October 16, 2019

3185 words 15 mins read

Paper Group ANR 974

Unsupervised/Semi-supervised Deep Learning for Low-dose CT Enhancement. Matrix Product Operator Restricted Boltzmann Machines. Tree Morphology for Phenotyping from Semantics-Based Mapping in Orchard Environments. CariGAN: Caricature Generation through Weakly Paired Adversarial Learning. EventKG: A Multilingual Event-Centric Temporal Knowledge Graph …

Unsupervised/Semi-supervised Deep Learning for Low-dose CT Enhancement


Title	Unsupervised/Semi-supervised Deep Learning for Low-dose CT Enhancement
Authors	Mingrui Geng, Yun Deng, Qian Zhao, Qi Xie, Dong Zeng, Dong Zeng, Wangmeng Zuo, Deyu Meng
Abstract	Recently, deep learning(DL) methods have been proposed for the low-dose computed tomography(LdCT) enhancement, and obtain good trade-off between computational efficiency and image quality. Most of them need large number of pre-collected ground-truth/high-dose sinograms with less noise, and train the network in a supervised end-to-end manner. This may bring major limitations on these methods because the number of such low-dose/high-dose training sinogram pairs would affect the network’s capability and sometimes the ground-truth sinograms are hard to be obtained in large scale. Since large number of low-dose ones are relatively easy to obtain, it should be critical to make these sources play roles in network training in an unsupervised learning manner. To address this issue, we propose an unsupervised DL method for LdCT enhancement that incorporates unlabeled LdCT sinograms directly into the network training. The proposed method effectively considers the structure characteristics and noise distribution in the measured LdCT sinogram, and then learns the proper gradient of the LdCT sinogram in a pure unsupervised manner. Similar to the labeled ground-truth, the gradient information in an unlabeled LdCT sinogram can be used for sufficient network training. The experiments on the patient data show effectiveness of the proposed method.
Tasks
Published	2018-08-08
URL	http://arxiv.org/abs/1808.02603v1
PDF	http://arxiv.org/pdf/1808.02603v1.pdf
PWC	https://paperswithcode.com/paper/unsupervisedsemi-supervised-deep-learning-for
Repo
Framework

Matrix Product Operator Restricted Boltzmann Machines


Title	Matrix Product Operator Restricted Boltzmann Machines
Authors	Cong Chen, Kim Batselier, Ching-Yun Ko, Ngai Wong
Abstract	A restricted Boltzmann machine (RBM) learns a probability distribution over its input samples and has numerous uses like dimensionality reduction, classification and generative modeling. Conventional RBMs accept vectorized data that dismisses potentially important structural information in the original tensor (multi-way) input. Matrix-variate and tensor-variate RBMs, named MvRBM and TvRBM, have been proposed but are all restrictive by model construction, which leads to a weak model expression power. This work presents the matrix product operator RBM (MPORBM) that utilizes a tensor network generalization of Mv/TvRBM, preserves input formats in both the visible and hidden layers, and results in higher expressive power. A novel training algorithm integrating contrastive divergence and an alternating optimization procedure is also developed. Numerical experiments compare the MPORBM with the traditional RBM and MvRBM for data classification and image completion and denoising tasks. The expressive power of the MPORBM as a function of the MPO-rank is also investigated.
Tasks	Denoising, Dimensionality Reduction
Published	2018-11-12
URL	http://arxiv.org/abs/1811.04608v1
PDF	http://arxiv.org/pdf/1811.04608v1.pdf
PWC	https://paperswithcode.com/paper/matrix-product-operator-restricted-boltzmann
Repo
Framework

Tree Morphology for Phenotyping from Semantics-Based Mapping in Orchard Environments


Title	Tree Morphology for Phenotyping from Semantics-Based Mapping in Orchard Environments
Authors	Wenbo Dong, Volkan Isler
Abstract	Measuring tree morphology for phenotyping is an essential but labor-intensive activity in horticulture. Researchers often rely on manual measurements which may not be accurate for example when measuring tree volume. Recent approaches on automating the measurement process rely on LIDAR measurements coupled with high-accuracy GPS. Usually each side of a row is reconstructed independently and then merged using GPS information. Such approaches have two disadvantages: (1) they rely on specialized and expensive equipment, and (2) since the reconstruction process does not simultaneously use information from both sides, side reconstructions may not be accurate. We also show that standard loop closure methods do not necessarily align tree trunks well. In this paper, we present a novel vision system that employs only an RGB-D camera to estimate morphological parameters. A semantics-based mapping algorithm merges the two-sides 3D models of tree rows, where integrated semantic information is obtained and refined by robust fitting algorithms. We focus on measuring tree height, canopy volume and trunk diameter from the optimized 3D model. Experiments conducted in real orchards quantitatively demonstrate the accuracy of our method.
Tasks
Published	2018-04-16
URL	http://arxiv.org/abs/1804.05905v1
PDF	http://arxiv.org/pdf/1804.05905v1.pdf
PWC	https://paperswithcode.com/paper/tree-morphology-for-phenotyping-from
Repo
Framework

CariGAN: Caricature Generation through Weakly Paired Adversarial Learning


Title	CariGAN: Caricature Generation through Weakly Paired Adversarial Learning
Authors	Wenbin Li, Wei Xiong, Haofu Liao, Jing Huo, Yang Gao, Jiebo Luo
Abstract	Caricature generation is an interesting yet challenging task. The primary goal is to generate plausible caricatures with reasonable exaggerations given face images. Conventional caricature generation approaches mainly use low-level geometric transformations such as image warping to generate exaggerated images, which lack richness and diversity in terms of content and style. The recent progress in generative adversarial networks (GANs) makes it possible to learn an image-to-image transformation from data, so that richer contents and styles can be generated. However, directly applying the GAN-based models to this task leads to unsatisfactory results because there is a large variance in the caricature distribution. Moreover, some models require strictly paired training data which largely limits their usage scenarios. In this paper, we propose CariGAN overcome these problems. Instead of training on paired data, CariGAN learns transformations only from weakly paired images. Specifically, to enforce reasonable exaggeration and facial deformation, facial landmarks are adopted as an additional condition to constrain the generated image. Furthermore, an attention mechanism is introduced to encourage our model to focus on the key facial parts so that more vivid details in these regions can be generated. Finally, a Diversity Loss is proposed to encourage the model to produce diverse results to help alleviate the `mode collapse' problem of the conventional GAN-based models. Extensive experiments on a new large-scale` WebCaricature’ dataset show that the proposed CariGAN can generate more plausible caricatures with larger diversity compared with the state-of-the-art models.
Tasks	Caricature
Published	2018-11-01
URL	http://arxiv.org/abs/1811.00445v2
PDF	http://arxiv.org/pdf/1811.00445v2.pdf
PWC	https://paperswithcode.com/paper/carigan-caricature-generation-through-weakly
Repo
Framework

EventKG: A Multilingual Event-Centric Temporal Knowledge Graph


Title	EventKG: A Multilingual Event-Centric Temporal Knowledge Graph
Authors	Simon Gottschalk, Elena Demidova
Abstract	One of the key requirements to facilitate semantic analytics of information regarding contemporary and historical events on the Web, in the news and in social media is the availability of reference knowledge repositories containing comprehensive representations of events and temporal relations. Existing knowledge graphs, with popular examples including DBpedia, YAGO and Wikidata, focus mostly on entity-centric information and are insufficient in terms of their coverage and completeness with respect to events and temporal relations. EventKG presented in this paper is a multilingual event-centric temporal knowledge graph that addresses this gap. EventKG incorporates over 690 thousand contemporary and historical events and over 2.3 million temporal relations extracted from several large-scale knowledge graphs and semi-structured sources and makes them available through a canonical representation.
Tasks	Knowledge Graphs
Published	2018-04-12
URL	http://arxiv.org/abs/1804.04526v1
PDF	http://arxiv.org/pdf/1804.04526v1.pdf
PWC	https://paperswithcode.com/paper/eventkg-a-multilingual-event-centric-temporal
Repo
Framework

The Effectiveness of Instance Normalization: a Strong Baseline for Single Image Dehazing


Title	The Effectiveness of Instance Normalization: a Strong Baseline for Single Image Dehazing
Authors	Zheng Xu, Xitong Yang, Xue Li, Xiaoshuai Sun
Abstract	We propose a novel deep neural network architecture for the challenging problem of single image dehazing, which aims to recover the clear image from a degraded hazy image. Instead of relying on hand-crafted image priors or explicitly estimating the components of the widely used atmospheric scattering model, our end-to-end system directly generates the clear image from an input hazy image. The proposed network has an encoder-decoder architecture with skip connections and instance normalization. We adopt the convolutional layers of the pre-trained VGG network as encoder to exploit the representation power of deep features, and demonstrate the effectiveness of instance normalization for image dehazing. Our simple yet effective network outperforms the state-of-the-art methods by a large margin on the benchmark datasets.
Tasks	Image Dehazing, Single Image Dehazing
Published	2018-05-08
URL	http://arxiv.org/abs/1805.03305v1
PDF	http://arxiv.org/pdf/1805.03305v1.pdf
PWC	https://paperswithcode.com/paper/the-effectiveness-of-instance-normalization-a
Repo
Framework

Learning Representations of Missing Data for Predicting Patient Outcomes


Title	Learning Representations of Missing Data for Predicting Patient Outcomes
Authors	Brandon Malone, Alberto Garcia-Duran, Mathias Niepert
Abstract	Extracting actionable insight from Electronic Health Records (EHRs) poses several challenges for traditional machine learning approaches. Patients are often missing data relative to each other; the data comes in a variety of modalities, such as multivariate time series, free text, and categorical demographic information; important relationships among patients can be difficult to detect; and many others. In this work, we propose a novel approach to address these first three challenges using a representation learning scheme based on message passing. We show that our proposed approach is competitive with or outperforms the state of the art for predicting in-hospital mortality (binary classification), the length of hospital visits (regression) and the discharge destination (multiclass classification).
Tasks	Predicting Patient Outcomes, Representation Learning, Time Series
Published	2018-11-12
URL	http://arxiv.org/abs/1811.04752v1
PDF	http://arxiv.org/pdf/1811.04752v1.pdf
PWC	https://paperswithcode.com/paper/learning-representations-of-missing-data-for
Repo
Framework

Factor analysis of dynamic PET images: beyond Gaussian noise


Title	Factor analysis of dynamic PET images: beyond Gaussian noise
Authors	Yanna Cruz Cavalcanti, Thomas Oberlin, Nicolas Dobigeon, Cédric Févotte, Simon Stute, Maria-Joao Ribeiro, Clovis Tauber
Abstract	Factor analysis has proven to be a relevant tool for extracting tissue time-activity curves (TACs) in dynamic PET images, since it allows for an unsupervised analysis of the data. Reliable and interpretable results are possible only if considered with respect to suitable noise statistics. However, the noise in reconstructed dynamic PET images is very difficult to characterize, despite the Poissonian nature of the count-rates. Rather than explicitly modeling the noise distribution, this work proposes to study the relevance of several divergence measures to be used within a factor analysis framework. To this end, the $\beta$-divergence, widely used in other applicative domains, is considered to design the data-fitting term involved in three different factor models. The performances of the resulting algorithms are evaluated for different values of $\beta$, in a range covering Gaussian, Poissonian and Gamma-distributed noises. The results obtained on two different types of synthetic images and one real image show the interest of applying non-standard values of $\beta$ to improve factor analysis.
Tasks
Published	2018-07-30
URL	http://arxiv.org/abs/1807.11455v2
PDF	http://arxiv.org/pdf/1807.11455v2.pdf
PWC	https://paperswithcode.com/paper/factor-analysis-of-dynamic-pet-images-beyond
Repo
Framework

Optimisation and Illumination of a Real-world Workforce Scheduling and Routing Application via Map-Elites


Title	Optimisation and Illumination of a Real-world Workforce Scheduling and Routing Application via Map-Elites
Authors	Neil Urquhart, Emma Hart
Abstract	Workforce Scheduling and Routing Problems (WSRP) are very common in many practical domains, and usually, have a number of objectives. Illumination algorithms such as Map-Elites (ME) have recently gained traction in application to {\em design} problems, in providing multiple diverse solutions as well as illuminating the solution space in terms of user-defined characteristics, but typically require significant computational effort to produce the solution archive. We investigate whether ME can provide an effective approach to solving WSRP, a {\em repetitive} problem in which solutions have to be produced quickly and often. The goals of the paper are two-fold. The first is to evaluate whether ME can provide solutions of competitive quality to an Evolutionary Algorithm (EA) in terms of a single objective function, and the second to examine its ability to provide a repertoire of solutions that maximise user choice. We find that very small computational budgets favour the EA in terms of quality, but ME outperforms the EA at larger budgets, provides a more diverse array of solutions, and lends insight to the end-user.
Tasks
Published	2018-05-29
URL	http://arxiv.org/abs/1805.11555v1
PDF	http://arxiv.org/pdf/1805.11555v1.pdf
PWC	https://paperswithcode.com/paper/optimisation-and-illumination-of-a-real-world
Repo
Framework

Topic Diffusion Discovery based on Sparseness-constrained Non-negative Matrix Factorization


Title	Topic Diffusion Discovery based on Sparseness-constrained Non-negative Matrix Factorization
Authors	Yihuang Kang, Keng-Pei Lin, I-Ling Cheng
Abstract	Due to recent explosion of text data, researchers have been overwhelmed by ever-increasing volume of articles produced by different research communities. Various scholarly search websites, citation recommendation engines, and research databases have been created to simplify the text search tasks. However, it is still difficult for researchers to be able to identify potential research topics without doing intensive reviews on a tremendous number of articles published by journals, conferences, meetings, and workshops. In this paper, we consider a novel topic diffusion discovery technique that incorporates sparseness-constrained Non-negative Matrix Factorization with generalized Jensen-Shannon divergence to help understand term-topic evolutions and identify topic diffusions. Our experimental result shows that this approach can extract more prominent topics from large article databases, visualize relationships between terms of interest and abstract topics, and further help researchers understand whether given terms/topics have been widely explored or whether new topics are emerging from literature.
Tasks
Published	2018-07-12
URL	http://arxiv.org/abs/1807.04386v1
PDF	http://arxiv.org/pdf/1807.04386v1.pdf
PWC	https://paperswithcode.com/paper/topic-diffusion-discovery-based-on-sparseness
Repo
Framework

How Drones Look: Crowdsourced Knowledge Transfer for Aerial Video Saliency Prediction


Title	How Drones Look: Crowdsourced Knowledge Transfer for Aerial Video Saliency Prediction
Authors	Kui Fu, Jia Li, Hongze Shen, Yonghong Tian
Abstract	In ground-level platforms, many saliency models have been developed to perceive the visual world as the human does. However, they may not fit a drone that can look from many abnormal viewpoints. To address this problem, this paper proposes a Crowdsourced Multi-path Network (CMNet) that transfer the ground-level knowledge for spatiotemporal saliency prediction in aerial videos. To train CMNet, we first collect and fuse the eye-tracking data of 24 subjects on 1,000 aerial videos to annotate the ground-truth salient regions. Inspired by the crowdsourced annotation in eye-tracking experiments, we design a multi-path architecture for CMNet, in which each path is initialized under the supervision of a classic ground-level saliency model. After that, the most representative paths are selected in a data-driven manner, which are then fused and simultaneously fine-tuned on aerial videos. In this manner, the prior knowledge in various classic ground-level saliency models can be transferred into CMNet so as to improve its capability in processing aerial videos. Finally, the spatial predictions given by CMNet are adaptively refined by incorporating the temporal saliency predictions via a spatiotemporal saliency optimization algorithm. Experimental results show that the proposed approach outperforms ten state-of-the-art models in predicting visual saliency in aerial videos.
Tasks	Aerial Video Saliency Prediction, Eye Tracking, Saliency Prediction, Transfer Learning
Published	2018-11-14
URL	http://arxiv.org/abs/1811.05625v1
PDF	http://arxiv.org/pdf/1811.05625v1.pdf
PWC	https://paperswithcode.com/paper/how-drones-look-crowdsourced-knowledge
Repo
Framework

Distributed ReliefF based Feature Selection in Spark


Title	Distributed ReliefF based Feature Selection in Spark
Authors	Raul-Jose Palma-Mendoza, Daniel Rodriguez, Luis de-Marcos
Abstract	Feature selection (FS) is a key research area in the machine learning and data mining fields, removing irrelevant and redundant features usually helps to reduce the effort required to process a dataset while maintaining or even improving the processing algorithm’s accuracy. However, traditional algorithms designed for executing on a single machine lack scalability to deal with the increasing amount of data that has become available in the current Big Data era. ReliefF is one of the most important algorithms successfully implemented in many FS applications. In this paper, we present a completely redesigned distributed version of the popular ReliefF algorithm based on the novel Spark cluster computing model that we have called DiReliefF. Spark is increasing its popularity due to its much faster processing times compared with Hadoop’s MapReduce model implementation. The effectiveness of our proposal is tested on four publicly available datasets, all of them with a large number of instances and two of them with also a large number of features. Subsets of these datasets were also used to compare the results to a non-distributed implementation of the algorithm. The results show that the non-distributed implementation is unable to handle such large volumes of data without specialized hardware, while our design can process them in a scalable way with much better processing times and memory usage.
Tasks	Feature Selection
Published	2018-11-01
URL	http://arxiv.org/abs/1811.00424v1
PDF	http://arxiv.org/pdf/1811.00424v1.pdf
PWC	https://paperswithcode.com/paper/distributed-relieff-based-feature-selection
Repo
Framework

Continuous Space Reordering Models for Phrase-based MT


Title	Continuous Space Reordering Models for Phrase-based MT
Authors	Nadir Durrani, Fahim Dalvi
Abstract	Bilingual sequence models improve phrase-based translation and reordering by overcoming phrasal independence assumption and handling long range reordering. However, due to data sparsity, these models often fall back to very small context sizes. This problem has been previously addressed by learning sequences over generalized representations such as POS tags or word clusters. In this paper, we explore an alternative based on neural network models. More concretely we train neuralized versions of lexicalized reordering and the operation sequence models using feed-forward neural network. Our results show improvements of up to 0.6 and 0.5 BLEU points on top of the baseline German->English and English->German systems. We also observed improvements compared to the systems that used POS tags and word clusters to train these models. Because we modify the bilingual corpus to integrate reordering operations, this allows us to also train a sequence-to-sequence neural MT model having explicit reordering triggers. Our motivation was to directly enable reordering information in the encoder-decoder framework, which otherwise relies solely on the attention model to handle long range reordering. We tried both coarser and fine-grained reordering operations. However, these experiments did not yield any improvements over the baseline Neural MT systems.
Tasks
Published	2018-01-25
URL	http://arxiv.org/abs/1801.08337v2
PDF	http://arxiv.org/pdf/1801.08337v2.pdf
PWC	https://paperswithcode.com/paper/continuous-space-reordering-models-for-phrase
Repo
Framework

Classical Copying versus Quantum Entanglement in Natural Language: The Case of VP-ellipsis


Title	Classical Copying versus Quantum Entanglement in Natural Language: The Case of VP-ellipsis
Authors	Gijs Wijnholds, Mehrnoosh Sadrzadeh
Abstract	This paper compares classical copying and quantum entanglement in natural language by considering the case of verb phrase (VP) ellipsis. VP ellipsis is a non-linear linguistic phenomenon that requires the reuse of resources, making it the ideal test case for a comparative study of different copying behaviours in compositional models of natural language. Following the line of research in compositional distributional semantics set out by (Coecke et al., 2010) we develop an extension of the Lambek calculus which admits a controlled form of contraction to deal with the copying of linguistic resources. We then develop two different compositional models of distributional meaning for this calculus. In the first model, we follow the categorical approach of (Coecke et al., 2013) in which a functorial passage sends the proofs of the grammar to linear maps on vector spaces and we use Frobenius algebras to allow for copying. In the second case, we follow the more traditional approach that one finds in categorial grammars, whereby an intermediate step interprets proofs as non-linear lambda terms, using multiple variable occurrences that model classical copying. As a case study, we apply the models to derive different readings of ambiguous elliptical phrases and compare the analyses that each model provides.
Tasks
Published	2018-11-08
URL	http://arxiv.org/abs/1811.03276v1
PDF	http://arxiv.org/pdf/1811.03276v1.pdf
PWC	https://paperswithcode.com/paper/classical-copying-versus-quantum-entanglement
Repo
Framework

Adversarial Contrastive Estimation


Title	Adversarial Contrastive Estimation
Authors	Avishek Joey Bose, Huan Ling, Yanshuai Cao
Abstract	Learning by contrasting positive and negative samples is a general strategy adopted by many methods. Noise contrastive estimation (NCE) for word embeddings and translating embeddings for knowledge graphs are examples in NLP employing this approach. In this work, we view contrastive learning as an abstraction of all such methods and augment the negative sampler into a mixture distribution containing an adversarially learned sampler. The resulting adaptive sampler finds harder negative examples, which forces the main model to learn a better representation of the data. We evaluate our proposal on learning word embeddings, order embeddings and knowledge graph embeddings and observe both faster convergence and improved results on multiple metrics.
Tasks	Knowledge Graph Embeddings, Knowledge Graphs, Learning Word Embeddings, Word Embeddings
Published	2018-05-09
URL	http://arxiv.org/abs/1805.03642v3
PDF	http://arxiv.org/pdf/1805.03642v3.pdf
PWC	https://paperswithcode.com/paper/adversarial-contrastive-estimation
Repo
Framework