407v1
PDF	http://arxiv.org/pdf/1712.04407v1.pdf
PWC	https://paperswithcode.com/paper/logo-synthesis-and-manipulation-with
Repo
Framework

CT Image Denoising with Perceptive Deep Neural Networks


Title	CT Image Denoising with Perceptive Deep Neural Networks
Authors	Qingsong Yang, Pingkun Yan, Mannudeep K. Kalra, Ge Wang
Abstract	Increasing use of CT in modern medical practice has raised concerns over associated radiation dose. Reduction of radiation dose associated with CT can increase noise and artifacts, which can adversely affect diagnostic confidence. Denoising of low-dose CT images on the other hand can help improve diagnostic confidence, which however is a challenging problem due to its ill-posed nature, since one noisy image patch may correspond to many different output patches. In the past decade, machine learning based approaches have made quite impressive progress in this direction. However, most of those methods, including the recently popularized deep learning techniques, aim for minimizing mean-squared-error (MSE) between a denoised CT image and the ground truth, which results in losing important structural details due to over-smoothing, although the PSNR based performance measure looks great. In this work, we introduce a new perceptual similarity measure as the objective function for a deep convolutional neural network to facilitate CT image denoising. Instead of directly computing MSE for pixel-to-pixel intensity loss, we compare the perceptual features of a denoised output against those of the ground truth in a feature space. Therefore, our proposed method is capable of not only reducing the image noise levels, but also keeping the critical structural information at the same time. Promising results have been obtained in our experiments with a large number of CT images.
Tasks	Denoising, Image Denoising
Published	2017-02-22
URL	http://arxiv.org/abs/1702.07019v1
PDF	http://arxiv.org/pdf/1702.07019v1.pdf
PWC	https://paperswithcode.com/paper/ct-image-denoising-with-perceptive-deep
Repo
Framework

Self-paced Convolutional Neural Network for Computer Aided Detection in Medical Imaging Analysis


Title	Self-paced Convolutional Neural Network for Computer Aided Detection in Medical Imaging Analysis
Authors	Xiang Li, Aoxiao Zhong, Ming Lin, Ning Guo, Mu Sun, Arkadiusz Sitek, Jieping Ye, James Thrall, Quanzheng Li
Abstract	Tissue characterization has long been an important component of Computer Aided Diagnosis (CAD) systems for automatic lesion detection and further clinical planning. Motivated by the superior performance of deep learning methods on various computer vision problems, there has been increasing work applying deep learning to medical image analysis. However, the development of a robust and reliable deep learning model for computer-aided diagnosis is still highly challenging due to the combination of the high heterogeneity in the medical images and the relative lack of training samples. Specifically, annotation and labeling of the medical images is much more expensive and time-consuming than other applications and often involves manual labor from multiple domain experts. In this work, we propose a multi-stage, self-paced learning framework utilizing a convolutional neural network (CNN) to classify Computed Tomography (CT) image patches. The key contribution of this approach is that we augment the size of training samples by refining the unlabeled instances with a self-paced learning CNN. By implementing the framework on high performance computing servers including the NVIDIA DGX1 machine, we obtained the experimental result, showing that the self-pace boosted network consistently outperformed the original network even with very scarce manual labels. The performance gain indicates that applications with limited training samples such as medical image analysis can benefit from using the proposed framework.
Tasks	Computed Tomography (CT)
Published	2017-07-19
URL	http://arxiv.org/abs/1707.06145v1
PDF	http://arxiv.org/pdf/1707.06145v1.pdf
PWC	https://paperswithcode.com/paper/self-paced-convolutional-neural-network-for
Repo
Framework

Early Experiences with Crowdsourcing Airway Annotations in Chest CT


Title	Early Experiences with Crowdsourcing Airway Annotations in Chest CT
Authors	Veronika Cheplygina, Adria Perez-Rovira, Wieying Kuo, Harm A. W. M. Tiddens, Marleen de Bruijne
Abstract	Measuring airways in chest computed tomography (CT) images is important for characterizing diseases such as cystic fibrosis, yet very time-consuming to perform manually. Machine learning algorithms offer an alternative, but need large sets of annotated data to perform well. We investigate whether crowdsourcing can be used to gather airway annotations which can serve directly for measuring the airways, or as training data for the algorithms. We generate image slices at known locations of airways and request untrained crowd workers to outline the airway lumen and airway wall. Our results show that the workers are able to interpret the images, but that the instructions are too complex, leading to many unusable annotations. After excluding unusable annotations, quantitative results show medium to high correlations with expert measurements of the airways. Based on this positive experience, we describe a number of further research directions and provide insight into the challenges of crowdsourcing in medical images from the perspective of first-time users.
Tasks	Computed Tomography (CT)
Published	2017-06-07
URL	http://arxiv.org/abs/1706.02055v1
PDF	http://arxiv.org/pdf/1706.02055v1.pdf
PWC	https://paperswithcode.com/paper/early-experiences-with-crowdsourcing-airway
Repo
Framework

A User-Study on Online Adaptation of Neural Machine Translation to Human Post-Edits


Title	A User-Study on Online Adaptation of Neural Machine Translation to Human Post-Edits
Authors	Sariya Karimova, Patrick Simianer, Stefan Riezler
Abstract	The advantages of neural machine translation (NMT) have been extensively validated for offline translation of several language pairs for different domains of spoken and written language. However, research on interactive learning of NMT by adaptation to human post-edits has so far been confined to simulation experiments. We present the first user study on online adaptation of NMT to user post-edits in the domain of patent translation. Our study involves 29 human subjects (translation students) whose post-editing effort and translation quality were measured on about 4,500 interactions of a human post-editor and a machine translation system integrating an online adaptive learning algorithm. Our experimental results show a significant reduction of human post-editing effort due to online adaptation in NMT according to several evaluation metrics, including hTER, hBLEU, and KSMR. Furthermore, we found significant improvements in BLEU/TER between NMT outputs and professional translations in granted patents, providing further evidence for the advantages of online adaptive NMT in an interactive setup.
Tasks	Machine Translation
Published	2017-12-13
URL	http://arxiv.org/abs/1712.04853v3
PDF	http://arxiv.org/pdf/1712.04853v3.pdf
PWC	https://paperswithcode.com/paper/a-user-study-on-online-adaptation-of-neural
Repo
Framework

Classification of Smartphone Users Using Internet Traffic


Title	Classification of Smartphone Users Using Internet Traffic
Authors	Andrey Finkelstein, Ron Biton, Rami Puzis, Asaf Shabtai
Abstract	Today, smartphone devices are owned by a large portion of the population and have become a very popular platform for accessing the Internet. Smartphones provide the user with immediate access to information and services. However, they can easily expose the user to many privacy risks. Applications that are installed on the device and entities with access to the device’s Internet traffic can reveal private information about the smartphone user and steal sensitive content stored on the device or transmitted by the device over the Internet. In this paper, we present a method to reveal various demographics and technical computer skills of smartphone users by their Internet traffic records, using machine learning classification models. We implement and evaluate the method on real life data of smartphone users and show that smartphone users can be classified by their gender, smoking habits, software programming experience, and other characteristics.
Tasks
Published	2017-01-01
URL	http://arxiv.org/abs/1701.00220v1
PDF	http://arxiv.org/pdf/1701.00220v1.pdf
PWC	https://paperswithcode.com/paper/classification-of-smartphone-users-using
Repo
Framework

Vision Based Railway Track Monitoring using Deep Learning


Title	Vision Based Railway Track Monitoring using Deep Learning
Authors	Shruti Mittal, Dattaraj Rao
Abstract	Computer vision based methods have been explored in the past for detection of railway track defects, but full automation has always been a challenge because both traditional image processing methods and deep learning classifiers trained from scratch fail to generalize that well to infinite novel scenarios seen in the real world, given limited amount of labeled data. Advancements have been made recently to make machine learning models utilize knowledge from a different but related domain. In this paper, we show that even though similar domain data is not available, transfer learning provides the model understanding of other real world objects and enables training production scale deep learning classifiers for uncontrolled real world data. Our models efficiently detect both track defects like sunkinks, loose ballast and railway assets like switches and signals. Models were validated with hours of track videos recorded in different continents resulting in different weather conditions, different ambience and surroundings. A track health index concept has also been proposed to monitor complete rail network.
Tasks	Transfer Learning
Published	2017-11-17
URL	http://arxiv.org/abs/1711.06423v2
PDF	http://arxiv.org/pdf/1711.06423v2.pdf
PWC	https://paperswithcode.com/paper/vision-based-railway-track-monitoring-using
Repo
Framework

The Case for Meta-Cognitive Machine Learning: On Model Entropy and Concept Formation in Deep Learning


Title	The Case for Meta-Cognitive Machine Learning: On Model Entropy and Concept Formation in Deep Learning
Authors	Johan Loeckx
Abstract	Machine learning is usually defined in behaviourist terms, where external validation is the primary mechanism of learning. In this paper, I argue for a more holistic interpretation in which finding more probable, efficient and abstract representations is as central to learning as performance. In other words, machine learning should be extended with strategies to reason over its own learning process, leading to so-called meta-cognitive machine learning. As such, the de facto definition of machine learning should be reformulated in these intrinsically multi-objective terms, taking into account not only the task performance but also internal learning objectives. To this end, we suggest a “model entropy function” to be defined that quantifies the efficiency of the internal learning processes. It is conjured that the minimization of this model entropy leads to concept formation. Besides philosophical aspects, some initial illustrations are included to support the claims.
Tasks
Published	2017-11-04
URL	http://arxiv.org/abs/1711.01431v1
PDF	http://arxiv.org/pdf/1711.01431v1.pdf
PWC	https://paperswithcode.com/paper/the-case-for-meta-cognitive-machine-learning
Repo
Framework

Learning Identifiable Gaussian Bayesian Networks in Polynomial Time and Sample Complexity


Title	Learning Identifiable Gaussian Bayesian Networks in Polynomial Time and Sample Complexity
Authors	Asish Ghoshal, Jean Honorio
Abstract	Learning the directed acyclic graph (DAG) structure of a Bayesian network from observational data is a notoriously difficult problem for which many hardness results are known. In this paper we propose a provably polynomial-time algorithm for learning sparse Gaussian Bayesian networks with equal noise variance — a class of Bayesian networks for which the DAG structure can be uniquely identified from observational data — under high-dimensional settings. We show that $O(k^4 \log p)$ number of samples suffices for our method to recover the true DAG structure with high probability, where $p$ is the number of variables and $k$ is the maximum Markov blanket size. We obtain our theoretical guarantees under a condition called Restricted Strong Adjacency Faithfulness, which is strictly weaker than strong faithfulness — a condition that other methods based on conditional independence testing need for their success. The sample complexity of our method matches the information-theoretic limits in terms of the dependence on $p$. We show that our method out-performs existing state-of-the-art methods for learning Gaussian Bayesian networks in terms of recovering the true DAG structure while being comparable in speed to heuristic methods.
Tasks
Published	2017-03-03
URL	http://arxiv.org/abs/1703.01196v1
PDF	http://arxiv.org/pdf/1703.01196v1.pdf
PWC	https://paperswithcode.com/paper/learning-identifiable-gaussian-bayesian
Repo
Framework

Learning Invariant Feature Spaces to Transfer Skills with Reinforcement Learning


Title	Learning Invariant Feature Spaces to Transfer Skills with Reinforcement Learning
Authors	Abhishek Gupta, Coline Devin, YuXuan Liu, Pieter Abbeel, Sergey Levine
Abstract	People can learn a wide range of tasks from their own experience, but can also learn from observing other creatures. This can accelerate acquisition of new skills even when the observed agent differs substantially from the learning agent in terms of morphology. In this paper, we examine how reinforcement learning algorithms can transfer knowledge between morphologically different agents (e.g., different robots). We introduce a problem formulation where two agents are tasked with learning multiple skills by sharing information. Our method uses the skills that were learned by both agents to train invariant feature spaces that can then be used to transfer other skills from one agent to another. The process of learning these invariant feature spaces can be viewed as a kind of “analogy making”, or implicit learning of partial correspondences between two distinct domains. We evaluate our transfer learning algorithm in two simulated robotic manipulation skills, and illustrate that we can transfer knowledge between simulated robotic arms with different numbers of links, as well as simulated arms with different actuation mechanisms, where one robot is torque-driven while the other is tendon-driven.
Tasks	Transfer Learning
Published	2017-03-08
URL	http://arxiv.org/abs/1703.02949v1
PDF	http://arxiv.org/pdf/1703.02949v1.pdf
PWC	https://paperswithcode.com/paper/learning-invariant-feature-spaces-to-transfer
Repo
Framework

Detection of Unauthorized IoT Devices Using Machine Learning Techniques


Title	Detection of Unauthorized IoT Devices Using Machine Learning Techniques
Authors	Yair Meidan, Michael Bohadana, Asaf Shabtai, Martin Ochoa, Nils Ole Tippenhauer, Juan Davis Guarnizo, Yuval Elovici
Abstract	Security experts have demonstrated numerous risks imposed by Internet of Things (IoT) devices on organizations. Due to the widespread adoption of such devices, their diversity, standardization obstacles, and inherent mobility, organizations require an intelligent mechanism capable of automatically detecting suspicious IoT devices connected to their networks. In particular, devices not included in a white list of trustworthy IoT device types (allowed to be used within the organizational premises) should be detected. In this research, Random Forest, a supervised machine learning algorithm, was applied to features extracted from network traffic data with the aim of accurately identifying IoT device types from the white list. To train and evaluate multi-class classifiers, we collected and manually labeled network traffic data from 17 distinct IoT devices, representing nine types of IoT devices. Based on the classification of 20 consecutive sessions and the use of majority rule, IoT device types that are not on the white list were correctly detected as unknown in 96% of test cases (on average), and white listed device types were correctly classified by their actual types in 99% of cases. Some IoT device types were identified quicker than others (e.g., sockets and thermostats were successfully detected within five TCP sessions of connecting to the network). Perfect detection of unauthorized IoT device types was achieved upon analyzing 110 consecutive sessions; perfect classification of white listed types required 346 consecutive sessions, 110 of which resulted in 99.49% accuracy. Further experiments demonstrated the successful applicability of classifiers trained in one location and tested on another. In addition, a discussion is provided regarding the resilience of our machine learning-based IoT white listing method to adversarial attacks.
Tasks
Published	2017-09-14
URL	http://arxiv.org/abs/1709.04647v1
PDF	http://arxiv.org/pdf/1709.04647v1.pdf
PWC	https://paperswithcode.com/paper/detection-of-unauthorized-iot-devices-using
Repo
Framework

Automatic Detection of Knee Joints and Quantification of Knee Osteoarthritis Severity using Convolutional Neural Networks


Title	Automatic Detection of Knee Joints and Quantification of Knee Osteoarthritis Severity using Convolutional Neural Networks
Authors	Joseph Antony, Kevin McGuinness, Kieran Moran, Noel E O’Connor
Abstract	This paper introduces a new approach to automatically quantify the severity of knee OA using X-ray images. Automatically quantifying knee OA severity involves two steps: first, automatically localizing the knee joints; next, classifying the localized knee joint images. We introduce a new approach to automatically detect the knee joints using a fully convolutional neural network (FCN). We train convolutional neural networks (CNN) from scratch to automatically quantify the knee OA severity optimizing a weighted ratio of two loss functions: categorical cross-entropy and mean-squared loss. This joint training further improves the overall quantification of knee OA severity, with the added benefit of naturally producing simultaneous multi-class classification and regression outputs. Two public datasets are used to evaluate our approach, the Osteoarthritis Initiative (OAI) and the Multicenter Osteoarthritis Study (MOST), with extremely promising results that outperform existing approaches.
Tasks
Published	2017-03-29
URL	http://arxiv.org/abs/1703.09856v1
PDF	http://arxiv.org/pdf/1703.09856v1.pdf
PWC	https://paperswithcode.com/paper/automatic-detection-of-knee-joints-and
Repo
Framework

How ConvNets model Non-linear Transformations


Title	How ConvNets model Non-linear Transformations
Authors	Dipan K. Pal, Marios Savvides
Abstract	In this paper, we theoretically address three fundamental problems involving deep convolutional networks regarding invariance, depth and hierarchy. We introduce the paradigm of Transformation Networks (TN) which are a direct generalization of Convolutional Networks (ConvNets). Theoretically, we show that TNs (and thereby ConvNets) are can be invariant to non-linear transformations of the input despite pooling over mere local translations. Our analysis provides clear insights into the increase in invariance with depth in these networks. Deeper networks are able to model much richer classes of transformations. We also find that a hierarchical architecture allows the network to generate invariance much more efficiently than a non-hierarchical network. Our results provide useful insight into these three fundamental problems in deep learning using ConvNets.
Tasks
Published	2017-02-24
URL	http://arxiv.org/abs/1702.07664v1
PDF	http://arxiv.org/pdf/1702.07664v1.pdf
PWC	https://paperswithcode.com/paper/how-convnets-model-non-linear-transformations
Repo
Framework

Whodunnit? Crime Drama as a Case for Natural Language Understanding


Title	Whodunnit? Crime Drama as a Case for Natural Language Understanding
Authors	Lea Frermann, Shay B. Cohen, Mirella Lapata
Abstract	In this paper we argue that crime drama exemplified in television programs such as CSI:Crime Scene Investigation is an ideal testbed for approximating real-world natural language understanding and the complex inferences associated with it. We propose to treat crime drama as a new inference task, capitalizing on the fact that each episode poses the same basic question (i.e., who committed the crime) and naturally provides the answer when the perpetrator is revealed. We develop a new dataset based on CSI episodes, formalize perpetrator identification as a sequence labeling problem, and develop an LSTM-based model which learns from multi-modal data. Experimental results show that an incremental inference strategy is key to making accurate guesses as well as learning from representations fusing textual, visual, and acoustic input.
Tasks
Published	2017-10-31
URL	http://arxiv.org/abs/1710.11601v1
PDF	http://arxiv.org/pdf/1710.11601v1.pdf
PWC	https://paperswithcode.com/paper/whodunnit-crime-drama-as-a-case-for-natural
Repo
Framework

Discriminative Transformation Learning for Fuzzy Sparse Subspace Clustering


Title	Discriminative Transformation Learning for Fuzzy Sparse Subspace Clustering
Authors	Zaidao Wen, Biao Hou, Qian Wu, Licheng Jiao
Abstract	This paper develops a novel iterative framework for subspace clustering in a learned discriminative feature domain. This framework consists of two modules of fuzzy sparse subspace clustering and discriminative transformation learning. In the first module, fuzzy latent labels containing discriminative information and latent representations capturing the subspace structure will be simultaneously evaluated in a feature domain. Then the linear transforming operator with respect to the feature domain will be successively updated in the second module with the advantages of more discrimination, subspace structure preservation and robustness to outliers. These two modules will be alternatively carried out and both theoretical analysis and empirical evaluations will demonstrate its effectiveness and superiorities. In particular, experimental results on three benchmark databases for subspace clustering clearly illustrate that the proposed framework can achieve significant improvements than other state-of-the-art approaches in terms of clustering accuracy.
Tasks
Published	2017-07-18
URL	http://arxiv.org/abs/1707.05446v1
PDF	http://arxiv.org/pdf/1707.05446v1.pdf
PWC	https://paperswithcode.com/paper/discriminative-transformation-learning-for
Repo
Framework