October 18, 2019

3057 words 15 mins read

Paper Group ANR 510

A Pseudo Multi-Exposure Fusion Method Using Single Image. Number Sequence Prediction Problems for Evaluating Computational Powers of Neural Networks. On the Needs for Rotations in Hypercubic Quantization Hashing. Modeling Activity Tracker Data Using Deep Boltzmann Machines. Discrete Sampling using Semigradient-based Product Mixtures. Co-Creative Le …

A Pseudo Multi-Exposure Fusion Method Using Single Image


Title	A Pseudo Multi-Exposure Fusion Method Using Single Image
Authors	Yuma Kinoshita, Sayaka Shiota, Hitoshi Kiya
Abstract	This paper proposes a novel pseudo multi-exposure image fusion method based on a single image. Multi-exposure image fusion is used to produce images without saturation regions, by using photos with different exposures. However, it is difficult to take photos suited for the multi-exposure image fusion when we take a photo of dynamic scenes or record a video. In addition, the multi-exposure image fusion cannot be applied to existing images with a single exposure or videos. The proposed method enables us to produce pseudo multi-exposure images from a single image. To produce multi-exposure images, the proposed method utilizes the relationship between the exposure values and pixel values, which is obtained by assuming that a digital camera has a linear response function. Moreover, it is shown that the use of a local contrast enhancement method allows us to produce pseudo multi-exposure images with higher quality. Most of conventional multi-exposure image fusion methods are also applicable to the proposed multi-exposure images. Experimental results show the effectiveness of the proposed method by comparing the proposed one with conventional ones.
Tasks
Published	2018-08-01
URL	http://arxiv.org/abs/1808.00195v1
PDF	http://arxiv.org/pdf/1808.00195v1.pdf
PWC	https://paperswithcode.com/paper/a-pseudo-multi-exposure-fusion-method-using
Repo
Framework

Number Sequence Prediction Problems for Evaluating Computational Powers of Neural Networks


Title	Number Sequence Prediction Problems for Evaluating Computational Powers of Neural Networks
Authors	Hyoungwook Nam, Segwang Kim, Kyomin Jung
Abstract	Inspired by number series tests to measure human intelligence, we suggest number sequence prediction tasks to assess neural network models’ computational powers for solving algorithmic problems. We define the complexity and difficulty of a number sequence prediction task with the structure of the smallest automaton that can generate the sequence. We suggest two types of number sequence prediction problems: the number-level and the digit-level problems. The number-level problems format sequences as 2-dimensional grids of digits and the digit-level problems provide a single digit input per a time step. The complexity of a number-level sequence prediction can be defined with the depth of an equivalent combinatorial logic, and the complexity of a digit-level sequence prediction can be defined with an equivalent state automaton for the generation rule. Experiments with number-level sequences suggest that CNN models are capable of learning the compound operations of sequence generation rules, but the depths of the compound operations are limited. For the digit-level problems, simple GRU and LSTM models can solve some problems with the complexity of finite state automata. Memory augmented models such as Stack-RNN, Attention, and Neural Turing Machines can solve the reverse-order task which has the complexity of simple pushdown automaton. However, all of above cannot solve general Fibonacci, Arithmetic or Geometric sequence generation problems that represent the complexity of queue automata or Turing machines. The results show that our number sequence prediction problems effectively evaluate machine learning models’ computational capabilities.
Tasks
Published	2018-05-19
URL	http://arxiv.org/abs/1805.07494v2
PDF	http://arxiv.org/pdf/1805.07494v2.pdf
PWC	https://paperswithcode.com/paper/number-sequence-prediction-problems-for
Repo
Framework

On the Needs for Rotations in Hypercubic Quantization Hashing


Title	On the Needs for Rotations in Hypercubic Quantization Hashing
Authors	Anne Morvan, Antoine Souloumiac, Krzysztof Choromanski, Cédric Gouy-Pailler, Jamal Atif
Abstract	The aim of this paper is to endow the well-known family of hypercubic quantization hashing methods with theoretical guarantees. In hypercubic quantization, applying a suitable (random or learned) rotation after dimensionality reduction has been experimentally shown to improve the results accuracy in the nearest neighbors search problem. We prove in this paper that the use of these rotations is optimal under some mild assumptions: getting optimal binary sketches is equivalent to applying a rotation uniformizing the diagonal of the covariance matrix between data points. Moreover, for two closed points, the probability to have dissimilar binary sketches is upper bounded by a factor of the initial distance between the data points. Relaxing these assumptions, we obtain a general concentration result for random matrices. We also provide some experiments illustrating these theoretical points and compare a set of algorithms in both the batch and online settings.
Tasks	Dimensionality Reduction, Quantization
Published	2018-02-12
URL	http://arxiv.org/abs/1802.03936v1
PDF	http://arxiv.org/pdf/1802.03936v1.pdf
PWC	https://paperswithcode.com/paper/on-the-needs-for-rotations-in-hypercubic
Repo
Framework

Modeling Activity Tracker Data Using Deep Boltzmann Machines


Title	Modeling Activity Tracker Data Using Deep Boltzmann Machines
Authors	Martin Treppner, Stefan Lenz, Harald Binder, Daniela Zöller
Abstract	Commercial activity trackers are set to become an essential tool in health research, due to increasing availability in the general population. The corresponding vast amounts of mostly unlabeled data pose a challenge to statistical modeling approaches. To investigate the feasibility of deep learning approaches for unsupervised learning with such data, we examine weekly usage patterns of Fitbit activity trackers with deep Boltzmann machines (DBMs). This method is particularly suitable for modeling complex joint distributions via latent variables. We also chose this specific procedure because it is a generative approach, i.e., artificial samples can be generated to explore the learned structure. We describe how the data can be preprocessed to be compatible with binary DBMs. The results reveal two distinct usage patterns in which one group frequently uses trackers on Mondays and Tuesdays, whereas the other uses trackers during the entire week. This exemplary result shows that DBMs are feasible and can be useful for modeling activity tracker data.
Tasks
Published	2018-02-28
URL	http://arxiv.org/abs/1802.10576v1
PDF	http://arxiv.org/pdf/1802.10576v1.pdf
PWC	https://paperswithcode.com/paper/modeling-activity-tracker-data-using-deep
Repo
Framework

Discrete Sampling using Semigradient-based Product Mixtures


Title	Discrete Sampling using Semigradient-based Product Mixtures
Authors	Alkis Gotovos, Hamed Hassani, Andreas Krause, Stefanie Jegelka
Abstract	We consider the problem of inference in discrete probabilistic models, that is, distributions over subsets of a finite ground set. These encompass a range of well-known models in machine learning, such as determinantal point processes and Ising models. Locally-moving Markov chain Monte Carlo algorithms, such as the Gibbs sampler, are commonly used for inference in such models, but their convergence is, at times, prohibitively slow. This is often caused by state-space bottlenecks that greatly hinder the movement of such samplers. We propose a novel sampling strategy that uses a specific mixture of product distributions to propose global moves and, thus, accelerate convergence. Furthermore, we show how to construct such a mixture using semigradient information. We illustrate the effectiveness of combining our sampler with existing ones, both theoretically on an example model, as well as practically on three models learned from real-world data sets.
Tasks	Point Processes
Published	2018-07-04
URL	http://arxiv.org/abs/1807.01808v2
PDF	http://arxiv.org/pdf/1807.01808v2.pdf
PWC	https://paperswithcode.com/paper/discrete-sampling-using-semigradient-based
Repo
Framework

Co-Creative Level Design via Machine Learning


Title	Co-Creative Level Design via Machine Learning
Authors	Matthew Guzdial, Nicholas Liao, Mark Riedl
Abstract	Procedural Level Generation via Machine Learning (PLGML), the study of generating game levels with machine learning, has received a large amount of recent academic attention. For certain measures these approaches have shown success at replicating the quality of existing game levels. However, it is unclear the extent to which they might benefit human designers. In this paper we present a framework for co-creative level design with a PLGML agent. In support of this framework we present results from a user study and results from a comparative study of PLGML approaches.
Tasks
Published	2018-09-25
URL	http://arxiv.org/abs/1809.09420v1
PDF	http://arxiv.org/pdf/1809.09420v1.pdf
PWC	https://paperswithcode.com/paper/co-creative-level-design-via-machine-learning
Repo
Framework

Modular Generative Adversarial Networks


Title	Modular Generative Adversarial Networks
Authors	Bo Zhao, Bo Chang, Zequn Jie, Leonid Sigal
Abstract	Existing methods for multi-domain image-to-image translation (or generation) attempt to directly map an input image (or a random vector) to an image in one of the output domains. However, most existing methods have limited scalability and robustness, since they require building independent models for each pair of domains in question. This leads to two significant shortcomings: (1) the need to train exponential number of pairwise models, and (2) the inability to leverage data from other domains when training a particular pairwise mapping. Inspired by recent work on module networks, this paper proposes ModularGAN for multi-domain image generation and image-to-image translation. ModularGAN consists of several reusable and composable modules that carry on different functions (e.g., encoding, decoding, transformations). These modules can be trained simultaneously, leveraging data from all domains, and then combined to construct specific GAN networks at test time, according to the specific image translation task. This leads to ModularGAN’s superior flexibility of generating (or translating to) an image in any desired domain. Experimental results demonstrate that our model not only presents compelling perceptual results but also outperforms state-of-the-art methods on multi-domain facial attribute transfer.
Tasks	Image Generation, Image-to-Image Translation
Published	2018-04-10
URL	http://arxiv.org/abs/1804.03343v1
PDF	http://arxiv.org/pdf/1804.03343v1.pdf
PWC	https://paperswithcode.com/paper/modular-generative-adversarial-networks
Repo
Framework

Structure Learning Using Forced Pruning


Title	Structure Learning Using Forced Pruning
Authors	Ahmed Abdelatty, Pracheta Sahoo, Chiradeep Roy
Abstract	Markov networks are widely used in many Machine Learning applications including natural language processing, computer vision, and bioinformatics . Learning Markov networks have many complications ranging from intractable computations involved to the possibility of learning a model with a huge number of parameters. In this report, we provide a computationally tractable greedy heuristic for learning Markov networks structure. The proposed heuristic results in a model with a limited predefined number of parameters. We ran our method on 3 fully-observed real datasets, and we observed that our method is doing comparably good to the state of the art methods.
Tasks
Published	2018-12-03
URL	http://arxiv.org/abs/1812.00975v1
PDF	http://arxiv.org/pdf/1812.00975v1.pdf
PWC	https://paperswithcode.com/paper/structure-learning-using-forced-pruning
Repo
Framework

Optimal Clustering under Uncertainty


Title	Optimal Clustering under Uncertainty
Authors	Lori A. Dalton, Marco E. Benalcázar, Edward R. Dougherty
Abstract	Classical clustering algorithms typically either lack an underlying probability framework to make them predictive or focus on parameter estimation rather than defining and minimizing a notion of error. Recent work addresses these issues by developing a probabilistic framework based on the theory of random labeled point processes and characterizing a Bayes clusterer that minimizes the number of misclustered points. The Bayes clusterer is analogous to the Bayes classifier. Whereas determining a Bayes classifier requires full knowledge of the feature-label distribution, deriving a Bayes clusterer requires full knowledge of the point process. When uncertain of the point process, one would like to find a robust clusterer that is optimal over the uncertainty, just as one may find optimal robust classifiers with uncertain feature-label distributions. Herein, we derive an optimal robust clusterer by first finding an effective random point process that incorporates all randomness within its own probabilistic structure and from which a Bayes clusterer can be derived that provides an optimal robust clusterer relative to the uncertainty. This is analogous to the use of effective class-conditional distributions in robust classification. After evaluating the performance of robust clusterers in synthetic mixtures of Gaussians models, we apply the framework to granular imaging, where we make use of the asymptotic granulometric moment theory for granular images to relate robust clustering theory to the application.
Tasks	Point Processes
Published	2018-06-02
URL	http://arxiv.org/abs/1806.00672v1
PDF	http://arxiv.org/pdf/1806.00672v1.pdf
PWC	https://paperswithcode.com/paper/optimal-clustering-under-uncertainty
Repo
Framework

Learning Instance-Aware Object Detection Using Determinantal Point Processes


Title	Learning Instance-Aware Object Detection Using Determinantal Point Processes
Authors	Nuri Kim, Donghoon Lee, Songhwai Oh
Abstract	Recent object detectors find instances while categorizing candidate regions. As each region is evaluated independently, the number of candidate regions from a detector is usually larger than the number of objects. Since the final goal of detection is to assign a single detection to each object, a heuristic algorithm, such as non-maximum suppression (NMS), is used to select a single bounding box for an object. While simple heuristic algorithms are effective for stand-alone objects, they can fail to detect overlapped objects. In this paper, we address this issue by training a network to distinguish different objects using the relationship between candidate boxes. We propose an instance-aware detection network (IDNet), which can learn to extract features from candidate regions and measure their similarities. Based on pairwise similarities and detection qualities, the IDNet selects a subset of candidate bounding boxes using instance-aware determinantal point process inference (IDPP). Extensive experiments demonstrate that the proposed algorithm achieves significant improvements for detecting overlapped objects compared to existing state-of-the-art detection methods on the PASCAL VOC and MS COCO datasets.
Tasks	Object Detection, Point Processes
Published	2018-05-28
URL	https://arxiv.org/abs/1805.10765v3
PDF	https://arxiv.org/pdf/1805.10765v3.pdf
PWC	https://paperswithcode.com/paper/learning-instance-aware-object-detection
Repo
Framework

One-Class Kernel Spectral Regression


Title	One-Class Kernel Spectral Regression
Authors	Shervin Rahimzadeh Arashloo, Josef Kittler
Abstract	The paper introduces a new efficient nonlinear one-class classifier formulated as the Rayleigh quotient criterion optimisation. The method, operating in a reproducing kernel Hilbert space, minimises the scatter of target distribution along an optimal projection direction while at the same time keeping projections of positive observations distant from the mean of the negative class. We provide a graph embedding view of the problem which can then be solved efficiently using the spectral regression approach. In this sense, unlike previous similar methods which often require costly eigen-computations of dense matrices, the proposed approach casts the problem under consideration into a regression framework which is computationally more efficient. In particular, it is shown that the dominant complexity of the proposed method is the complexity of computing the kernel matrix. Additional appealing characteristics of the proposed one-class classifier are: 1-the ability to be trained in an incremental fashion (allowing for application in streaming data scenarios while also reducing the computational complexity in a non-streaming operation mode); 2-being unsupervised, but providing the option for refining the solution using negative training examples, when available; And last but not the least, 3-the use of the kernel trick which facilitates a nonlinear mapping of the data into a high-dimensional feature space to seek better solutions.
Tasks	Graph Embedding, One-class classifier, Outlier Detection
Published	2018-07-03
URL	http://arxiv.org/abs/1807.01085v6
PDF	http://arxiv.org/pdf/1807.01085v6.pdf
PWC	https://paperswithcode.com/paper/one-class-kernel-spectral-regression
Repo
Framework

Discovering conservation laws from data for control


Title	Discovering conservation laws from data for control
Authors	Eurika Kaiser, J. Nathan Kutz, Steven L. Brunton
Abstract	Conserved quantities, i.e. constants of motion, are critical for characterizing many dynamical systems in science and engineering. These quantities are related to underlying symmetries and they provide fundamental knowledge about physical laws, describe the evolution of the system, and enable system reduction. In this work, we formulate a data-driven architecture for discovering conserved quantities based on Koopman theory. The Koopman operator has emerged as a principled linear embedding of nonlinear dynamics, and its eigenfunctions establish intrinsic coordinates along which the dynamics behave linearly. Interestingly, eigenfunctions of the Koopman operator associated with vanishing eigenvalues correspond to conserved quantities of the underlying system. In this paper, we show that these invariants may be identified with data-driven regression and power series expansions, based on the infinitesimal generator of the Koopman operator. We further establish a connection between the Koopman framework, conserved quantities, and the Lie-Poisson bracket. This data-driven method for discovering conserved quantities is demonstrated on the three-dimensional rigid body equations, where we simultaneously discover the total energy and angular momentum and use these intrinsic coordinates to develop a model predictive controller to track a given reference value.
Tasks
Published	2018-11-02
URL	http://arxiv.org/abs/1811.00961v1
PDF	http://arxiv.org/pdf/1811.00961v1.pdf
PWC	https://paperswithcode.com/paper/discovering-conservation-laws-from-data-for
Repo
Framework

Mini-Unmanned Aerial Vehicle-Based Remote Sensing: Techniques, Applications, and Prospects


Title	Mini-Unmanned Aerial Vehicle-Based Remote Sensing: Techniques, Applications, and Prospects
Authors	Tian-Zhu Xiang, Gui-Song Xia, Liangpei Zhang
Abstract	The past few decades have witnessed the great progress of unmanned aircraft vehicles (UAVs) in civilian fields, especially in photogrammetry and remote sensing. In contrast with the platforms of manned aircraft and satellite, the UAV platform holds many promising characteristics: flexibility, efficiency, high-spatial/temporal resolution, low cost, easy operation, etc., which make it an effective complement to other remote-sensing platforms and a cost-effective means for remote sensing. Considering the popularity and expansion of UAV-based remote sensing in recent years, this paper provides a systematic survey on the recent advances and future prospectives of UAVs in the remote-sensing community. Specifically, the main challenges and key technologies of remote-sensing data processing based on UAVs are discussed and summarized firstly. Then, we provide an overview of the widespread applications of UAVs in remote sensing. Finally, some prospects for future work are discussed. We hope this paper will provide remote-sensing researchers an overall picture of recent UAV-based remote sensing developments and help guide the further research on this topic.
Tasks
Published	2018-12-19
URL	https://arxiv.org/abs/1812.07770v3
PDF	https://arxiv.org/pdf/1812.07770v3.pdf
PWC	https://paperswithcode.com/paper/mini-uav-based-remote-sensing-techniques
Repo
Framework

Multi-Head Decoder for End-to-End Speech Recognition


Title	Multi-Head Decoder for End-to-End Speech Recognition
Authors	Tomoki Hayashi, Shinji Watanabe, Tomoki Toda, Kazuya Takeda
Abstract	This paper presents a new network architecture called multi-head decoder for end-to-end speech recognition as an extension of a multi-head attention model. In the multi-head attention model, multiple attentions are calculated, and then, they are integrated into a single attention. On the other hand, instead of the integration in the attention level, our proposed method uses multiple decoders for each attention and integrates their outputs to generate a final output. Furthermore, in order to make each head to capture the different modalities, different attention functions are used for each head, leading to the improvement of the recognition performance with an ensemble effect. To evaluate the effectiveness of our proposed method, we conduct an experimental evaluation using Corpus of Spontaneous Japanese. Experimental results demonstrate that our proposed method outperforms the conventional methods such as location-based and multi-head attention models, and that it can capture different speech/linguistic contexts within the attention-based encoder-decoder framework.
Tasks	End-To-End Speech Recognition, Speech Recognition
Published	2018-04-22
URL	http://arxiv.org/abs/1804.08050v2
PDF	http://arxiv.org/pdf/1804.08050v2.pdf
PWC	https://paperswithcode.com/paper/multi-head-decoder-for-end-to-end-speech
Repo
Framework

Class-conditional embeddings for music source separation


Title	Class-conditional embeddings for music source separation
Authors	Prem Seetharaman, Gordon Wichern, Shrikant Venkataramani, Jonathan Le Roux
Abstract	Isolating individual instruments in a musical mixture has a myriad of potential applications, and seems imminently achievable given the levels of performance reached by recent deep learning methods. While most musical source separation techniques learn an independent model for each instrument, we propose using a common embedding space for the time-frequency bins of all instruments in a mixture inspired by deep clustering and deep attractor networks. Additionally, an auxiliary network is used to generate parameters of a Gaussian mixture model (GMM) where the posterior distribution over GMM components in the embedding space can be used to create a mask that separates individual sources from a mixture. In addition to outperforming a mask-inference baseline on the MUSDB-18 dataset, our embedding space is easily interpretable and can be used for query-based separation.
Tasks	Music Source Separation
Published	2018-11-07
URL	http://arxiv.org/abs/1811.03076v1
PDF	http://arxiv.org/pdf/1811.03076v1.pdf
PWC	https://paperswithcode.com/paper/class-conditional-embeddings-for-music-source
Repo
Framework