October 15, 2019

2737 words 13 mins read

Paper Group NANR 232

Paper Group NANR 232

X-ray Computed Tomography Through Scatter. Negotiable Reinforcement Learning for Pareto Optimal Sequential Decision-Making. Exploring Sentence Vectors Through Automatic Summarization. Adversarially Occluded Samples for Person Re-Identification. JDCFC: A Japanese Dialogue Corpus with Feature Changes. Convolutional Neural Networks for Soft Matching N …

X-ray Computed Tomography Through Scatter

Title X-ray Computed Tomography Through Scatter
Authors Adam Geva, Yoav Y. Schechner, Yonatan Chernyak, Rajiv Gupta
Abstract In current Xray CT scanners, tomographic reconstruction relies only on directly transmitted photons. The models used for reconstruction have regarded photons scattered by the body as noise or disturbance to be disposed of, either by acquisition hardware (an anti-scatter grid) or by the reconstruction software. This increases the radiation dose delivered to the patient. Treating these scattered photons as a source of information, we solve an inverse problem based on a 3D radiative transfer model that includes both elastic (Rayleigh) and inelastic (Compton) scattering. We further present ways to make the solution numerically efficient. The resulting tomographic reconstruction is more accurate than traditional CT, while enabling significant dose reduction and chemical decomposition. Demonstrations include both simulations based on a standard medical phantom and a real scattering tomography experiment.
Tasks
Published 2018-09-01
URL http://openaccess.thecvf.com/content_ECCV_2018/html/Adam_Geva_X-ray_Computational_Tomography_ECCV_2018_paper.html
PDF http://openaccess.thecvf.com/content_ECCV_2018/papers/Adam_Geva_X-ray_Computational_Tomography_ECCV_2018_paper.pdf
PWC https://paperswithcode.com/paper/x-ray-computed-tomography-through-scatter
Repo
Framework

Negotiable Reinforcement Learning for Pareto Optimal Sequential Decision-Making

Title Negotiable Reinforcement Learning for Pareto Optimal Sequential Decision-Making
Authors Nishant Desai, Andrew Critch, Stuart J. Russell
Abstract It is commonly believed that an agent making decisions on behalf of two or more principals who have different utility functions should adopt a Pareto optimal policy, i.e. a policy that cannot be improved upon for one principal without making sacrifices for another. Harsanyi’s theorem shows that when the principals have a common prior on the outcome distributions of all policies, a Pareto optimal policy for the agent is one that maximizes a fixed, weighted linear combination of the principals’ utilities. In this paper, we derive a more precise generalization for the sequential decision setting in the case of principals with different priors on the dynamics of the environment. We refer to this generalization as the Negotiable Reinforcement Learning (NRL) framework. In this more general case, the relative weight given to each principal’s utility should evolve over time according to how well the agent’s observations conform with that principal’s prior. To gain insight into the dynamics of this new framework, we implement a simple NRL agent and empirically examine its behavior in a simple environment.
Tasks Decision Making
Published 2018-12-01
URL http://papers.nips.cc/paper/7721-negotiable-reinforcement-learning-for-pareto-optimal-sequential-decision-making
PDF http://papers.nips.cc/paper/7721-negotiable-reinforcement-learning-for-pareto-optimal-sequential-decision-making.pdf
PWC https://paperswithcode.com/paper/negotiable-reinforcement-learning-for-pareto
Repo
Framework

Exploring Sentence Vectors Through Automatic Summarization

Title Exploring Sentence Vectors Through Automatic Summarization
Authors Adly Templeton, Jugal Kalita
Abstract Vector semantics, especially sentence vectors, have recently been used successfully in many areas of natural language processing. However, relatively little work has explored the internal structure and properties of spaces of sentence vectors. In this paper, we will explore the properties of sentence vectors by studying a particular real-world application: Automatic Summarization. In particular, we show that cosine similarity between sentence vectors and document vectors is strongly correlated with sentence importance and that vector semantics can identify and correct gaps between the sentences chosen so far and the document. In addition, we identify specific dimensions which are linked to effective summaries. To our knowledge, this is the first time specific dimensions of sentence embeddings have been connected to sentence properties. We also compare the features of different methods of sentence embeddings. Many of these insights have applications in uses of sentence embeddings far beyond summarization.
Tasks Sentence Embeddings
Published 2018-01-01
URL https://openreview.net/forum?id=S1347ot3b
PDF https://openreview.net/pdf?id=S1347ot3b
PWC https://paperswithcode.com/paper/exploring-sentence-vectors-through-automatic
Repo
Framework

Adversarially Occluded Samples for Person Re-Identification

Title Adversarially Occluded Samples for Person Re-Identification
Authors Houjing Huang, Dangwei Li, Zhang Zhang, Xiaotang Chen, Kaiqi Huang
Abstract Person re-identification (ReID) is the task of retrieving particular persons across different cameras. Despite its great progress in recent years, it is still confronted with challenges like pose variation, occlusion, and similar appearance among different persons. The large gap between training and testing performance with existing models implies the insufficiency of generalization. Considering this fact, we propose to augment the variation of training data by introducing Adversarially Occluded Samples. These special samples are both a) meaningful in that they resemble real-scene occlusions, and b) effective in that they are tough for the original model and thus provide the momentum to jump out of local optimum. We mine these samples based on a trained ReID model and with the help of network visualization techniques. Extensive experiments show that the proposed samples help the model discover new discriminative clues on the body and generalize much better at test time. Our strategy makes significant improvement over strong baselines on three large-scale ReID datasets, Market1501, CUHK03 and DukeMTMC-reID.
Tasks Person Re-Identification
Published 2018-06-01
URL http://openaccess.thecvf.com/content_cvpr_2018/html/Huang_Adversarially_Occluded_Samples_CVPR_2018_paper.html
PDF http://openaccess.thecvf.com/content_cvpr_2018/papers/Huang_Adversarially_Occluded_Samples_CVPR_2018_paper.pdf
PWC https://paperswithcode.com/paper/adversarially-occluded-samples-for-person-re
Repo
Framework

JDCFC: A Japanese Dialogue Corpus with Feature Changes

Title JDCFC: A Japanese Dialogue Corpus with Feature Changes
Authors Tetsuaki Nakamura, Daisuke Kawahara
Abstract
Tasks Dialogue Understanding
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1461/
PDF https://www.aclweb.org/anthology/L18-1461
PWC https://paperswithcode.com/paper/jdcfc-a-japanese-dialogue-corpus-with-feature
Repo
Framework
Title Convolutional Neural Networks for Soft Matching N-Grams in Ad-hoc Search
Authors Zhuyun Dai, Chenyan Xiong, Jamie Callan, Zhiyuan Liu
Abstract This paper presents Conv-KNRM, a Convolutional Kernel-based Neural Ranking Model that models n-gram soft matches for ad-hoc search. Instead of exact matching query and document n-grams, Conv-KNRM uses Convolutional Neural Networks to represent ngrams of various lengths and soft matches them in a uni€ed embedding space. The n-gram soft matches are then utilized by the kernel pooling and learning-to-rank layers to generate the final ranking score. Conv-KNRM can be learned end-to-end and fully optimized from user feedback. The learned model’s generalizability is investigated by testing how well it performs in a related domain with small amounts of training data. Experiments on English search logs, Chinese search logs, and TREC Web track tasks demonstrated consistent advantages of Conv-KNRM over prior neural IR methods and feature-based methods.
Tasks Learning-To-Rank
Published 2018-02-02
URL http://www.cs.cmu.edu/~./callan/Papers/wsdm18-zhuyun-dai.pdf
PDF http://www.cs.cmu.edu/~./callan/Papers/wsdm18-zhuyun-dai.pdf
PWC https://paperswithcode.com/paper/convolutional-neural-networks-for-soft
Repo
Framework

Discriminating between Similar Languages on Imbalanced Conversational Texts

Title Discriminating between Similar Languages on Imbalanced Conversational Texts
Authors Junqing He, Xian Huang, Xuemin Zhao, Yan Zhang, Yonghong Yan
Abstract
Tasks Language Identification
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1497/
PDF https://www.aclweb.org/anthology/L18-1497
PWC https://paperswithcode.com/paper/discriminating-between-similar-languages-on
Repo
Framework

Out-of-the-box Universal Romanization Tool uroman

Title Out-of-the-box Universal Romanization Tool uroman
Authors Ulf Hermjakob, Jonathan May, Kevin Knight
Abstract We present uroman, a tool for converting text in myriads of languages and scripts such as Chinese, Arabic and Cyrillic into a common Latin-script representation. The tool relies on Unicode data and other tables, and handles nearly all character sets, including some that are quite obscure such as Tibetan and Tifinagh. uroman converts digital numbers in various scripts to Western Arabic numerals. Romanization enables the application of string-similarity metrics to texts from different scripts without the need and complexity of an intermediate phonetic representation. The tool is freely and publicly available as a Perl script suitable for inclusion in data processing pipelines and as an interactive demo web page.
Tasks Machine Translation
Published 2018-07-01
URL https://www.aclweb.org/anthology/P18-4003/
PDF https://www.aclweb.org/anthology/P18-4003
PWC https://paperswithcode.com/paper/out-of-the-box-universal-romanization-tool
Repo
Framework

Enhanced network anomaly detection based on deep neural networks

Title Enhanced network anomaly detection based on deep neural networks
Authors Naseer, Sheraz; Saleem, Yasir; Khalid, Shehzad; Bashir, Muhammad Khawar; Han, Jihun; Iqbal, Muhammad Munwar; Han, Kijun
Abstract Due to the monumental growth of Internet applications in the last decade, the need for security of information network has increased manifolds. As a primary defense of network infrastructure, an intrusion detection system is expected to adapt to dynamically changing threat landscape. Many supervised and unsupervised techniques have been devised by researchers from the discipline of machine learning and data mining to achieve reliable detection of anomalies. Deep learning is an area of machine learning which applies neuron-like structure for learning tasks. Deep learning has profoundly changed the way we approach learning tasks by delivering monumental progress in different disciplines like speech processing, computer vision, and natural language processing to name a few. It is only relevant that this new technology must be investigated for information security applications. The aim of this paper is to investigate the suitability of deep learning approaches for anomaly-based intrusion detection system. For this research, we developed anomaly detection models based on different deep neural network structures, including convolutional neural networks, autoencoders, and recurrent neural networks. These deep models were trained on NSLKDD training data set and evaluated on both test data sets provided by NSLKDD, namely NSLKDDTest+ and NSLKDDTest21. All experiments in this paper are performed by authors on a GPU-based test bed. Conventional machine learning-based intrusion detection models were implemented using well-known classification techniques, including extreme learning machine, nearest neighbor, decision-tree, random-forest, support vector machine, naive-bays, and quadratic discriminant analysis. Both deep and conventional machine learning models were evaluated using well-known classification metrics, including receiver operating characteristics, area under curve, precision-recall curve, mean average precision and accuracy of classification. Experimental results of deep IDS models showed promising results for real-world application in anomaly detection systems.
Tasks Anomaly Detection, Intrusion Detection
Published 2018-08-17
URL https://ieeexplore.ieee.org/abstract/document/8438865
PDF https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8438865
PWC https://paperswithcode.com/paper/enhanced-network-anomaly-detection-based-on
Repo
Framework

A Bandit Approach to Sequential Experimental Design with False Discovery Control

Title A Bandit Approach to Sequential Experimental Design with False Discovery Control
Authors Kevin G. Jamieson, Lalit Jain
Abstract We propose a new adaptive sampling approach to multiple testing which aims to maximize statistical power while ensuring anytime false discovery control. We consider $n$ distributions whose means are partitioned by whether they are below or equal to a baseline (nulls), versus above the baseline (true positives). In addition, each distribution can be sequentially and repeatedly sampled. Using techniques from multi-armed bandits, we provide an algorithm that takes as few samples as possible to exceed a target true positive proportion (i.e. proportion of true positives discovered) while giving anytime control of the false discovery proportion (nulls predicted as true positives). Our sample complexity results match known information theoretic lower bounds and through simulations we show a substantial performance improvement over uniform sampling and an adaptive elimination style algorithm. Given the simplicity of the approach, and its sample efficiency, the method has promise for wide adoption in the biological sciences, clinical testing for drug discovery, and maximization of click through in A/B/n testing problems.
Tasks Drug Discovery, Multi-Armed Bandits
Published 2018-12-01
URL http://papers.nips.cc/paper/7624-a-bandit-approach-to-sequential-experimental-design-with-false-discovery-control
PDF http://papers.nips.cc/paper/7624-a-bandit-approach-to-sequential-experimental-design-with-false-discovery-control.pdf
PWC https://paperswithcode.com/paper/a-bandit-approach-to-sequential-experimental
Repo
Framework

A Certifiably Globally Optimal Solution to the Non-Minimal Relative Pose Problem

Title A Certifiably Globally Optimal Solution to the Non-Minimal Relative Pose Problem
Authors Jesus Briales, Laurent Kneip, Javier Gonzalez-Jimenez
Abstract Finding the relative pose between two calibrated views ranks among the most fundamental geometric vision problems. It therefore appears as somewhat a surprise that a globally optimal solver that minimizes a properly defined energy over non-minimal correspondence sets and in the original space of relative transformations has yet to be discovered. This, notably, is the contribution of the present paper. We formulate the problem as a Quadratically Constrained Quadratic Program (QCQP), which can be converted into a Semidefinite Program (SDP) using Shor’s convex relaxation. While a theoretical proof for the tightness of this relaxation remains open, we prove through exhaustive validation on both simulated and real experiments that our approach always finds and certifies (a-posteriori) the global optimum of the cost function.
Tasks
Published 2018-06-01
URL http://openaccess.thecvf.com/content_cvpr_2018/html/Briales_A_Certifiably_Globally_CVPR_2018_paper.html
PDF http://openaccess.thecvf.com/content_cvpr_2018/papers/Briales_A_Certifiably_Globally_CVPR_2018_paper.pdf
PWC https://paperswithcode.com/paper/a-certifiably-globally-optimal-solution-to
Repo
Framework

QuickEdit: Editing Text & Translations by Crossing Words Out

Title QuickEdit: Editing Text & Translations by Crossing Words Out
Authors David Grangier, Michael Auli
Abstract We propose a framework for computer-assisted text editing. It applies to translation post-editing and to paraphrasing. Our proposal relies on very simple interactions: a human editor modifies a sentence by marking tokens they would like the system to change. Our model then generates a new sentence which reformulates the initial sentence by avoiding marked words. The approach builds upon neural sequence-to-sequence modeling and introduces a neural network which takes as input a sentence along with change markers. Our model is trained on translation bitext by simulating post-edits. We demonstrate the advantage of our approach for translation post-editing through simulated post-edits. We also evaluate our model for paraphrasing through a user study.
Tasks Machine Translation
Published 2018-06-01
URL https://www.aclweb.org/anthology/N18-1025/
PDF https://www.aclweb.org/anthology/N18-1025
PWC https://paperswithcode.com/paper/quickedit-editing-text-translations-by-1
Repo
Framework

Generative Adversarial Learning Towards Fast Weakly Supervised Detection

Title Generative Adversarial Learning Towards Fast Weakly Supervised Detection
Authors Yunhan Shen, Rongrong Ji, Shengchuan Zhang, Wangmeng Zuo, Yan Wang
Abstract Weakly supervised object detection has attracted extensive research efforts in recent years. Without the need of annotating bounding boxes, the existing methods usually follow a two/multi-stage pipeline with an online compulsive stage to extract object proposals, which is an order of magnitude slower than fast fully supervised object detectors such as SSD [31] and YOLO [34]. In this paper, we speedup online weakly supervised object detectors by orders of magnitude by proposing a novel generative adversarial learning paradigm. In the proposed paradigm, the generator is a one-stage object detector to generate bounding boxes from images. To guide the learning of object-level generator, a surrogator is introduced to mine high-quality bounding boxes for training. We further adapt a structural similarity loss in combination with an adversarial loss into the training objective, which solves the challenge that the bounding boxes produced by the surrogator may not well capture their ground truth. Our one-stage detector outperforms all existing schemes in terms of detection accuracy, running at 118 frames per second, which is up to 438x faster than the state-of-the-art weakly supervised detectors [8, 30, 15, 27, 45]. The code will be available publicly soon.
Tasks Object Detection, Weakly Supervised Object Detection
Published 2018-06-01
URL http://openaccess.thecvf.com/content_cvpr_2018/html/Shen_Generative_Adversarial_Learning_CVPR_2018_paper.html
PDF http://openaccess.thecvf.com/content_cvpr_2018/papers/Shen_Generative_Adversarial_Learning_CVPR_2018_paper.pdf
PWC https://paperswithcode.com/paper/generative-adversarial-learning-towards-fast
Repo
Framework

Representing dynamically: An active process for describing sequential data

Title Representing dynamically: An active process for describing sequential data
Authors Juan Sebastian Olier, Emilia Barakova, Matthias Rauterberg, Carlo Regazzoni
Abstract We propose an unsupervised method for building dynamic representations of sequential data, particularly of observed interactions. The method simultaneously acquires representations of input data and its dynamics. It is based on a hierarchical generative model composed of two levels. In the first level, a model learns representations to generate observed data. In the second level, representational states encode the dynamics of the lower one. The model is designed as a Bayesian network with switching variables represented in the higher level, and which generates transition models. The method actively explores the latent space guided by its knowledge and the uncertainty about it. That is achieved by updating the latent variables from prediction error signals backpropagated to the latent space. So, no encoder or inference models are used since the generators also serve as their inverse transformations. The method is evaluated in two scenarios, with static images and with videos. The results show that the adaptation over time leads to better performance than with similar architectures without temporal dependencies, e.g., variational autoencoders. With videos, it is shown that the system extracts the dynamics of the data in states that highly correlate with the ground truth of the actions observed.
Tasks
Published 2018-01-01
URL https://openreview.net/forum?id=Sk7cHb-C-
PDF https://openreview.net/pdf?id=Sk7cHb-C-
PWC https://paperswithcode.com/paper/representing-dynamically-an-active-process
Repo
Framework

Soft Value Iteration Networks for Planetary Rover Path Planning

Title Soft Value Iteration Networks for Planetary Rover Path Planning
Authors Max Pflueger, Ali Agha, Gaurav S. Sukhatme
Abstract Value iteration networks are an approximation of the value iteration (VI) algorithm implemented with convolutional neural networks to make VI fully differentiable. In this work, we study these networks in the context of robot motion planning, with a focus on applications to planetary rovers. The key challenging task in learning-based motion planning is to learn a transformation from terrain observations to a suitable navigation reward function. In order to deal with complex terrain observations and policy learning, we propose a value iteration recurrence, referred to as the soft value iteration network (SVIN). SVIN is designed to produce more effective training gradients through the value iteration network. It relies on a soft policy model, where the policy is represented with a probability distribution over all possible actions, rather than a deterministic policy that returns only the best action. We demonstrate the effectiveness of the proposed method in robot motion planning scenarios. In particular, we study the application of SVIN to very challenging problems in planetary rover navigation and present early training results on data gathered by the Curiosity rover that is currently operating on Mars.
Tasks Motion Planning
Published 2018-01-01
URL https://openreview.net/forum?id=Sktm4zWRb
PDF https://openreview.net/pdf?id=Sktm4zWRb
PWC https://paperswithcode.com/paper/soft-value-iteration-networks-for-planetary
Repo
Framework
comments powered by Disqus