October 20, 2019

3040 words 15 mins read

Paper Group ANR 101

DeepPET: A deep encoder-decoder network for directly solving the PET reconstruction inverse problem. Automatic Speech Recognition for Humanitarian Applications in Somali. Deep Neural Network Aided Scenario Identification in Wireless Multi-path Fading Channels. Simple and Fast Algorithms for Interactive Machine Learning with Random Counter-examples. …

DeepPET: A deep encoder-decoder network for directly solving the PET reconstruction inverse problem


Title	DeepPET: A deep encoder-decoder network for directly solving the PET reconstruction inverse problem
Authors	Ida Häggström, C. Ross Schmidtlein, Gabriele Campanella, Thomas J. Fuchs
Abstract	Positron emission tomography (PET) is a cornerstone of modern radiology. The ability to detect cancer and metastases in whole body scans fundamentally changed cancer diagnosis and treatment. One of the main bottlenecks in the clinical application is the time it takes to reconstruct the anatomical image from the deluge of data in PET imaging. State-of-the art methods based on expectation maximization can take hours for a single patient and depend on manual fine-tuning. This results not only in financial burden for hospitals but more importantly leads to less efficient patient handling, evaluation, and ultimately diagnosis and treatment for patients. To overcome this problem we present a novel PET image reconstruction technique based on a deep convolutional encoder-decoder network, that takes PET sinogram data as input and directly outputs full PET images. Using realistic simulated data, we demonstrate that our network is able to reconstruct images >100 times faster, and with comparable image quality (in terms of root mean squared error) relative to conventional iterative reconstruction techniques.
Tasks	Image Reconstruction
Published	2018-04-20
URL	http://arxiv.org/abs/1804.07851v2
PDF	http://arxiv.org/pdf/1804.07851v2.pdf
PWC	https://paperswithcode.com/paper/deeppet-a-deep-encoder-decoder-network-for
Repo
Framework

Automatic Speech Recognition for Humanitarian Applications in Somali


Title	Automatic Speech Recognition for Humanitarian Applications in Somali
Authors	Raghav Menon, Astik Biswas, Armin Saeb, John Quinn, Thomas Niesler
Abstract	We present our first efforts in building an automatic speech recognition system for Somali, an under-resourced language, using 1.57 hrs of annotated speech for acoustic model training. The system is part of an ongoing effort by the United Nations (UN) to implement keyword spotting systems supporting humanitarian relief programmes in parts of Africa where languages are severely under-resourced. We evaluate several types of acoustic model, including recent neural architectures. Language model data augmentation using a combination of recurrent neural networks (RNN) and long short-term memory neural networks (LSTMs) as well as the perturbation of acoustic data are also considered. We find that both types of data augmentation are beneficial to performance, with our best system using a combination of convolutional neural networks (CNNs), time-delay neural networks (TDNNs) and bi-directional long short term memory (BLSTMs) to achieve a word error rate of 53.75%.
Tasks	Data Augmentation, Keyword Spotting, Language Modelling, Speech Recognition
Published	2018-07-23
URL	http://arxiv.org/abs/1807.08669v1
PDF	http://arxiv.org/pdf/1807.08669v1.pdf
PWC	https://paperswithcode.com/paper/automatic-speech-recognition-for-humanitarian
Repo
Framework

Deep Neural Network Aided Scenario Identification in Wireless Multi-path Fading Channels


Title	Deep Neural Network Aided Scenario Identification in Wireless Multi-path Fading Channels
Authors	Jun Liu, Kai Mei, Dongtang Ma, Jibo Wei
Abstract	This letter illustrates our preliminary works in deep nerual network (DNN) for wireless communication scenario identification in wireless multi-path fading channels. In this letter, six kinds of channel scenarios referring to COST 207 channel model have been performed. 100% identification accuracy has been observed given signal-to-noise (SNR) over 20dB whereas a 88.4% average accuracy has been obtained where SNR ranged from 0dB to 40dB. The proposed method has tested under fast time-varying conditions, which were similar with real world wireless multi-path fading channels, enabling it to work feasibly in practical scenario identification.
Tasks
Published	2018-11-23
URL	http://arxiv.org/abs/1811.09346v1
PDF	http://arxiv.org/pdf/1811.09346v1.pdf
PWC	https://paperswithcode.com/paper/deep-neural-network-aided-scenario
Repo
Framework

Simple and Fast Algorithms for Interactive Machine Learning with Random Counter-examples


Title	Simple and Fast Algorithms for Interactive Machine Learning with Random Counter-examples
Authors	Jagdeep Bhatia
Abstract	This work describes simple and efficient algorithms for interactively learning non-binary concepts in the learning from random counter-examples (LRC) model. Here, learning takes place from random counter-examples that the learner receives in response to their proper equivalence queries. In this context, the learning time is defined as the number of counter-examples needed by the learner to identify the target concept. Such learning is particularly suited for online ranking, classification, clustering, etc., where machine learning models must be used before they are fully trained. We provide two simple LRC algorithms, deterministic and randomized, for exactly learning non-binary target concepts for any concept class $H$. We show that both of these algorithms have an $\mathcal{O}(\log{}H)$ asymptotically optimal average learning time. This solves an open problem on the existence of an efficient LRC randomized algorithm while simplifying and generalizing previous results. We also show that the expected learning time of any arbitrary LRC algorithm can be upper bounded by $\mathcal{O}(\frac{1}{\epsilon}\log{\frac{H}{\delta}})$, where $\epsilon$ and $\delta$ are the allowed learning error and failure probability respectively. This shows that LRC interactive learning is at least as efficient as non-interactive Probably Approximately Correct (PAC) learning. Our simulations show that in practice, these algorithms outperform their theoretical bounds.
Tasks
Published	2018-10-01
URL	https://arxiv.org/abs/1810.00506v2
PDF	https://arxiv.org/pdf/1810.00506v2.pdf
PWC	https://paperswithcode.com/paper/simple-algorithms-for-learning-from-random
Repo
Framework

Relation Mention Extraction from Noisy Data with Hierarchical Reinforcement Learning


Title	Relation Mention Extraction from Noisy Data with Hierarchical Reinforcement Learning
Authors	Jun Feng, Minlie Huang, Yijie Zhang, Yang Yang, Xiaoyan Zhu
Abstract	In this paper we address a task of relation mention extraction from noisy data: extracting representative phrases for a particular relation from noisy sentences that are collected via distant supervision. Despite its significance and value in many downstream applications, this task is less studied on noisy data. The major challenges exists in 1) the lack of annotation on mention phrases, and more severely, 2) handling noisy sentences which do not express a relation at all. To address the two challenges, we formulate the task as a semi-Markov decision process and propose a novel hierarchical reinforcement learning model. Our model consists of a top-level sentence selector to remove noisy sentences, a low-level mention extractor to extract relation mentions, and a reward estimator to provide signals to guide data denoising and mention extraction without explicit annotations. Experimental results show that our model is effective to extract relation mentions from noisy data.
Tasks	Denoising, Hierarchical Reinforcement Learning, Relation Mention Extraction
Published	2018-11-03
URL	http://arxiv.org/abs/1811.01237v1
PDF	http://arxiv.org/pdf/1811.01237v1.pdf
PWC	https://paperswithcode.com/paper/relation-mention-extraction-from-noisy-data
Repo
Framework

Classifying cooking object’s state using a tuned VGG convolutional neural network


Title	Classifying cooking object’s state using a tuned VGG convolutional neural network
Authors	Rahul Paul
Abstract	In robotics, knowing the object states and recognizing the desired states are very important. Objects at different states would require different grasping. To achieve different states, different manipulations would be required, as well as different grasping. To analyze the objects at different states, a dataset of cooking objects was created. Cooking consists of various cutting techniques needed for different dishes (e.g. diced, julienne etc.). Identifying each of this state of cooking objects by the human can be difficult sometimes too. In this paper, we have analyzed seven different cooking object states by tuning a convolutional neural network (CNN). For this task, images were downloaded and annotated by students and they are divided into training and a completely different test set. By tuning the vgg-16 CNN 77% accuracy was obtained. The work presented in this paper focuses on classification between various object states rather than task recognition or recipe prediction. This framework can be easily adapted in any other object state classification activity.
Tasks
Published	2018-05-23
URL	http://arxiv.org/abs/1805.09391v2
PDF	http://arxiv.org/pdf/1805.09391v2.pdf
PWC	https://paperswithcode.com/paper/classifying-cooking-objects-state-using-a
Repo
Framework

Approximate Vanishing Ideal via Data Knotting


Title	Approximate Vanishing Ideal via Data Knotting
Authors	Hiroshi Kera, Yoshihiko Hasegawa
Abstract	The vanishing ideal is a set of polynomials that takes zero value on the given data points. Originally proposed in computer algebra, the vanishing ideal has been recently exploited for extracting the nonlinear structures of data in many applications. To avoid overfitting to noisy data, the polynomials are often designed to approximately rather than exactly equal zero on the designated data. Although such approximations empirically demonstrate high performance, the sound algebraic structure of the vanishing ideal is lost. The present paper proposes a vanishing ideal that is tolerant to noisy data and also pursued to have a better algebraic structure. As a new problem, we simultaneously find a set of polynomials and data points for which the polynomials approximately vanish on the input data points, and almost exactly vanish on the discovered data points. In experimental classification tests, our method discovered much fewer and lower-degree polynomials than an existing state-of-the-art method. Consequently, our method accelerated the runtime of the classification tasks without degrading the classification accuracy.
Tasks
Published	2018-01-29
URL	http://arxiv.org/abs/1801.09367v1
PDF	http://arxiv.org/pdf/1801.09367v1.pdf
PWC	https://paperswithcode.com/paper/approximate-vanishing-ideal-via-data-knotting
Repo
Framework

Optimal Transport on Discrete Domains


Title	Optimal Transport on Discrete Domains
Authors	Justin Solomon
Abstract	Inspired by the matching of supply to demand in logistical problems, the optimal transport (or Monge–Kantorovich) problem involves the matching of probability distributions defined over a geometric domain such as a surface or manifold. In its most obvious discretization, optimal transport becomes a large-scale linear program, which typically is infeasible to solve efficiently on triangle meshes, graphs, point clouds, and other domains encountered in graphics and machine learning. Recent breakthroughs in numerical optimal transport, however, enable scalability to orders-of-magnitude larger problems, solvable in a fraction of a second. Here, we discuss advances in numerical optimal transport that leverage understanding of both discrete and smooth aspects of the problem. State-of-the-art techniques in discrete optimal transport combine insight from partial differential equations (PDE) with convex analysis to reformulate, discretize, and optimize transportation problems. The end result is a set of theoretically-justified models suitable for domains with thousands or millions of vertices. Since numerical optimal transport is a relatively new discipline, special emphasis is placed on identifying and explaining open problems in need of mathematical insight and additional research.
Tasks
Published	2018-01-23
URL	http://arxiv.org/abs/1801.07745v2
PDF	http://arxiv.org/pdf/1801.07745v2.pdf
PWC	https://paperswithcode.com/paper/optimal-transport-on-discrete-domains
Repo
Framework

An Unsupervised Clustering-Based Short-Term Solar Forecasting Methodology Using Multi-Model Machine Learning Blending


Title	An Unsupervised Clustering-Based Short-Term Solar Forecasting Methodology Using Multi-Model Machine Learning Blending
Authors	Cong Feng, Mingjian Cui, Bri-Mathias Hodge, Siyuan Lu, Hendrik F. Hamann, Jie Zhang
Abstract	Solar forecasting accuracy is affected by weather conditions, and weather awareness forecasting models are expected to improve the performance. However, it may not be available and reliable to classify different forecasting tasks by using only meteorological weather categorization. In this paper, an unsupervised clustering-based (UC-based) solar forecasting methodology is developed for short-term (1-hour-ahead) global horizontal irradiance (GHI) forecasting. This methodology consists of three parts: GHI time series unsupervised clustering, pattern recognition, and UC-based forecasting. The daily GHI time series is first clustered by an Optimized Cross-validated ClUsteRing (OCCUR) method, which determines the optimal number of clusters and best clustering results. Then, support vector machine pattern recognition (SVM-PR) is adopted to recognize the category of a certain day using the first few hours’ data in the forecasting stage. GHI forecasts are generated by the most suitable models in different clusters, which are built by a two-layer Machine learning based Multi-Model (M3) forecasting framework. The developed UC-based methodology is validated by using 1-year of data with six solar features. Numerical results show that (i) UC-based models outperform non-UC (all-in-one) models with the same M3 architecture by approximately 20%; (ii) M3-based models also outperform the single-algorithm machine learning (SAML) models by approximately 20%.
Tasks	Time Series
Published	2018-05-10
URL	http://arxiv.org/abs/1805.04193v1
PDF	http://arxiv.org/pdf/1805.04193v1.pdf
PWC	https://paperswithcode.com/paper/an-unsupervised-clustering-based-short-term
Repo
Framework

Joint Estimation of Age and Gender from Unconstrained Face Images using Lightweight Multi-task CNN for Mobile Applications


Title	Joint Estimation of Age and Gender from Unconstrained Face Images using Lightweight Multi-task CNN for Mobile Applications
Authors	Jia-Hong Lee, Yi-Ming Chan, Ting-Yen Chen, Chu-Song Chen
Abstract	Automatic age and gender classification based on unconstrained images has become essential techniques on mobile devices. With limited computing power, how to develop a robust system becomes a challenging task. In this paper, we present an efficient convolutional neural network (CNN) called lightweight multi-task CNN for simultaneous age and gender classification. Lightweight multi-task CNN uses depthwise separable convolution to reduce the model size and save the inference time. On the public challenging Adience dataset, the accuracy of age and gender classification is better than baseline multi-task CNN methods.
Tasks	Age And Gender Classification
Published	2018-06-06
URL	http://arxiv.org/abs/1806.02023v1
PDF	http://arxiv.org/pdf/1806.02023v1.pdf
PWC	https://paperswithcode.com/paper/joint-estimation-of-age-and-gender-from
Repo
Framework

Feature2Mass: Visual Feature Processing in Latent Space for Realistic Labeled Mass Generation


Title	Feature2Mass: Visual Feature Processing in Latent Space for Realistic Labeled Mass Generation
Authors	Jae-Hyeok Lee, Seong Tae Kim, Hakmin Lee, Yong Man Ro
Abstract	This paper deals with a method for generating realistic labeled masses. Recently, there have been many attempts to apply deep learning to various bio-image computing fields including computer-aided detection and diagnosis. In order to learn deep network model to be well-behaved in bio-image computing fields, a lot of labeled data is required. However, in many bioimaging fields, the large-size of labeled dataset is scarcely available. Although a few researches have been dedicated to solving this problem through generative model, there are some problems as follows: 1) The generated bio-image does not seem realistic; 2) the variation of generated bio-image is limited; and 3) additional label annotation task is needed. In this study, we propose a realistic labeled bio-image generation method through visual feature processing in latent space. Experimental results have shown that mass images generated by the proposed method were realistic and had wide expression range of targeted mass characteristics.
Tasks	Image Generation
Published	2018-09-17
URL	http://arxiv.org/abs/1809.06147v2
PDF	http://arxiv.org/pdf/1809.06147v2.pdf
PWC	https://paperswithcode.com/paper/feature2mass-visual-feature-processing-in
Repo
Framework

No Peek: A Survey of private distributed deep learning


Title	No Peek: A Survey of private distributed deep learning
Authors	Praneeth Vepakomma, Tristan Swedish, Ramesh Raskar, Otkrist Gupta, Abhimanyu Dubey
Abstract	We survey distributed deep learning models for training or inference without accessing raw data from clients. These methods aim to protect confidential patterns in data while still allowing servers to train models. The distributed deep learning methods of federated learning, split learning and large batch stochastic gradient descent are compared in addition to private and secure approaches of differential privacy, homomorphic encryption, oblivious transfer and garbled circuits in the context of neural networks. We study their benefits, limitations and trade-offs with regards to computational resources, data leakage and communication efficiency and also share our anticipated future trends.
Tasks
Published	2018-12-08
URL	http://arxiv.org/abs/1812.03288v1
PDF	http://arxiv.org/pdf/1812.03288v1.pdf
PWC	https://paperswithcode.com/paper/no-peek-a-survey-of-private-distributed-deep
Repo
Framework

Vision-based Semantic Mapping and Localization for Autonomous Indoor Parking


Title	Vision-based Semantic Mapping and Localization for Autonomous Indoor Parking
Authors	Yewei Huang, Junqiao Zhao, Xudong He, Shaoming Zhang, Tiantian Feng
Abstract	In this paper, we proposed a novel and practical solution for the real-time indoor localization of autonomous driving in parking lots. High-level landmarks, the parking slots, are extracted and enriched with labels to avoid the aliasing of low-level visual features. We then proposed a robust method for detecting incorrect data associations between parking slots and further extended the optimization framework by dynamically eliminating suboptimal data associations. Visual fiducial markers are introduced to improve the overall precision. As a result, a semantic map of the parking lot can be established fully automatically and robustly. We experimented the performance of real-time localization based on the map using our autonomous driving platform TiEV, and the average accuracy of 0.3m track tracing can be achieved at a speed of 10kph.
Tasks	Autonomous Driving
Published	2018-09-26
URL	http://arxiv.org/abs/1809.09929v1
PDF	http://arxiv.org/pdf/1809.09929v1.pdf
PWC	https://paperswithcode.com/paper/vision-based-semantic-mapping-and
Repo
Framework

From Knowledge Graph Embedding to Ontology Embedding? An Analysis of the Compatibility between Vector Space Representations and Rules


Title	From Knowledge Graph Embedding to Ontology Embedding? An Analysis of the Compatibility between Vector Space Representations and Rules
Authors	Víctor Gutiérrez-Basulto, Steven Schockaert
Abstract	Recent years have witnessed the successful application of low-dimensional vector space representations of knowledge graphs to predict missing facts or find erroneous ones. However, it is not yet well-understood to what extent ontological knowledge, e.g. given as a set of (existential) rules, can be embedded in a principled way. To address this shortcoming, in this paper we introduce a general framework based on a view of relations as regions, which allows us to study the compatibility between ontological knowledge and different types of vector space embeddings. Our technical contribution is two-fold. First, we show that some of the most popular existing embedding methods are not capable of modelling even very simple types of rules, which in particular also means that they are not able to learn the type of dependencies captured by such rules. Second, we study a model in which relations are modelled as convex regions. We show particular that ontologies which are expressed using so-called quasi-chained existential rules can be exactly represented using convex regions, such that any set of facts which is induced using that vector space embedding is logically consistent and deductively closed with respect to the input ontology.
Tasks	Graph Embedding, Knowledge Graph Embedding, Knowledge Graphs
Published	2018-05-26
URL	http://arxiv.org/abs/1805.10461v3
PDF	http://arxiv.org/pdf/1805.10461v3.pdf
PWC	https://paperswithcode.com/paper/from-knowledge-graph-embedding-to-ontology
Repo
Framework

Data Augmentation by Pairing Samples for Images Classification


Title	Data Augmentation by Pairing Samples for Images Classification
Authors	Hiroshi Inoue
Abstract	Data augmentation is a widely used technique in many machine learning tasks, such as image classification, to virtually enlarge the training dataset size and avoid overfitting. Traditional data augmentation techniques for image classification tasks create new samples from the original training data by, for example, flipping, distorting, adding a small amount of noise to, or cropping a patch from an original image. In this paper, we introduce a simple but surprisingly effective data augmentation technique for image classification tasks. With our technique, named SamplePairing, we synthesize a new sample from one image by overlaying another image randomly chosen from the training data (i.e., taking an average of two images for each pixel). By using two images randomly selected from the training set, we can generate $N^2$ new samples from $N$ training samples. This simple data augmentation technique significantly improved classification accuracy for all the tested datasets; for example, the top-1 error rate was reduced from 33.5% to 29.0% for the ILSVRC 2012 dataset with GoogLeNet and from 8.22% to 6.93% in the CIFAR-10 dataset. We also show that our SamplePairing technique largely improved accuracy when the number of samples in the training set was very small. Therefore, our technique is more valuable for tasks with a limited amount of training data, such as medical imaging tasks.
Tasks	Data Augmentation, Image Classification
Published	2018-01-09
URL	http://arxiv.org/abs/1801.02929v2
PDF	http://arxiv.org/pdf/1801.02929v2.pdf
PWC	https://paperswithcode.com/paper/data-augmentation-by-pairing-samples-for
Repo
Framework