October 18, 2019

3119 words 15 mins read

Paper Group ANR 599

Learning Image Conditioned Label Space for Multilabel Classification. Aff2Vec: Affect–Enriched Distributional Word Representations. Radiative Transport Based Flame Volume Reconstruction from Videos. Review Helpfulness Assessment based on Convolutional Neural Network. New CleverHans Feature: Better Adversarial Robustness Evaluations with Attack Bun …

Learning Image Conditioned Label Space for Multilabel Classification


Title	Learning Image Conditioned Label Space for Multilabel Classification
Authors	Yi-Nan Li, Mei-Chen Yeh
Abstract	This work addresses the task of multilabel image classification. Inspired by the great success from deep convolutional neural networks (CNNs) for single-label visual-semantic embedding, we exploit extending these models for multilabel images. Specifically, we propose an image-dependent ranking model, which returns a ranked list of labels according to its relevance to the input image. In contrast to conventional CNN models that learn an image representation (i.e. the image embedding vector), the developed model learns a mapping (i.e. a transformation matrix) from an image in an attempt to differentiate between its relevant and irrelevant labels. Despite the conceptual simplicity of our approach, experimental results on a public benchmark dataset demonstrate that the proposed model achieves state-of-the-art performance while using fewer training images than other multilabel classification methods.
Tasks	Image Classification
Published	2018-02-21
URL	http://arxiv.org/abs/1802.07460v1
PDF	http://arxiv.org/pdf/1802.07460v1.pdf
PWC	https://paperswithcode.com/paper/learning-image-conditioned-label-space-for
Repo
Framework

Aff2Vec: Affect–Enriched Distributional Word Representations


Title	Aff2Vec: Affect–Enriched Distributional Word Representations
Authors	Sopan Khosla, Niyati Chhaya, Kushal Chawla
Abstract	Human communication includes information, opinions, and reactions. Reactions are often captured by the affective-messages in written as well as verbal communications. While there has been work in affect modeling and to some extent affective content generation, the area of affective word distributions in not well studied. Synsets and lexica capture semantic relationships across words. These models however lack in encoding affective or emotional word interpretations. Our proposed model, Aff2Vec provides a method for enriched word embeddings that are representative of affective interpretations of words. Aff2Vec outperforms the state–of–the–art in intrinsic word-similarity tasks. Further, the use of Aff2Vec representations outperforms baseline embeddings in downstream natural language understanding tasks including sentiment analysis, personality detection, and frustration prediction.
Tasks	Sentiment Analysis, Word Embeddings
Published	2018-05-21
URL	http://arxiv.org/abs/1805.07966v1
PDF	http://arxiv.org/pdf/1805.07966v1.pdf
PWC	https://paperswithcode.com/paper/aff2vec-affect-enriched-distributional-word
Repo
Framework

Radiative Transport Based Flame Volume Reconstruction from Videos


Title	Radiative Transport Based Flame Volume Reconstruction from Videos
Authors	Liang Shen, Dengming Zhu, Saad Nadeem, Zhaoqi Wang, Arie Kaufman
Abstract	We introduce a novel approach for flame volume reconstruction from videos using inexpensive charge-coupled device (CCD) consumer cameras. The approach includes an economical data capture technique using inexpensive CCD cameras. Leveraging the smear feature of the CCD chip, we present a technique for synchronizing CCD cameras while capturing flame videos from different views. Our reconstruction is based on the radiative transport equation which enables complex phenomena such as emission, extinction, and scattering to be used in the rendering process. Both the color intensity and temperature reconstructions are implemented using the CUDA parallel computing framework, which provides real-time performance and allows visualization of reconstruction results after every iteration. We present the results of our approach using real captured data and physically-based simulated data. Finally, we also compare our approach against the other state-of-the-art flame volume reconstruction methods and demonstrate the efficacy and efficiency of our approach in four different applications: (1) rendering of reconstructed flames in virtual environments, (2) rendering of reconstructed flames in augmented reality, (3) flame stylization, and (4) reconstruction of other semitransparent phenomena.
Tasks
Published	2018-09-17
URL	http://arxiv.org/abs/1809.06417v1
PDF	http://arxiv.org/pdf/1809.06417v1.pdf
PWC	https://paperswithcode.com/paper/radiative-transport-based-flame-volume
Repo
Framework

Review Helpfulness Assessment based on Convolutional Neural Network


Title	Review Helpfulness Assessment based on Convolutional Neural Network
Authors	Xianshan Qu, Xiaopeng Li, John R. Rose
Abstract	In this paper we describe the implementation of a convolutional neural network (CNN) used to assess online review helpfulness. To our knowledge, this is the first use of this architecture to address this problem. We explore the impact of two related factors impacting CNN performance: different word embedding initializations and different input review lengths. We also propose an approach to combining rating star information with review text to further improve prediction accuracy. We demonstrate that this can improve the overall accuracy by 2%. Finally, we evaluate the method on a benchmark dataset and show an improvement in accuracy relative to published results for traditional methods of 2.5% for a model trained using only review text and 4.24% for a model trained on a combination of rating star information and review text.
Tasks
Published	2018-08-27
URL	http://arxiv.org/abs/1808.09016v1
PDF	http://arxiv.org/pdf/1808.09016v1.pdf
PWC	https://paperswithcode.com/paper/review-helpfulness-assessment-based-on
Repo
Framework

New CleverHans Feature: Better Adversarial Robustness Evaluations with Attack Bundling


Title	New CleverHans Feature: Better Adversarial Robustness Evaluations with Attack Bundling
Authors	Ian Goodfellow
Abstract	This technical report describes a new feature of the CleverHans library called “attack bundling”. Many papers about adversarial examples present lists of error rates corresponding to different attack algorithms. A common approach is to take the maximum across this list and compare defenses against that error rate. We argue that a better approach is to use attack bundling: the max should be taken across many examples at the level of individual examples, then the error rate should be calculated by averaging after this maximization operation. Reporting the bundled attacker error rate provides a lower bound on the true worst-case error rate. The traditional approach of reporting the maximum error rate across attacks can underestimate the true worst-case error rate by an amount approaching 100% as the number of attacks approaches infinity. Attack bundling can be used with different prioritization schemes to optimize quantities such as error rate on adversarial examples, perturbation size needed to cause misclassification, or failure rate when using a specific confidence threshold.
Tasks
Published	2018-11-08
URL	http://arxiv.org/abs/1811.03685v1
PDF	http://arxiv.org/pdf/1811.03685v1.pdf
PWC	https://paperswithcode.com/paper/new-cleverhans-feature-better-adversarial
Repo
Framework

Disease-Atlas: Navigating Disease Trajectories with Deep Learning


Title	Disease-Atlas: Navigating Disease Trajectories with Deep Learning
Authors	Bryan Lim, Mihaela van der Schaar
Abstract	Joint models for longitudinal and time-to-event data are commonly used in longitudinal studies to forecast disease trajectories over time. While there are many advantages to joint modeling, the standard forms suffer from limitations that arise from a fixed model specification, and computational difficulties when applied to high-dimensional datasets. In this paper, we propose a deep learning approach to address these limitations, enhancing existing methods with the inherent flexibility and scalability of deep neural networks, while retaining the benefits of joint modeling. Using longitudinal data from a real-world medical dataset, we demonstrate improvements in performance and scalability, as well as robustness in the presence of irregularly sampled data.
Tasks
Published	2018-03-27
URL	http://arxiv.org/abs/1803.10254v3
PDF	http://arxiv.org/pdf/1803.10254v3.pdf
PWC	https://paperswithcode.com/paper/disease-atlas-navigating-disease-trajectories
Repo
Framework

SBAF: A New Activation Function for Artificial Neural Net based Habitability Classification


Title	SBAF: A New Activation Function for Artificial Neural Net based Habitability Classification
Authors	Snehanshu Saha, Archana Mathur, Kakoli Bora, Surbhi Agrawal, Suryoday Basak
Abstract	We explore the efficacy of using a novel activation function in Artificial Neural Networks (ANN) in characterizing exoplanets into different classes. We call this Saha-Bora Activation Function (SBAF) as the motivation is derived from long standing understanding of using advanced calculus in modeling habitability score of Exoplanets. The function is demonstrated to possess nice analytical properties and doesn’t seem to suffer from local oscillation problems. The manuscript presents the analytical properties of the activation function and the architecture implemented on the function. Keywords: Astroinformatics, Machine Learning, Exoplanets, ANN, Activation Function.
Tasks
Published	2018-06-06
URL	http://arxiv.org/abs/1806.01844v1
PDF	http://arxiv.org/pdf/1806.01844v1.pdf
PWC	https://paperswithcode.com/paper/sbaf-a-new-activation-function-for-artificial
Repo
Framework

Optimization of Information-Seeking Dialogue Strategy for Argumentation-Based Dialogue System


Title	Optimization of Information-Seeking Dialogue Strategy for Argumentation-Based Dialogue System
Authors	Hisao Katsumi, Takuya Hiraoka, Koichiro Yoshino, Kazeto Yamamoto, Shota Motoura, Kunihiko Sadamasa, Satoshi Nakamura
Abstract	Argumentation-based dialogue systems, which can handle and exchange arguments through dialogue, have been widely researched. It is required that these systems have sufficient supporting information to argue their claims rationally; however, the systems often do not have enough of such information in realistic situations. One way to fill in the gap is acquiring such missing information from dialogue partners (information-seeking dialogue). Existing information-seeking dialogue systems are based on handcrafted dialogue strategies that exhaustively examine missing information. However, the proposed strategies are not specialized in collecting information for constructing rational arguments. Moreover, the number of system’s inquiry candidates grows in accordance with the size of the argument set that the system deal with. In this paper, we formalize the process of information-seeking dialogue as Markov decision processes (MDPs) and apply deep reinforcement learning (DRL) for automatically optimizing a dialogue strategy. By utilizing DRL, our dialogue strategy can successfully minimize objective functions, the number of turns it takes for our system to collect necessary information in a dialogue. We conducted dialogue experiments using two datasets from different domains of argumentative dialogue. Experimental results show that the proposed formalization based on MDP works well, and the policy optimized by DRL outperformed existing heuristic dialogue strategies.
Tasks
Published	2018-11-26
URL	http://arxiv.org/abs/1811.10728v1
PDF	http://arxiv.org/pdf/1811.10728v1.pdf
PWC	https://paperswithcode.com/paper/optimization-of-information-seeking-dialogue
Repo
Framework

Model-Free Adaptive Optimal Control of Episodic Fixed-Horizon Manufacturing Processes using Reinforcement Learning


Title	Model-Free Adaptive Optimal Control of Episodic Fixed-Horizon Manufacturing Processes using Reinforcement Learning
Authors	Johannes Dornheim, Norbert Link, Peter Gumbsch
Abstract	A self-learning optimal control algorithm for episodic fixed-horizon manufacturing processes with time-discrete control actions is proposed and evaluated on a simulated deep drawing process. The control model is built during consecutive process executions under optimal control via reinforcement learning, using the measured product quality as reward after each process execution. Prior model formulation, which is required by state-of-the-art algorithms from model predictive control and approximate dynamic programming, is therefore obsolete. This avoids several difficulties namely in system identification, accurate modelling, and runtime complexity, that arise when dealing with processes subject to nonlinear dynamics and stochastic influences. Instead of using pre-created process and observation models, value function-based reinforcement learning algorithms build functions of expected future reward, which are used to derive optimal process control decisions. The expectation functions are learned online, by interacting with the process. The proposed algorithm takes stochastic variations of the process conditions into account and is able to cope with partial observability. A Q-learning-based method for adaptive optimal control of partially observable episodic fixed-horizon manufacturing processes is developed and studied. The resulting algorithm is instantiated and evaluated by applying it to a simulated stochastic optimal control problem in metal sheet deep drawing.
Tasks	Q-Learning
Published	2018-09-18
URL	http://arxiv.org/abs/1809.06646v3
PDF	http://arxiv.org/pdf/1809.06646v3.pdf
PWC	https://paperswithcode.com/paper/model-free-adaptive-optimal-control-of
Repo
Framework

Innovative 3D Depth Map Generation From A Holoscopic 3D Image Based on Graph Cut Technique


Title	Innovative 3D Depth Map Generation From A Holoscopic 3D Image Based on Graph Cut Technique
Authors	Bodor Almatrouk, Mohammad Rafiq Swash, Abdul Hamid Sadka
Abstract	Holoscopic 3D imaging is a promising technique for capturing full colour spatial 3D images using a single aperture holoscopic 3D camera. It mimics fly’s eye technique with a microlens array, which views the scene at a slightly different angle to its adjacent lens that records three dimensional information onto a two dimensional surface. This paper proposes a method of depth map generation from a holoscopic 3D image based on graph cut technique. The principal objective of this study is to estimate the depth information presented in a holoscopic 3D image with high precision. As such, depth map extraction is measured from a single still holoscopic 3D image which consists of multiple viewpoint images. The viewpoints are extracted and utilised for disparity calculation via disparity space image technique and pixels displacement is measured with sub pixel accuracy to overcome the issue of the narrow baseline between the viewpoint images for stereo matching. In addition, cost aggregation is used to correlate the matching costs within a particular neighbouring region using sum of absolute difference SAD combined with gradient-based metric and winner takes all algorithm is employed to select the minimum elements in the array as optimal disparity value. Finally, the optimal depth map is obtained using graph cut technique. The proposed method extends the utilisation of holoscopic 3D imaging system and enables the expansion of the technology for various applications of autonomous robotics, medical, inspection, AR VR, security and entertainment where 3D depth sensing and measurement are a concern.
Tasks	Stereo Matching, Stereo Matching Hand
Published	2018-11-10
URL	http://arxiv.org/abs/1811.04217v1
PDF	http://arxiv.org/pdf/1811.04217v1.pdf
PWC	https://paperswithcode.com/paper/innovative-3d-depth-map-generation-from-a
Repo
Framework

Opening the black box of deep learning


Title	Opening the black box of deep learning
Authors	Dian Lei, Xiaoxiao Chen, Jianfei Zhao
Abstract	The great success of deep learning shows that its technology contains profound truth, and understanding its internal mechanism not only has important implications for the development of its technology and effective application in various fields, but also provides meaningful insights into the understanding of human brain mechanism. At present, most of the theoretical research on deep learning is based on mathematics. This dissertation proposes that the neural network of deep learning is a physical system, examines deep learning from three different perspectives: microscopic, macroscopic, and physical world views, answers multiple theoretical puzzles in deep learning by using physics principles. For example, from the perspective of quantum mechanics and statistical physics, this dissertation presents the calculation methods for convolution calculation, pooling, normalization, and Restricted Boltzmann Machine, as well as the selection of cost functions, explains why deep learning must be deep, what characteristics are learned in deep learning, why Convolutional Neural Networks do not have to be trained layer by layer, and the limitations of deep learning, etc., and proposes the theoretical direction and basis for the further development of deep learning now and in the future. The brilliance of physics flashes in deep learning, we try to establish the deep learning technology based on the scientific theory of physics.
Tasks
Published	2018-05-22
URL	http://arxiv.org/abs/1805.08355v1
PDF	http://arxiv.org/pdf/1805.08355v1.pdf
PWC	https://paperswithcode.com/paper/opening-the-black-box-of-deep-learning
Repo
Framework

Privacy-Preserving Distributed Parameter Estimation for Probability Distribution of Wind Power Forecast Error


Title	Privacy-Preserving Distributed Parameter Estimation for Probability Distribution of Wind Power Forecast Error
Authors	Mengshuo Jia, Shaowei Huang, Zhiwen Wang, Chen Shen
Abstract	Building the conditional probability distribution of wind power forecast errors benefits both wind farms (WFs) and independent system operators (ISOs). Establishing the joint probability distribution of wind power and the corresponding forecast data of spatially correlated WFs is the foundation for deriving the conditional probability distribution. Traditional parameter estimation methods for probability distributions require the collection of historical data of all WFs. However, in the context of multi-regional interconnected grids, neither regional ISOs nor WFs can collect the raw data of WFs in other regions due to privacy or competition considerations. Therefore, based on the Gaussian mixture model, this paper first proposes a privacy-preserving distributed expectation-maximization algorithm to estimate the parameters of the joint probability distribution. This algorithm consists of two original methods: (1) a privacy-preserving distributed summation algorithm and (2) a privacy-preserving distributed inner product algorithm. Then, we derive each WF’s conditional probability distribution of forecast error from the joint one. By the proposed algorithms, WFs only need local calculations and privacy-preserving neighboring communications to achieve the whole parameter estimation. These algorithms are verified using the wind integration data set published by the NREL.
Tasks	Decision Making
Published	2018-12-17
URL	https://arxiv.org/abs/1812.09247v4
PDF	https://arxiv.org/pdf/1812.09247v4.pdf
PWC	https://paperswithcode.com/paper/privacy-preserving-distributed-joint
Repo
Framework

Robust and Efficient Boosting Method using the Conditional Risk


Title	Robust and Efficient Boosting Method using the Conditional Risk
Authors	Zhi Xiao, Zhe Luo, Bo Zhong, Xin Dang
Abstract	Well-known for its simplicity and effectiveness in classification, AdaBoost, however, suffers from overfitting when class-conditional distributions have significant overlap. Moreover, it is very sensitive to noise that appears in the labels. This article tackles the above limitations simultaneously via optimizing a modified loss function (i.e., the conditional risk). The proposed approach has the following two advantages. (1) It is able to directly take into account label uncertainty with an associated label confidence. (2) It introduces a “trustworthiness” measure on training samples via the Bayesian risk rule, and hence the resulting classifier tends to have finite sample performance that is superior to that of the original AdaBoost when there is a large overlap between class conditional distributions. Theoretical properties of the proposed method are investigated. Extensive experimental results using synthetic data and real-world data sets from UCI machine learning repository are provided. The empirical study shows the high competitiveness of the proposed method in predication accuracy and robustness when compared with the original AdaBoost and several existing robust AdaBoost algorithms.
Tasks
Published	2018-06-21
URL	http://arxiv.org/abs/1806.08151v1
PDF	http://arxiv.org/pdf/1806.08151v1.pdf
PWC	https://paperswithcode.com/paper/robust-and-efficient-boosting-method-using
Repo
Framework

Kernel based low-rank sparse model for single image super-resolution


Title	Kernel based low-rank sparse model for single image super-resolution
Authors	Jiahe Shi, Chun Qi
Abstract	Self-similarity learning has been recognized as a promising method for single image super-resolution (SR) to produce high-resolution (HR) image in recent years. The performance of learning based SR reconstruction, however, highly depends on learned representation coeffcients. Due to the degradation of input image, conventional sparse coding is prone to produce unfaithful representation coeffcients. To this end, we propose a novel kernel based low-rank sparse model with self-similarity learning for single image SR which incorporates nonlocalsimilarity prior to enforce similar patches having similar representation weights. We perform a gradual magnification scheme, using self-examples extracted from the degraded input image and up-scaled versions. To exploit nonlocal-similarity, we concatenate the vectorized input patch and its nonlocal neighbors at different locations into a data matrix which consists of similar components. Then we map the nonlocal data matrix into a high-dimensional feature space by kernel method to capture their nonlinear structures. Under the assumption that the sparse coeffcients for the nonlocal data in the kernel space should be low-rank, we impose low-rank constraint on sparse coding to share similarities among representation coeffcients and remove outliers in order that stable weights for SR reconstruction can be obtained. Experimental results demonstrate the advantage of our proposed method in both visual quality and reconstruction error.
Tasks	Image Super-Resolution, Super-Resolution
Published	2018-09-27
URL	http://arxiv.org/abs/1809.10582v1
PDF	http://arxiv.org/pdf/1809.10582v1.pdf
PWC	https://paperswithcode.com/paper/kernel-based-low-rank-sparse-model-for-single
Repo
Framework

Semi-Supervised Convolutional Neural Networks for Human Activity Recognition


Title	Semi-Supervised Convolutional Neural Networks for Human Activity Recognition
Authors	Ming Zeng, Tong Yu, Xiao Wang, Le T. Nguyen, Ole J. Mengshoel, Ian Lane
Abstract	Labeled data used for training activity recognition classifiers are usually limited in terms of size and diversity. Thus, the learned model may not generalize well when used in real-world use cases. Semi-supervised learning augments labeled examples with unlabeled examples, often resulting in improved performance. However, the semi-supervised methods studied in the activity recognition literatures assume that feature engineering is already done. In this paper, we lift this assumption and present two semi-supervised methods based on convolutional neural networks (CNNs) to learn discriminative hidden features. Our semi-supervised CNNs learn from both labeled and unlabeled data while also performing feature learning on raw sensor data. In experiments on three real world datasets, we show that our CNNs outperform supervised methods and traditional semi-supervised learning methods by up to 18% in mean F1-score (Fm).
Tasks	Activity Recognition, Feature Engineering, Human Activity Recognition
Published	2018-01-22
URL	http://arxiv.org/abs/1801.07827v1
PDF	http://arxiv.org/pdf/1801.07827v1.pdf
PWC	https://paperswithcode.com/paper/semi-supervised-convolutional-neural-networks
Repo
Framework