January 30, 2020

2922 words 14 mins read

Paper Group ANR 460

Hexagonal Image Processing in the Context of Machine Learning: Conception of a Biologically Inspired Hexagonal Deep Learning Framework. A Quantum-inspired Algorithm for General Minimum Conical Hull Problems. Combining mixture models with linear mixing updates: multilayer image segmentation and synthesis. Value Functions for Depth-Limited Solving in …

Hexagonal Image Processing in the Context of Machine Learning: Conception of a Biologically Inspired Hexagonal Deep Learning Framework


Title	Hexagonal Image Processing in the Context of Machine Learning: Conception of a Biologically Inspired Hexagonal Deep Learning Framework
Authors	Tobias Schlosser, Michael Friedrich, Danny Kowerko
Abstract	Inspired by the human visual perception system, hexagonal image processing in the context of machine learning deals with the development of image processing systems that combine the advantages of evolutionary motivated structures based on biological models. While conventional state of the art image processing systems of recording and output devices almost exclusively utilize square arranged methods, their hexagonal counterparts offer a number of key advantages that can benefit both researchers and users. This contribution serves as a general application-oriented approach the synthesis of the therefore designed hexagonal image processing framework, called Hexnet, the processing steps of hexagonal image transformation, and dependent methods. The results of our created test environment show that the realized framework surpasses current approaches of hexagonal image processing systems, while hexagonal artificial neural networks can benefit from the implemented hexagonal architecture. As hexagonal lattice format based deep neural networks, also called H-DNN, can be compared to their square counterparts by transforming classical square lattice based data sets into their hexagonal representation, they can also result in a reduction of trainable parameters as well as result in increased training and test rates.
Tasks
Published	2019-11-25
URL	https://arxiv.org/abs/1911.11251v5
PDF	https://arxiv.org/pdf/1911.11251v5.pdf
PWC	https://paperswithcode.com/paper/hexagonal-image-processing-in-the-context-of
Repo
Framework

A Quantum-inspired Algorithm for General Minimum Conical Hull Problems


Title	A Quantum-inspired Algorithm for General Minimum Conical Hull Problems
Authors	Yuxuan Du, Min-Hsiu Hsieh, Tongliang Liu, Dacheng Tao
Abstract	A wide range of fundamental machine learning tasks that are addressed by the maximum a posteriori estimation can be reduced to a general minimum conical hull problem. The best-known solution to tackle general minimum conical hull problems is the divide-and-conquer anchoring learning scheme (DCA), whose runtime complexity is polynomial in size. However, big data is pushing these polynomial algorithms to their performance limits. In this paper, we propose a sublinear classical algorithm to tackle general minimum conical hull problems when the input has stored in a sample-based low-overhead data structure. The algorithm’s runtime complexity is polynomial in the rank and polylogarithmic in size. The proposed algorithm achieves the exponential speedup over DCA and, therefore, provides advantages for high dimensional problems.
Tasks
Published	2019-07-16
URL	https://arxiv.org/abs/1907.06814v1
PDF	https://arxiv.org/pdf/1907.06814v1.pdf
PWC	https://paperswithcode.com/paper/a-quantum-inspired-algorithm-for-general
Repo
Framework

Combining mixture models with linear mixing updates: multilayer image segmentation and synthesis


Title	Combining mixture models with linear mixing updates: multilayer image segmentation and synthesis
Authors	Jonathan Vacher, Ruben Coen-Cagli
Abstract	Finite mixture models for clustering can often be improved by adding a regularization that is specific to the topology of the data. For instance, mixtures are common in unsupervised image segmentation, and typically rely on averaging the posterior mixing probabilities of spatially adjacent data points (i.e. smoothing). However, this approach has had limited success with natural images. Here we make three contributions. First, we show that a Dirichlet prior with an appropriate choice of parameters allows – using the Expectation-Maximization approach – to define any linear update rule for the mixing probabilities, including many smoothing regularizations as special cases. Second, we demonstrate how to use this flexible design of the update rule to propagate segmentation information across layers of a deep network, and to train mixtures jointly across layers. Third, we compare the standard Gaussian mixture and the Student-t mixture, which is known to better capture the statistics of low-level visual features. We show that our models achieve competitive performance in natural image segmentation, with the Student-t mixtures reaching state-of-the art on boundaries scores. We also demonstrate how to exploit the resulting multilayer probabilistic generative model to synthesize naturalistic images beyond uniform textures.
Tasks	Semantic Segmentation
Published	2019-05-25
URL	https://arxiv.org/abs/1905.10629v1
PDF	https://arxiv.org/pdf/1905.10629v1.pdf
PWC	https://paperswithcode.com/paper/combining-mixture-models-with-linear-mixing
Repo
Framework

Value Functions for Depth-Limited Solving in Imperfect-Information Games beyond Poker


Title	Value Functions for Depth-Limited Solving in Imperfect-Information Games beyond Poker
Authors	Dominik Seitz, Vojtěch Kovařík, Viliam Lisý, Jan Rudolf, Shuo Sun, Karel Ha
Abstract	Depth-limited look-ahead search is an essential tool for agents playing perfect-information games. In imperfect information games, the lack of a clear definition of a value of a state makes designing theoretically sound depth-limited solving algorithms substantially more difficult. Furthermore, most results in this direction only consider the domain of poker. We propose a domain and algorithm independent definition of a value function in general extensive-form games, formally analyze its uniqueness, structure, and compact representations. In an empirical study, we show that neural networks can be easily trained to approximate value functions in three substantially different domains. Furthermore, we analyze the influence of the precision of the value function on the quality of the strategies produced by the depth-limited equilibrium solving algorithm using it.
Tasks
Published	2019-05-31
URL	https://arxiv.org/abs/1906.06412v2
PDF	https://arxiv.org/pdf/1906.06412v2.pdf
PWC	https://paperswithcode.com/paper/value-functions-for-depth-limited-solving-in
Repo
Framework

Concept Discovery through Information Extraction in Restaurant Domain


Title	Concept Discovery through Information Extraction in Restaurant Domain
Authors	Nadeesha Pathirana, Sandaru Seneviratne, Rangika Samarawickrama, Shane Wolff, Charith Chitraranjan, Uthayasanker Thayasivam, Tharindu Ranasinghe
Abstract	Concept identification is a crucial step in understanding and building a knowledge base for any particular domain. However, it is not a simple task in very large domains such as restaurants and hotel. In this paper, a novel approach of identifying a concept hierarchy and classifying unseen words into identified concepts related to restaurant domain is presented. Sorting, identifying, classifying of domain-related words manually is tedious and therefore, the proposed process is automated to a great extent. Word embedding, hierarchical clustering, classification algorithms are effectively used to obtain concepts related to the restaurant domain. Further, this approach can also be extended to create a semi-automatic ontology on restaurant domain.
Tasks
Published	2019-06-12
URL	https://arxiv.org/abs/1906.05039v1
PDF	https://arxiv.org/pdf/1906.05039v1.pdf
PWC	https://paperswithcode.com/paper/concept-discovery-through-information
Repo
Framework

Fast Algorithm for K-Truss Discovery on Public-Private Graphs


Title	Fast Algorithm for K-Truss Discovery on Public-Private Graphs
Authors	Soroush Ebadian, Xin Huang
Abstract	In public-private graphs, users share one public graph and have their own private graphs. A private graph consists of personal private contacts that only can be visible to its owner, e.g., hidden friend lists on Facebook and secret following on Sina Weibo. However, existing public-private analytic algorithms have not yet investigated the dense subgraph discovery of k-truss, where each edge is contained in at least k-2 triangles. This paper aims at finding k-truss efficiently in public-private graphs. The core of our solution is a novel algorithm to update k-truss with node insertions. We develop a classification-based hybrid strategy of node insertions and edge insertions to incrementally compute k-truss in public-private graphs. Extensive experiments validate the superiority of our proposed algorithms against state-of-the-art methods on real-world datasets.
Tasks
Published	2019-06-01
URL	https://arxiv.org/abs/1906.00140v1
PDF	https://arxiv.org/pdf/1906.00140v1.pdf
PWC	https://paperswithcode.com/paper/190600140
Repo
Framework

Differentially Private High Dimensional Sparse Covariance Matrix Estimation


Title	Differentially Private High Dimensional Sparse Covariance Matrix Estimation
Authors	Di Wang, Jinhui Xu
Abstract	In this paper, we study the problem of estimating the covariance matrix under differential privacy, where the underlying covariance matrix is assumed to be sparse and of high dimensions. We propose a new method, called DP-Thresholding, to achieve a non-trivial $\ell_2$-norm based error bound, which is significantly better than the existing ones from adding noise directly to the empirical covariance matrix. We also extend the $\ell_2$-norm based error bound to a general $\ell_w$-norm based one for any $1\leq w\leq \infty$, and show that they share the same upper bound asymptotically. Our approach can be easily extended to local differential privacy. Experiments on the synthetic datasets show consistent results with our theoretical claims.
Tasks
Published	2019-01-18
URL	http://arxiv.org/abs/1901.06413v2
PDF	http://arxiv.org/pdf/1901.06413v2.pdf
PWC	https://paperswithcode.com/paper/differentially-private-high-dimensional
Repo
Framework

Quick and Easy Time Series Generation with Established Image-based GANs


Title	Quick and Easy Time Series Generation with Established Image-based GANs
Authors	Eoin Brophy, Zhengwei Wang, Tomas E. Ward
Abstract	In the recent years Generative Adversarial Networks (GANs) have demonstrated significant progress in generating authentic looking data. In this work we introduce our simple method to exploit the advancements in well established image-based GANs to synthesise single channel time series data. We implement Wasserstein GANs (WGANs) with gradient penalty due to their stability in training to synthesise three different types of data; sinusoidal data, photoplethysmograph (PPG) data and electrocardiograph (ECG) data. The length of the returned time series data is limited only by the image resolution, we use an image size of 64x64 pixels which yields 4096 data points. We present both visual and quantitative evidence that our novel method can successfully generate time series data using image-based GANs.
Tasks	Time Series
Published	2019-02-14
URL	https://arxiv.org/abs/1902.05624v3
PDF	https://arxiv.org/pdf/1902.05624v3.pdf
PWC	https://paperswithcode.com/paper/quick-and-easy-time-series-generation-with
Repo
Framework

Arbitrary Shape Scene Text Detection with Adaptive Text Region Representation


Title	Arbitrary Shape Scene Text Detection with Adaptive Text Region Representation
Authors	Xiaobing Wang, Yingying Jiang, Zhenbo Luo, Cheng-Lin Liu, Hyunsoo Choi, Sungjin Kim
Abstract	Scene text detection attracts much attention in computer vision, because it can be widely used in many applications such as real-time text translation, automatic information entry, blind person assistance, robot sensing and so on. Though many methods have been proposed for horizontal and oriented texts, detecting irregular shape texts such as curved texts is still a challenging problem. To solve the problem, we propose a robust scene text detection method with adaptive text region representation. Given an input image, a text region proposal network is first used for extracting text proposals. Then, these proposals are verified and refined with a refinement network. Here, recurrent neural network based adaptive text region representation is proposed for text region refinement, where a pair of boundary points are predicted each time step until no new points are found. In this way, text regions of arbitrary shapes are detected and represented with adaptive number of boundary points. This gives more accurate description of text regions. Experimental results on five benchmarks, namely, CTW1500, TotalText, ICDAR2013, ICDAR2015 and MSRATD500, show that the proposed method achieves state-of-the-art in scene text detection.
Tasks	Scene Text Detection
Published	2019-05-15
URL	https://arxiv.org/abs/1905.05980v1
PDF	https://arxiv.org/pdf/1905.05980v1.pdf
PWC	https://paperswithcode.com/paper/arbitrary-shape-scene-text-detection-with
Repo
Framework

What are Neural Networks made of?


Title	What are Neural Networks made of?
Authors	Rene Schaub
Abstract	The success of Deep Learning methods is not well understood, though various attempts at explaining it have been made, typically centered on properties of stochastic gradient descent. Even less clear is why certain neural network architectures perform better than others. We provide a potential opening with the hypothesis that neural network training is a form of Genetic Programming.
Tasks
Published	2019-08-25
URL	https://arxiv.org/abs/1909.09588v1
PDF	https://arxiv.org/pdf/1909.09588v1.pdf
PWC	https://paperswithcode.com/paper/what-are-neural-networks-made-of
Repo
Framework

Phoneme-Based Contextualization for Cross-Lingual Speech Recognition in End-to-End Models


Title	Phoneme-Based Contextualization for Cross-Lingual Speech Recognition in End-to-End Models
Authors	Ke Hu, Antoine Bruguier, Tara N. Sainath, Rohit Prabhavalkar, Golan Pundak
Abstract	Contextual automatic speech recognition, i.e., biasing recognition towards a given context (e.g. user’s playlists, or contacts), is challenging in end-to-end (E2E) models. Such models maintain a limited number of candidates during beam-search decoding, and have been found to recognize rare named entities poorly. The problem is exacerbated when biasing towards proper nouns in foreign languages, e.g., geographic location names, which are virtually unseen in training and are thus out-of-vocabulary (OOV). While grapheme or wordpiece E2E models might have a difficult time spelling OOV words, phonemes are more acoustically salient and past work has shown that E2E phoneme models can better predict such words. In this work, we propose an E2E model containing both English wordpieces and phonemes in the modeling space, and perform contextual biasing of foreign words at the phoneme level by mapping pronunciations of foreign words into similar English phonemes. In experimental evaluations, we find that the proposed approach performs 16% better than a grapheme-only biasing model, and 8% better than a wordpiece-only biasing model on a foreign place name recognition task, with only slight degradation on regular English tasks.
Tasks	Speech Recognition
Published	2019-06-21
URL	https://arxiv.org/abs/1906.09292v3
PDF	https://arxiv.org/pdf/1906.09292v3.pdf
PWC	https://paperswithcode.com/paper/phoneme-based-contextualization-for-cross
Repo
Framework

Multi-Resolution Overlapping Stripes Network for Person Re-Identification


Title	Multi-Resolution Overlapping Stripes Network for Person Re-Identification
Authors	Arda Efe Okay, Manal AlGhamdi, Robert Westendorp, Mohamed Abdel-Mottaleb
Abstract	This paper addresses the person re-identification (PReID) problem by combining global and local information at multiple feature resolutions with different loss functions. Many previous studies address this problem using either part-based features or global features. In case of part-based representation, the spatial correlation between these parts is not considered, while global-based representation are not sensitive to spatial variations. This paper presents a part-based model with a multi-resolution network that uses different level of features. The output of the last two conv blocks is then partitioned horizontally and processed in pairs with overlapping stripes to cover the important information that might lie between parts. We use different loss functions to combine local and global information for classification. Experimental results on a benchmark dataset demonstrate that the presented method outperforms the state-of-the-art methods.
Tasks	Person Re-Identification
Published	2019-10-27
URL	https://arxiv.org/abs/1910.12322v1
PDF	https://arxiv.org/pdf/1910.12322v1.pdf
PWC	https://paperswithcode.com/paper/multi-resolution-overlapping-stripes-network
Repo
Framework

High-resolution home location prediction from tweets using deep learning with dynamic structure


Title	High-resolution home location prediction from tweets using deep learning with dynamic structure
Authors	Meysam Ghaffari, Ashok Srinivasan, Xiuwen Liu
Abstract	Timely and high-resolution estimates of the home locations of a sufficiently large subset of the population are critical for effective disaster response and public health intervention, but this is still an open problem. Conventional data sources, such as census and surveys, have a substantial time lag and cannot capture seasonal trends. Recently, social media data has been exploited to address this problem by leveraging its large user-base and real-time nature. However, inherent sparsity and noise, along with large estimation uncertainty in home locations, have limited their effectiveness. Consequently, much of previous research has aimed only at a coarse spatial resolution, with accuracy being limited for high-resolution methods. In this paper, we develop a deep-learning solution that uses a two-phase dynamic structure to deal with sparse and noisy social media data. In the first phase, high recall is achieved using a random forest, producing more balanced home location candidates. Then two deep neural networks are used to detect home locations with high accuracy. We obtained over 90% accuracy for large subsets on a commonly used dataset. Compared to other high-resolution methods, our approach yields up to 60% error reduction by reducing high-resolution home prediction error from over 21% to less than 8%. Systematic comparisons show that our method gives the highest accuracy both for the entire sample and for subsets. Evaluation on a real-world public health problem further validates the effectiveness of our approach.
Tasks
Published	2019-02-03
URL	https://arxiv.org/abs/1902.03111v2
PDF	https://arxiv.org/pdf/1902.03111v2.pdf
PWC	https://paperswithcode.com/paper/high-resolution-home-location-prediction-from
Repo
Framework

Surfing: Iterative optimization over incrementally trained deep networks


Title	Surfing: Iterative optimization over incrementally trained deep networks
Authors	Ganlin Song, Zhou Fan, John Lafferty
Abstract	We investigate a sequential optimization procedure to minimize the empirical risk functional $f_{\hat\theta}(x) = \frac{1}{2}\G_{\hat\theta}(x) - y^2$ for certain families of deep networks $G_{\theta}(x)$. The approach is to optimize a sequence of objective functions that use network parameters obtained during different stages of the training process. When initialized with random parameters $\theta_0$, we show that the objective $f_{\theta_0}(x)$ is “nice’’ and easy to optimize with gradient descent. As learning is carried out, we obtain a sequence of generative networks $x \mapsto G_{\theta_t}(x)$ and associated risk functions $f_{\theta_t}(x)$, where $t$ indicates a stage of stochastic gradient descent during training. Since the parameters of the network do not change by very much in each step, the surface evolves slowly and can be incrementally optimized. The algorithm is formalized and analyzed for a family of expansive networks. We call the procedure {\it surfing} since it rides along the peak of the evolving (negative) empirical risk function, starting from a smooth surface at the beginning of learning and ending with a wavy nonconvex surface after learning is complete. Experiments show how surfing can be used to find the global optimum and for compressed sensing even when direct gradient descent on the final learned network fails.
Tasks
Published	2019-07-19
URL	https://arxiv.org/abs/1907.08653v1
PDF	https://arxiv.org/pdf/1907.08653v1.pdf
PWC	https://paperswithcode.com/paper/surfing-iterative-optimization-over
Repo
Framework

Hetero-Center Loss for Cross-Modality Person Re-Identification


Title	Hetero-Center Loss for Cross-Modality Person Re-Identification
Authors	Yuanxin Zhu, Zhao Yang, Li Wang, Sai Zhao, Xiao Hu, Dapeng Tao
Abstract	Cross-modality person re-identification is a challenging problem which retrieves a given pedestrian image in RGB modality among all the gallery images in infrared modality. The task can address the limitation of RGB-based person Re-ID in dark environments. Existing researches mainly focus on enlarging inter-class differences of feature to solve the problem. However, few studies investigate improving intra-class cross-modality similarity, which is important for this issue. In this paper, we propose a novel loss function, called Hetero-Center loss (HC loss) to reduce the intra-class cross-modality variations. Specifically, HC loss can supervise the network learning the cross-modality invariant information by constraining the intra-class center distance between two heterogenous modalities. With the joint supervision of Cross-Entropy (CE) loss and HC loss, the network is trained to achieve two vital objectives, inter-class discrepancy and intra-class cross-modality similarity as much as possible. Besides, we propose a simple and high-performance network architecture to learn local feature representations for cross-modality person re-identification, which can be a baseline for future research. Extensive experiments indicate the effectiveness of the proposed methods, which outperform state-of-the-art methods by a wide margin.
Tasks	Person Re-Identification
Published	2019-10-22
URL	https://arxiv.org/abs/1910.09830v1
PDF	https://arxiv.org/pdf/1910.09830v1.pdf
PWC	https://paperswithcode.com/paper/hetero-center-loss-for-cross-modality-person
Repo
Framework