January 25, 2020

2995 words 15 mins read

Paper Group ANR 1703

hauWE: Hausa Words Embedding for Natural Language Processing. Bag of Color Features For Color Constancy. Curve Text Detection with Local Segmentation Network and Curve Connection. Two-Hop Walks Indicate PageRank Order. Data Augmentation for Skin Lesion using Self-Attention based Progressive Generative Adversarial Network. Collaborative Interactive …

hauWE: Hausa Words Embedding for Natural Language Processing


Title	hauWE: Hausa Words Embedding for Natural Language Processing
Authors	Idris Abdulmumin, Bashir Shehu Galadanci
Abstract	Words embedding (distributed word vector representations) have become an essential component of many natural language processing (NLP) tasks such as machine translation, sentiment analysis, word analogy, named entity recognition and word similarity. Despite this, the only work that provides word vectors for Hausa language is that of Bojanowski et al. [1] trained using fastText, consisting of only a few words vectors. This work presents words embedding models using Word2Vec’s Continuous Bag of Words (CBoW) and Skip Gram (SG) models. The models, hauWE (Hausa Words Embedding), are bigger and better than the only previous model, making them more useful in NLP tasks. To compare the models, they were used to predict the 10 most similar words to 30 randomly selected Hausa words. hauWE CBoW’s 88.7% and hauWE SG’s 79.3% prediction accuracy greatly outperformed Bojanowski et al. [1]‘s 22.3%.
Tasks	Machine Translation, Named Entity Recognition, Sentiment Analysis
Published	2019-11-25
URL	https://arxiv.org/abs/1911.10708v1
PDF	https://arxiv.org/pdf/1911.10708v1.pdf
PWC	https://paperswithcode.com/paper/hauwe-hausa-words-embedding-for-natural
Repo
Framework

Bag of Color Features For Color Constancy


Title	Bag of Color Features For Color Constancy
Authors	Firas Laakom, Nikolaos Passalis, Jenni Raitoharju, Jarno Nikkanen, Anastasios Tefas, Alexandros Iosifidis, Moncef Gabbouj
Abstract	In this paper, we propose a novel color constancy approach, called Bag of Color Features (BoCF), building upon Bag-of-Features pooling. The proposed method substantially reduces the number of parameters needed for illumination estimation. At the same time, the proposed method is consistent with the color constancy assumption stating that global spatial information is not relevant for illumination estimation and local information ( edges, etc.) is sufficient. Furthermore, BoCF is consistent with color constancy statistical approaches and can be interpreted as a learning-based generalization of many statistical approaches. To further improve the illumination estimation accuracy, we propose a novel attention mechanism for the BoCF model with two variants based on self-attention. BoCF approach and its variants achieve competitive, compared to the state of the art, results while requiring much fewer parameters on three benchmark datasets: ColorChecker RECommended, INTEL-TUT version 2, and NUS8.
Tasks	Color Constancy
Published	2019-06-11
URL	https://arxiv.org/abs/1906.04445v1
PDF	https://arxiv.org/pdf/1906.04445v1.pdf
PWC	https://paperswithcode.com/paper/bag-of-color-features-for-color-constancy
Repo
Framework

Curve Text Detection with Local Segmentation Network and Curve Connection


Title	Curve Text Detection with Local Segmentation Network and Curve Connection
Authors	Zhao Zhou, Shufan Wu, Shuchen Kong, Yingbin Zheng, Hao Ye, Luhui Chen, Jian Pu
Abstract	Curve text or arbitrary shape text is very common in real-world scenarios. In this paper, we propose a novel framework with the local segmentation network (LSN) followed by the curve connection to detect text in horizontal, oriented and curved forms. The LSN is composed of two elements, i.e., proposal generation to get the horizontal rectangle proposals with high overlap with text and text segmentation to find the arbitrary shape text region within proposals. The curve connection is then designed to connect the local mask to the detection results. We conduct experiments using the proposed framework on two real-world curve text detection datasets and demonstrate the effectiveness over previous approaches.
Tasks
Published	2019-03-23
URL	http://arxiv.org/abs/1903.09837v1
PDF	http://arxiv.org/pdf/1903.09837v1.pdf
PWC	https://paperswithcode.com/paper/curve-text-detection-with-local-segmentation
Repo
Framework

Two-Hop Walks Indicate PageRank Order


Title	Two-Hop Walks Indicate PageRank Order
Authors	Ying Tang
Abstract	This paper shows that pairwise PageRank orders emerge from two-hop walks. The main tool used here refers to a specially designed sign-mirror function and a parameter curve, whose low-order derivative information implies pairwise PageRank orders with high probability. We study the pairwise correct rate by placing the Google matrix $\textbf{G}$ in a probabilistic framework, where $\textbf{G}$ may be equipped with different random ensembles for model-generated or real-world networks with sparse, small-world, scale-free features, the proof of which is mixed by mathematical and numerical evidence. We believe that the underlying spectral distribution of aforementioned networks is responsible for the high pairwise correct rate. Moreover, the perspective of this paper naturally leads to an $O(1)$ algorithm for any single pairwise PageRank comparison if assuming both $\textbf{A}=\textbf{G}-\textbf{I}_n$, where $\textbf{I}_n$ denotes the identity matrix of order $n$, and $\textbf{A}^2$ are ready on hand (e.g., constructed offline in an incremental manner), based on which it is easy to extract the top $k$ list in $O(kn)$, thus making it possible for PageRank algorithm to deal with super large-scale datasets in real time.
Tasks
Published	2019-03-09
URL	http://arxiv.org/abs/1903.03756v1
PDF	http://arxiv.org/pdf/1903.03756v1.pdf
PWC	https://paperswithcode.com/paper/two-hop-walks-indicate-pagerank-order
Repo
Framework

Data Augmentation for Skin Lesion using Self-Attention based Progressive Generative Adversarial Network


Title	Data Augmentation for Skin Lesion using Self-Attention based Progressive Generative Adversarial Network
Authors	Ibrahim Saad Ali, Mamdouh Farouk Mohamed, Yousef Bassyouni Mahdy
Abstract	Deep Neural Networks (DNNs) show a significant impact on medical imaging. One significant problem with adopting DNNs for skin cancer classification is that the class frequencies in the existing datasets are imbalanced. This problem hinders the training of robust and well-generalizing models. Data Augmentation addresses this by using existing data more effectively. However, standard data augmentation implementations are manually designed and produce only limited reasonably alternative data. Instead, Generative Adversarial Networks (GANs) is utilized to generate a much broader set of augmentations. This paper proposes a novel enhancement for the progressive generative adversarial networks (PGAN) using self-attention mechanism. Self-attention mechanism is used to directly model the long-range dependencies in the feature maps. Accordingly, self-attention complements PGAN to generate fine-grained samples that comprise clinically-meaningful information. Moreover, the stabilization technique was applied to the enhanced generative model. To train the generative models, ISIC 2018 skin lesion challenge dataset was used to synthesize highly realistic skin lesion samples for boosting further the classification result. We achieve an accuracy of 70.1% which is 2.8% better than the non-augmented one of 67.3%.
Tasks	Data Augmentation, Skin Cancer Classification
Published	2019-10-25
URL	https://arxiv.org/abs/1910.11960v1
PDF	https://arxiv.org/pdf/1910.11960v1.pdf
PWC	https://paperswithcode.com/paper/data-augmentation-for-skin-lesion-using-self
Repo
Framework

Collaborative Interactive Learning – A clarification of terms and a differentiation from other research fields


Title	Collaborative Interactive Learning – A clarification of terms and a differentiation from other research fields
Authors	Tom Hanika, Marek Herde, Jochen Kuhn, Jan Marco Leimeister, Paul Lukowicz, Sarah Oeste-Reiß, Albrecht Schmidt, Bernhard Sick, Gerd Stumme, Sven Tomforde, Katharina Anna Zweig
Abstract	The field of collaborative interactive learning (CIL) aims at developing and investigating the technological foundations for a new generation of smart systems that support humans in their everyday life. While the concept of CIL has already been carved out in detail (including the fields of dedicated CIL and opportunistic CIL) and many research objectives have been stated, there is still the need to clarify some terms such as information, knowledge, and experience in the context of CIL and to differentiate CIL from recent and ongoing research in related fields such as active learning, collaborative learning, and others. Both aspects are addressed in this paper.
Tasks	Active Learning
Published	2019-05-16
URL	https://arxiv.org/abs/1905.07264v1
PDF	https://arxiv.org/pdf/1905.07264v1.pdf
PWC	https://paperswithcode.com/paper/collaborative-interactive-learning-a
Repo
Framework

A knowledge-based intelligent system for control of dirt recognition process in the smart washing machines


Title	A knowledge-based intelligent system for control of dirt recognition process in the smart washing machines
Authors	Mohsen Annabestani, Alireza Rowhanimanesh, Akram Rezaei, Ladan Avazpour, Fatemeh Sheikhhasani
Abstract	In this paper, we propose an intelligence approach based on fuzzy logic to modeling human intelligence in washing clothes. At first, an intelligent feedback loop is designed for perception-based sensing of dirt inspired by human color understanding. Then, when color stains leak out of some colored clothes the human probabilistic decision making is computationally modeled to detect this stain leakage and thus the problem of recognizing dirt from stain can be considered in the washing process. Finally, we discuss the fuzzy control of washing clothes and design and simulate a smart controller based on the fuzzy intelligence feedback loop.
Tasks	Decision Making
Published	2019-05-02
URL	https://arxiv.org/abs/1905.00607v2
PDF	https://arxiv.org/pdf/1905.00607v2.pdf
PWC	https://paperswithcode.com/paper/a-knowledge-based-intelligence-system-for
Repo
Framework

Fast Multi-Class Probabilistic Classifier by Sparse Non-parametric Density Estimation


Title	Fast Multi-Class Probabilistic Classifier by Sparse Non-parametric Density Estimation
Authors	Wan-Ping Nicole Chen, Yuan-chin Ivan Chang
Abstract	The model interpretation is essential in many application scenarios and to build a classification model with a ease of model interpretation may provide useful information for further studies and improvement. It is common to encounter with a lengthy set of variables in modern data analysis, especially when data are collected in some automatic ways. This kinds of datasets may not collected with a specific analysis target and usually contains redundant features, which have no contribution to a the current analysis task of interest. Variable selection is a common way to increase the ability of model interpretation and is popularly used with some parametric classification models. There is a lack of studies about variable selection in nonparametric classification models such as the density estimation-based methods and this is especially the case for multiple-class classification situations. In this study we study multiple-class classification problems using the thought of sparse non-parametric density estimation and propose a method for identifying high impacts variables for each class. We present the asymptotic properties and the computation procedure for the proposed method together with some suggested sample size. We also repost the numerical results using both synthesized and some real data sets.
Tasks	Density Estimation
Published	2019-01-04
URL	http://arxiv.org/abs/1901.01000v1
PDF	http://arxiv.org/pdf/1901.01000v1.pdf
PWC	https://paperswithcode.com/paper/fast-multi-class-probabilistic-classifier-by
Repo
Framework

Learned human-agent decision-making, communication and joint action in a virtual reality environment


Title	Learned human-agent decision-making, communication and joint action in a virtual reality environment
Authors	Patrick M. Pilarski, Andrew Butcher, Michael Johanson, Matthew M. Botvinick, Andrew Bolt, Adam S. R. Parker
Abstract	Humans make decisions and act alongside other humans to pursue both short-term and long-term goals. As a result of ongoing progress in areas such as computing science and automation, humans now also interact with non-human agents of varying complexity as part of their day-to-day activities; substantial work is being done to integrate increasingly intelligent machine agents into human work and play. With increases in the cognitive, sensory, and motor capacity of these agents, intelligent machinery for human assistance can now reasonably be considered to engage in joint action with humans—i.e., two or more agents adapting their behaviour and their understanding of each other so as to progress in shared objectives or goals. The mechanisms, conditions, and opportunities for skillful joint action in human-machine partnerships is of great interest to multiple communities. Despite this, human-machine joint action is as yet under-explored, especially in cases where a human and an intelligent machine interact in a persistent way during the course of real-time, daily-life experience. In this work, we contribute a virtual reality environment wherein a human and an agent can adapt their predictions, their actions, and their communication so as to pursue a simple foraging task. In a case study with a single participant, we provide an example of human-agent coordination and decision-making involving prediction learning on the part of the human and the machine agent, and control learning on the part of the machine agent wherein audio communication signals are used to cue its human partner in service of acquiring shared reward. These comparisons suggest the utility of studying human-machine coordination in a virtual reality environment, and identify further research that will expand our understanding of persistent human-machine joint action.
Tasks	Decision Making
Published	2019-05-07
URL	https://arxiv.org/abs/1905.02691v1
PDF	https://arxiv.org/pdf/1905.02691v1.pdf
PWC	https://paperswithcode.com/paper/learned-human-agent-decision-making
Repo
Framework

RHR-Net: A Residual Hourglass Recurrent Neural Network for Speech Enhancement


Title	RHR-Net: A Residual Hourglass Recurrent Neural Network for Speech Enhancement
Authors	Jalal Abdulbaqi, Yue Gu, Ivan Marsic
Abstract	Most current speech enhancement models use spectrogram features that require an expensive transformation and result in phase information loss. Previous work has overcome these issues by using convolutional networks to learn long-range temporal correlations across high-resolution waveforms. These models, however, are limited by memory-intensive dilated convolution and aliasing artifacts from upsampling. We introduce an end-to-end fully-recurrent hourglass-shaped neural network architecture with residual connections for waveform-based single-channel speech enhancement. Our model can efficiently capture long-range temporal dependencies by reducing the features resolution without information loss. Experimental results show that our model outperforms state-of-the-art approaches in six evaluation metrics.
Tasks	Speech Enhancement
Published	2019-04-15
URL	http://arxiv.org/abs/1904.07294v1
PDF	http://arxiv.org/pdf/1904.07294v1.pdf
PWC	https://paperswithcode.com/paper/rhr-net-a-residual-hourglass-recurrent-neural
Repo
Framework

SPONGE: A generalized eigenproblem for clustering signed networks


Title	SPONGE: A generalized eigenproblem for clustering signed networks
Authors	Mihai Cucuringu, Peter Davies, Aldo Glielmo, Hemant Tyagi
Abstract	We introduce a principled and theoretically sound spectral method for $k$-way clustering in signed graphs, where the affinity measure between nodes takes either positive or negative values. Our approach is motivated by social balance theory, where the task of clustering aims to decompose the network into disjoint groups, such that individuals within the same group are connected by as many positive edges as possible, while individuals from different groups are connected by as many negative edges as possible. Our algorithm relies on a generalized eigenproblem formulation inspired by recent work on constrained clustering. We provide theoretical guarantees for our approach in the setting of a signed stochastic block model, by leveraging tools from matrix perturbation theory and random matrix theory. An extensive set of numerical experiments on both synthetic and real data shows that our approach compares favorably with state-of-the-art methods for signed clustering, especially for large number of clusters and sparse measurement graphs.
Tasks
Published	2019-04-18
URL	https://arxiv.org/abs/1904.08575v2
PDF	https://arxiv.org/pdf/1904.08575v2.pdf
PWC	https://paperswithcode.com/paper/sponge-a-generalized-eigenproblem-for
Repo
Framework

Short-term Load Forecasting at Different Aggregation Levels with Predictability Analysis


Title	Short-term Load Forecasting at Different Aggregation Levels with Predictability Analysis
Authors	Yayu Peng, Yishen Wang, Xiao Lu, Haifeng Li, Di Shi, Zhiwei Wang, Jie Li
Abstract	Short-term load forecasting (STLF) is essential for the reliable and economic operation of power systems. Though many STLF methods were proposed over the past decades, most of them focused on loads at high aggregation levels only. Thus, low-aggregation load forecast still requires further research and development. Compared with the substation or city level loads, individual loads are typically more volatile and much more challenging to forecast. To further address this issue, this paper first discusses the characteristics of small-and-medium enterprise (SME) and residential loads at different aggregation levels and quantifies their predictability with approximate entropy. Various STLF techniques, from the conventional linear regression to state-of-the-art deep learning, are implemented for a detailed comparative analysis to verify the forecasting performances as well as the predictability using an Irish smart meter dataset. In addition, the paper also investigates how using data processing improves individual-level residential load forecasting with low predictability. Effectiveness of the discussed method is validated with numerical results.
Tasks	Load Forecasting
Published	2019-03-26
URL	http://arxiv.org/abs/1903.10679v1
PDF	http://arxiv.org/pdf/1903.10679v1.pdf
PWC	https://paperswithcode.com/paper/short-term-load-forecasting-at-different
Repo
Framework

Visual Indeterminacy in GAN Art


Title	Visual Indeterminacy in GAN Art
Authors	Aaron Hertzmann
Abstract	This paper explores visual indeterminacy as a description for artwork created with Generative Adversarial Networks (GANs). Visual indeterminacy describes images which appear to depict real scenes, but, on closer examination, defy coherent spatial interpretation. GAN models seem to be predisposed to producing indeterminate images, and indeterminacy is a key feature of much modern representational art, as well as most GAN art. It is hypothesized that indeterminacy is a consequence of a powerful-but-imperfect image synthesis model that must combine general classes of objects, scenes, and textures.
Tasks	Image Generation
Published	2019-10-10
URL	https://arxiv.org/abs/1910.04639v3
PDF	https://arxiv.org/pdf/1910.04639v3.pdf
PWC	https://paperswithcode.com/paper/visual-indeterminacy-in-generative-neural-art
Repo
Framework

Taco-VC: A Single Speaker Tacotron based Voice Conversion with Limited Data


Title	Taco-VC: A Single Speaker Tacotron based Voice Conversion with Limited Data
Authors	Roee Levy Leshem, Raja Giryes
Abstract	This paper introduces Taco-VC, a novel architecture for voice conversion (VC) based on the Tacotron synthesizer, which is a sequence-to-sequence with attention model. The training of multi-speaker voice conversion systems requires a large amount of resources, both in training and corpus size. Taco-VC is implemented using a single speaker Tacotron synthesizer based on Phonetic Posteriorgrams (PPGs) and a single speaker Wavenet vocoder conditioned on Mel Spectrograms. To enhance the converted speech quality, the outputs of the Tacotron are passed through a novel speech-enhancement network, which is composed of a combination of phoneme recognition and Tacotron networks. Our system is trained just with a mid-size, single speaker corpus, and adapted to new speakers using only few minutes of training data. Using public mid-size datasets, our method outperforms the baseline in the VCC 2018 SPOKE task, and achieves competitive results compared to multi-speaker networks trained on private large datasets.
Tasks	Speech Enhancement, Voice Conversion
Published	2019-04-06
URL	https://arxiv.org/abs/1904.03522v3
PDF	https://arxiv.org/pdf/1904.03522v3.pdf
PWC	https://paperswithcode.com/paper/taco-vc-a-single-speaker-tacotron-based-voice
Repo
Framework

Interpretable Modelling of Driving Behaviors in Interactive Driving Scenarios based on Cumulative Prospect Theory


Title	Interpretable Modelling of Driving Behaviors in Interactive Driving Scenarios based on Cumulative Prospect Theory
Authors	Liting Sun, Wei Zhan, Yeping Hu, Masayoshi Tomizuka
Abstract	Understanding human driving behavior is important for autonomous vehicles. In this paper, we propose an interpretable human behavior model in interactive driving scenarios based on the cumulative prospect theory (CPT). As a non-expected utility theory, CPT can well explain some systematically biased or `irrational'' behavior/decisions of human that cannot be explained by the expected utility theory. Hence, the goal of this work is to formulate the human drivers' behavior generation model with CPT so that some` irrational’’ behavior or decisions of human can be better captured and predicted. Towards such a goal, we first develop a CPT-driven decision-making model focusing on driving scenarios with two interacting agents. A hierarchical learning algorithm is proposed afterward to learn the utility function, the value function, and the decision weighting function in the CPT model. A case study for roundabout merging is also provided as verification. With real driving data, the prediction performances of three different models are compared: a predefined model based on time-to-collision (TTC), a learning-based model based on neural networks, and the proposed CPT-based model. The results show that the proposed model outperforms the TTC model and achieves similar performance as the learning-based model with much less training data and better interpretability.
Tasks	Autonomous Vehicles, Decision Making
Published	2019-07-19
URL	https://arxiv.org/abs/1907.08707v1
PDF	https://arxiv.org/pdf/1907.08707v1.pdf
PWC	https://paperswithcode.com/paper/interpretable-modelling-of-driving-behaviors
Repo
Framework