January 27, 2020

2906 words 14 mins read

Paper Group ANR 1246

Improving the resolution of microscope by deconvolution after dense scan. Privacy-Preserving Classification of Personal Text Messages with Secure Multi-Party Computation: An Application to Hate-Speech Detection. Agent-Based Adaptive Level Generation for Dynamic Difficulty Adjustment in Angry Birds. Progressive Attention Memory Network for Movie Sto …

Improving the resolution of microscope by deconvolution after dense scan


Title	Improving the resolution of microscope by deconvolution after dense scan
Authors	Yaohua Xie
Abstract	Super-resolution microscopes (such as STED) illuminate samples with a tiny spot, and achieve very high resolution. But structures smaller than the spot cannot be resolved in this way. Therefore, we propose a technique to solve this problem. It is termed “Deconvolution after Dense Scan (DDS)". First, a preprocessing stage is introduced to eliminate the optical uncertainty of the peripheral areas around the sample’s ROI (Region of Interest). Then, the ROI is scanned densely together with its peripheral areas. Finally, the high resolution image is recovered by deconvolution. The proposed technique does not need to modify the apparatus much, and is mainly performed by algorithm. Simulation experiments show that the technique can further improve the resolution of super-resolution microscopes.
Tasks	Super-Resolution
Published	2019-07-06
URL	https://arxiv.org/abs/1907.05275v3
PDF	https://arxiv.org/pdf/1907.05275v3.pdf
PWC	https://paperswithcode.com/paper/improving-the-resolution-of-microscope-by
Repo
Framework

Privacy-Preserving Classification of Personal Text Messages with Secure Multi-Party Computation: An Application to Hate-Speech Detection


Title	Privacy-Preserving Classification of Personal Text Messages with Secure Multi-Party Computation: An Application to Hate-Speech Detection
Authors	Martine De Cock, Rafael Dowsley, Anderson C. A. Nascimento, Devin Reich, Ariel Todoki
Abstract	Classification of personal text messages has many useful applications in surveillance, e-commerce, and mental health care, to name a few. Giving applications access to personal texts can easily lead to (un)intentional privacy violations. We propose the first privacy-preserving solution for text classification that is provably secure. Our method, which is based on Secure Multiparty Computation (SMC), encompasses both feature extraction from texts, and subsequent classification with logistic regression and tree ensembles. We prove that when using our secure text classification method, the application does not learn anything about the text, and the author of the text does not learn anything about the text classification model used by the application beyond what is given by the classification result itself. We perform end-to-end experiments with an application for detecting hate speech against women and immigrants, demonstrating excellent runtime results without loss of accuracy.
Tasks	Hate Speech Detection, Text Classification
Published	2019-06-05
URL	https://arxiv.org/abs/1906.02325v1
PDF	https://arxiv.org/pdf/1906.02325v1.pdf
PWC	https://paperswithcode.com/paper/privacy-preserving-classification-of-personal
Repo
Framework

Agent-Based Adaptive Level Generation for Dynamic Difficulty Adjustment in Angry Birds


Title	Agent-Based Adaptive Level Generation for Dynamic Difficulty Adjustment in Angry Birds
Authors	Matthew Stephenson, Jochen Renz
Abstract	This paper presents an adaptive level generation algorithm for the physics-based puzzle game Angry Birds. The proposed algorithm is based on a pre-existing level generator for this game, but where the difficulty of the generated levels can be adjusted based on the player’s performance. This allows for the creation of personalised levels tailored specifically to the player’s own abilities. The effectiveness of our proposed method is evaluated using several agents with differing strategies and AI techniques. By using these agents as models / representations of real human player’s characteristics, we can optimise level properties efficiently over a large number of generations. As a secondary investigation, we also demonstrate that by combining the performance of several agents together it is possible to generate levels that are especially challenging for certain players but not others.
Tasks
Published	2019-02-07
URL	http://arxiv.org/abs/1902.02518v1
PDF	http://arxiv.org/pdf/1902.02518v1.pdf
PWC	https://paperswithcode.com/paper/agent-based-adaptive-level-generation-for
Repo
Framework

Progressive Attention Memory Network for Movie Story Question Answering


Title	Progressive Attention Memory Network for Movie Story Question Answering
Authors	Junyeong Kim, Minuk Ma, Kyungsu Kim, Sungjin Kim, Chang D. Yoo
Abstract	This paper proposes the progressive attention memory network (PAMN) for movie story question answering (QA). Movie story QA is challenging compared to VQA in two aspects: (1) pinpointing the temporal parts relevant to answer the question is difficult as the movies are typically longer than an hour, (2) it has both video and subtitle where different questions require different modality to infer the answer. To overcome these challenges, PAMN involves three main features: (1) progressive attention mechanism that utilizes cues from both question and answer to progressively prune out irrelevant temporal parts in memory, (2) dynamic modality fusion that adaptively determines the contribution of each modality for answering the current question, and (3) belief correction answering scheme that successively corrects the prediction score on each candidate answer. Experiments on publicly available benchmark datasets, MovieQA and TVQA, demonstrate that each feature contributes to our movie story QA architecture, PAMN, and improves performance to achieve the state-of-the-art result. Qualitative analysis by visualizing the inference mechanism of PAMN is also provided.
Tasks	Question Answering, Video Story QA, Visual Question Answering
Published	2019-04-18
URL	http://arxiv.org/abs/1904.08607v1
PDF	http://arxiv.org/pdf/1904.08607v1.pdf
PWC	https://paperswithcode.com/paper/progressive-attention-memory-network-for
Repo
Framework

Learning low-precision neural networks without Straight-Through Estimator(STE)


Title	Learning low-precision neural networks without Straight-Through Estimator(STE)
Authors	Zhi-Gang Liu, Matthew Mattina
Abstract	The Straight-Through Estimator (STE) is widely used for back-propagating gradients through the quantization function, but the STE technique lacks a complete theoretical understanding. We propose an alternative methodology called alpha-blending (AB), which quantizes neural networks to low-precision using stochastic gradient descent (SGD). Our method (AB) avoids STE approximation by replacing the quantized weight in the loss function by an affine combination of the quantized weight w_q and the corresponding full-precision weight w with non-trainable scalar coefficient $\alpha$ and $1-\alpha$. During training, $\alpha$ is gradually increased from 0 to 1; the gradient updates to the weights are through the full-precision term, $(1-\alpha)w$, of the affine combination; the model is converted from full-precision to low-precision progressively. To evaluate the method, a 1-bit BinaryNet on CIFAR10 dataset and 8-bits, 4-bits MobileNet v1, ResNet_50 v1/2 on ImageNet dataset are trained using the alpha-blending approach, and the evaluation indicates that AB improves top-1 accuracy by 0.9%, 0.82% and 2.93% respectively compared to the results of STE based quantization.
Tasks	Quantization
Published	2019-03-04
URL	https://arxiv.org/abs/1903.01061v2
PDF	https://arxiv.org/pdf/1903.01061v2.pdf
PWC	https://paperswithcode.com/paper/learning-low-precision-neural-networks
Repo
Framework

FaceShapeGene: A Disentangled Shape Representation for Flexible Face Image Editing


Title	FaceShapeGene: A Disentangled Shape Representation for Flexible Face Image Editing
Authors	Sen-Zhe Xu, Hao-Zhi Huang, Shi-Min Hu, Wei Liu
Abstract	Existing methods for face image manipulation generally focus on editing the expression, changing some predefined attributes, or applying different filters. However, users lack the flexibility of controlling the shapes of different semantic facial parts in the generated face. In this paper, we propose an approach to compute a disentangled shape representation for a face image, namely the FaceShapeGene. The proposed FaceShapeGene encodes the shape information of each semantic facial part separately into a 1D latent vector. On the basis of the FaceShapeGene, a novel part-wise face image editing system is developed, which contains a shape-remix network and a conditional label-to-face transformer. The shape-remix network can freely recombine the part-wise latent vectors from different individuals, producing a remixed face shape in the form of a label map, which contains the facial characteristics of multiple subjects. The conditional label-to-face transformer, which is trained in an unsupervised cyclic manner, performs part-wise face editing while preserving the original identity of the subject. Experimental results on several tasks demonstrate that the proposed FaceShapeGene representation correctly disentangles the shape features of different semantic parts. %In addition, we test our system on several novel part-wise face editing tasks. Comparisons to existing methods demonstrate the superiority of the proposed method on accomplishing novel face editing tasks.
Tasks
Published	2019-05-06
URL	https://arxiv.org/abs/1905.01920v1
PDF	https://arxiv.org/pdf/1905.01920v1.pdf
PWC	https://paperswithcode.com/paper/faceshapegene-a-disentangled-shape
Repo
Framework

Unified estimation framework for unnormalized models with statistical efficiency


Title	Unified estimation framework for unnormalized models with statistical efficiency
Authors	Masatoshi Uehara, Takafumi Kanamori, Takashi Takenouchi, Takeru Matsuda
Abstract	Parameter estimation of unnormalized models is a challenging problem because normalizing constants are not calculated explicitly and maximum likelihood estimation is computationally infeasible. Although some consistent estimators have been proposed earlier, the problem of statistical efficiency does remain. In this study, we propose a unified, statistically efficient estimation framework for unnormalized models and several novel efficient estimators with reasonable computational time regardless of whether the sample space is discrete or continuous. The loss functions of the proposed estimators are derived by combining the following two methods: (1) density-ratio matching using Bregman divergence, and (2) plugging-in nonparametric estimators. We also analyze the properties of the proposed estimators when the unnormalized model is misspecified. Finally, the experimental results demonstrate the advantages of our method over existing approaches.
Tasks
Published	2019-01-23
URL	http://arxiv.org/abs/1901.07710v2
PDF	http://arxiv.org/pdf/1901.07710v2.pdf
PWC	https://paperswithcode.com/paper/unified-estimation-framework-for-unnormalized
Repo
Framework

Offline and Online Deep Learning for Image Recognition


Title	Offline and Online Deep Learning for Image Recognition
Authors	Nguyen Huu Phong, Bernardete Ribeiro
Abstract	Image recognition using Deep Learning has been evolved for decades though advances in the field through different settings is still a challenge. In this paper, we present our findings in searching for better image classifiers in offline and online environments. We resort to Convolutional Neural Network and its variations of fully connected Multi-layer Perceptron. Though still preliminary, these results are encouraging and may provide a better understanding about the field and directions toward future works.
Tasks
Published	2019-03-18
URL	http://arxiv.org/abs/1903.07479v1
PDF	http://arxiv.org/pdf/1903.07479v1.pdf
PWC	https://paperswithcode.com/paper/offline-and-online-deep-learning-for-image
Repo
Framework

General Matrix-Matrix Multiplication Using SIMD features of the PIII


Title	General Matrix-Matrix Multiplication Using SIMD features of the PIII
Authors	Douglas Aberdeen, Jonathan Baxter
Abstract	Generalised matrix-matrix multiplication forms the kernel of many mathematical algorithms. A faster matrix-matrix multiply immediately benefits these algorithms. In this paper we implement efficient matrix multiplication for large matrices using the floating point Intel Pentium SIMD (Single Instruction Multiple Data) architecture. A description of the issues and our solution is presented, paying attention to all levels of the memory hierarchy. Our results demonstrate an average performance of 2.09 times faster than the leading public domain matrix-matrix multiply routines.
Tasks
Published	2019-11-18
URL	https://arxiv.org/abs/1912.04379v1
PDF	https://arxiv.org/pdf/1912.04379v1.pdf
PWC	https://paperswithcode.com/paper/general-matrix-matrix-multiplication-using
Repo
Framework

Inversion of 1D frequency- and time-domain electromagnetic data with convolutional neural networks


Title	Inversion of 1D frequency- and time-domain electromagnetic data with convolutional neural networks
Authors	Vladimir Puzyrev, Andrei Swidinsky
Abstract	Inversion of electromagnetic data finds applications in many areas of geophysics. The inverse problem is commonly solved with either deterministic optimization methods (such as the nonlinear conjugate gradient or Gauss-Newton) which are prone to getting trapped in a local minimum, or probabilistic methods which are very computationally demanding. A recently emerging alternative is to employ deep neural networks for predicting subsurface model properties from measured data. This approach is entirely data-driven, does not employ traditional gradient-based techniques and provides a guess to the model instantaneously. In this study, we apply deep convolutional neural networks for 1D inversion of marine frequency-domain controlled-source electromagnetic (CSEM) data as well as onshore time-domain electromagnetic (TEM) data. Our approach yields accurate results both on synthetic and real data and provides them instantaneously. Using several networks and combining their outputs from various training epochs can also provide insights into the uncertainty distribution, which is found to be higher in the regions where resistivity anomalies are present. The proposed method opens up possibilities to estimate the subsurface resistivity distribution in exploration scenarios in real time.
Tasks
Published	2019-12-02
URL	https://arxiv.org/abs/1912.00612v1
PDF	https://arxiv.org/pdf/1912.00612v1.pdf
PWC	https://paperswithcode.com/paper/inversion-of-1d-frequency-and-time-domain
Repo
Framework

Reinforcement Learning When All Actions are Not Always Available


Title	Reinforcement Learning When All Actions are Not Always Available
Authors	Yash Chandak, Georgios Theocharous, Blossom Metevier, Philip S. Thomas
Abstract	The Markov decision process (MDP) formulation used to model many real-world sequential decision making problems does not efficiently capture the setting where the set of available decisions (actions) at each time step is stochastic. Recently, the stochastic action set Markov decision process (SAS-MDP) formulation has been proposed, which better captures the concept of a stochastic action set. In this paper we argue that existing RL algorithms for SAS-MDPs can suffer from potential divergence issues, and present new policy gradient algorithms for SAS-MDPs that incorporate variance reduction techniques unique to this setting, and provide conditions for their convergence. We conclude with experiments that demonstrate the practicality of our approaches on tasks inspired by real-life use cases wherein the action set is stochastic.
Tasks	Decision Making
Published	2019-06-05
URL	https://arxiv.org/abs/1906.01772v2
PDF	https://arxiv.org/pdf/1906.01772v2.pdf
PWC	https://paperswithcode.com/paper/reinforcement-learning-when-all-actions-are
Repo
Framework

Timeline-based Planning and Execution with Uncertainty: Theory, Modeling Methodologies and Practice


Title	Timeline-based Planning and Execution with Uncertainty: Theory, Modeling Methodologies and Practice
Authors	Alessandro Umbrico
Abstract	Automated Planning is one of the main research field of Artificial Intelligence since its beginnings. Research in Automated Planning aims at developing general reasoners (i.e., planners) capable of automatically solve complex problems. Broadly speaking, planners rely on a general model characterizing the possible states of the world and the actions that can be performed in order to change the status of the world. Given a model and an initial known state, the objective of a planner is to synthesize a set of actions needed to achieve a particular goal state. The classical approach to planning roughly corresponds to the description given above. The timeline-based approach is a particular planning paradigm capable of integrating causal and temporal reasoning within a unified solving process. This approach has been successfully applied in many real-world scenarios although a common interpretation of the related planning concepts is missing. Indeed, there are significant differences among the existing frameworks that apply this technique. Each framework relies on its own interpretation of timeline-based planning and therefore it is not easy to compare these systems. Thus, the objective of this work is to investigate the timeline-based approach to planning by addressing several aspects ranging from the semantics of the related planning concepts to the modeling and solving techniques. Specifically, the main contributions of this PhD work consist of: (i) the proposal of a formal characterization of the timeline-based approach capable of dealing with temporal uncertainty; (ii) the proposal of a hierarchical modeling and solving approach; (iii) the development of a general purpose framework for planning and execution with timelines; (iv) the validation{\dag}of this approach in real-world manufacturing scenarios.
Tasks
Published	2019-05-14
URL	https://arxiv.org/abs/1905.05713v1
PDF	https://arxiv.org/pdf/1905.05713v1.pdf
PWC	https://paperswithcode.com/paper/timeline-based-planning-and-execution-with
Repo
Framework

Generalization Studies of Neural Network Models for Cardiac Disease Detection Using Limited Channel ECG


Title	Generalization Studies of Neural Network Models for Cardiac Disease Detection Using Limited Channel ECG
Authors	Deepta Rajan, David Beymer, Girish Narayan
Abstract	Acceleration of machine learning research in healthcare is challenged by lack of large annotated and balanced datasets. Furthermore, dealing with measurement inaccuracies and exploiting unsupervised data are considered to be central to improving existing solutions. In particular, a primary objective in predictive modeling is to generalize well to both unseen variations within the observed classes, and unseen classes. In this work, we consider such a challenging problem in machine learning driven diagnosis: detecting a gamut of cardiovascular conditions (e.g. infarction, dysrhythmia etc.) from limited channel ECG measurements. Though deep neural networks have achieved unprecedented success in predictive modeling, they rely solely on discriminative models that can generalize poorly to unseen classes. We argue that unsupervised learning can be utilized to construct effective latent spaces that facilitate better generalization. This work extensively compares the generalization of our proposed approach against a state-of-the-art deep learning solution. Our results show significant improvements in F1-scores.
Tasks
Published	2019-01-05
URL	http://arxiv.org/abs/1901.03295v1
PDF	http://arxiv.org/pdf/1901.03295v1.pdf
PWC	https://paperswithcode.com/paper/generalization-studies-of-neural-network
Repo
Framework

In the Wild Human Pose Estimation Using Explicit 2D Features and Intermediate 3D Representations


Title	In the Wild Human Pose Estimation Using Explicit 2D Features and Intermediate 3D Representations
Authors	Ikhsanul Habibie, Weipeng Xu, Dushyant Mehta, Gerard Pons-Moll, Christian Theobalt
Abstract	Convolutional Neural Network based approaches for monocular 3D human pose estimation usually require a large amount of training images with 3D pose annotations. While it is feasible to provide 2D joint annotations for large corpora of in-the-wild images with humans, providing accurate 3D annotations to such in-the-wild corpora is hardly feasible in practice. Most existing 3D labelled data sets are either synthetically created or feature in-studio images. 3D pose estimation algorithms trained on such data often have limited ability to generalize to real world scene diversity. We therefore propose a new deep learning based method for monocular 3D human pose estimation that shows high accuracy and generalizes better to in-the-wild scenes. It has a network architecture that comprises a new disentangled hidden space encoding of explicit 2D and 3D features, and uses supervision by a new learned projection model from predicted 3D pose. Our algorithm can be jointly trained on image data with 3D labels and image data with only 2D labels. It achieves state-of-the-art accuracy on challenging in-the-wild data.
Tasks	3D Human Pose Estimation, 3D Pose Estimation, Pose Estimation
Published	2019-04-05
URL	http://arxiv.org/abs/1904.03289v1
PDF	http://arxiv.org/pdf/1904.03289v1.pdf
PWC	https://paperswithcode.com/paper/in-the-wild-human-pose-estimation-using
Repo
Framework

Using Deep Networks and Transfer Learning to Address Disinformation


Title	Using Deep Networks and Transfer Learning to Address Disinformation
Authors	Numa Dhamani, Paul Azunre, Jeffrey L. Gleason, Craig Corcoran, Garrett Honke, Steve Kramer, Jonathon Morgan
Abstract	We apply an ensemble pipeline composed of a character-level convolutional neural network (CNN) and a long short-term memory (LSTM) as a general tool for addressing a range of disinformation problems. We also demonstrate the ability to use this architecture to transfer knowledge from labeled data in one domain to related (supervised and unsupervised) tasks. Character-level neural networks and transfer learning are particularly valuable tools in the disinformation space because of the messy nature of social media, lack of labeled data, and the multi-channel tactics of influence campaigns. We demonstrate their effectiveness in several tasks relevant for detecting disinformation: spam emails, review bombing, political sentiment, and conversation clustering.
Tasks	Transfer Learning
Published	2019-05-24
URL	https://arxiv.org/abs/1905.10412v1
PDF	https://arxiv.org/pdf/1905.10412v1.pdf
PWC	https://paperswithcode.com/paper/using-deep-networks-and-transfer-learning-to
Repo
Framework