October 19, 2019

2910 words 14 mins read

Paper Group ANR 289

Computational Approaches for Stochastic Shortest Path on Succinct MDPs. Attribute-aware Face Aging with Wavelet-based Generative Adversarial Networks. Mapping Navigation Instructions to Continuous Control Actions with Position-Visitation Prediction. Orders-of-magnitude speedup in atmospheric chemistry modeling through neural network-based emulation …

Computational Approaches for Stochastic Shortest Path on Succinct MDPs


Title	Computational Approaches for Stochastic Shortest Path on Succinct MDPs
Authors	Krishnendu Chatterjee, Hongfei Fu, Amir Kafshdar Goharshady, Nastaran Okati
Abstract	We consider the stochastic shortest path (SSP) problem for succinct Markov decision processes (MDPs), where the MDP consists of a set of variables, and a set of nondeterministic rules that update the variables. First, we show that several examples from the AI literature can be modeled as succinct MDPs. Then we present computational approaches for upper and lower bounds for the SSP problem: (a)~for computing upper bounds, our method is polynomial-time in the implicit description of the MDP; (b)~for lower bounds, we present a polynomial-time (in the size of the implicit description) reduction to quadratic programming. Our approach is applicable even to infinite-state MDPs. Finally, we present experimental results to demonstrate the effectiveness of our approach on several classical examples from the AI literature.
Tasks
Published	2018-04-24
URL	http://arxiv.org/abs/1804.08984v3
PDF	http://arxiv.org/pdf/1804.08984v3.pdf
PWC	https://paperswithcode.com/paper/computational-approaches-for-stochastic
Repo
Framework

Attribute-aware Face Aging with Wavelet-based Generative Adversarial Networks


Title	Attribute-aware Face Aging with Wavelet-based Generative Adversarial Networks
Authors	Yunfan Liu, Qi Li, Zhenan Sun
Abstract	Since it is difficult to collect face images of the same subject over a long range of age span, most existing face aging methods resort to unpaired datasets to learn age mappings. However, the matching ambiguity between young and aged face images inherent to unpaired training data may lead to unnatural changes of facial attributes during the aging process, which could not be solved by only enforcing identity consistency like most existing studies do. In this paper, we propose a attribute-aware face aging model with wavelet-based Generative Adversarial Networks (GANs) to address the above issues. To be specific, we embed facial attribute vectors into both generator and discriminator of the model to encourage each synthesized elderly face image to be faithful to the attribute of its corresponding input. In addition, a wavelet packet transform (WPT) module is incorporated to improve the visual fidelity of generated images by capturing age-related texture details at multiple scales in the frequency space. Qualitative results demonstrate the ability of our model to synthesize visually plausible face images, and extensive quantitative evaluation results show that the proposed method achieves state-of-the-art performance on existing datasets.
Tasks
Published	2018-09-18
URL	http://arxiv.org/abs/1809.06647v3
PDF	http://arxiv.org/pdf/1809.06647v3.pdf
PWC	https://paperswithcode.com/paper/attribute-aware-face-aging-with-wavelet-based
Repo
Framework


Title	Mapping Navigation Instructions to Continuous Control Actions with Position-Visitation Prediction
Authors	Valts Blukis, Dipendra Misra, Ross A. Knepper, Yoav Artzi
Abstract	We propose an approach for mapping natural language instructions and raw observations to continuous control of a quadcopter drone. Our model predicts interpretable position-visitation distributions indicating where the agent should go during execution and where it should stop, and uses the predicted distributions to select the actions to execute. This two-step model decomposition allows for simple and efficient training using a combination of supervised learning and imitation learning. We evaluate our approach with a realistic drone simulator, and demonstrate absolute task-completion accuracy improvements of 16.85% over two state-of-the-art instruction-following methods.
Tasks	Continuous Control, Imitation Learning
Published	2018-11-10
URL	http://arxiv.org/abs/1811.04179v2
PDF	http://arxiv.org/pdf/1811.04179v2.pdf
PWC	https://paperswithcode.com/paper/mapping-navigation-instructions-to-continuous
Repo
Framework

Orders-of-magnitude speedup in atmospheric chemistry modeling through neural network-based emulation


Title	Orders-of-magnitude speedup in atmospheric chemistry modeling through neural network-based emulation
Authors	Makoto M. Kelp, Christopher W. Tessum, Julian D. Marshall
Abstract	Chemical transport models (CTMs), which simulate air pollution transport, transformation, and removal, are computationally expensive, largely because of the computational intensity of the chemical mechanisms: systems of coupled differential equations representing atmospheric chemistry. Here we investigate the potential for machine learning to reproduce the behavior of a chemical mechanism, yet with reduced computational expense. We create a 17-layer residual multi-target regression neural network to emulate the Carbon Bond Mechanism Z (CBM-Z) gas-phase chemical mechanism. We train the network to match CBM-Z predictions of changes in concentrations of 77 chemical species after one hour, given a range of chemical and meteorological input conditions, which it is able to do with root-mean-square error (RMSE) of less than 1.97 ppb (median RMSE = 0.02 ppb), while achieving a 250x computational speedup. An additional 17x speedup (total 4250x speedup) is achieved by running the neural network on a graphics-processing unit (GPU). The neural network is able to reproduce the emergent behavior of the chemical system over diurnal cycles using Euler integration, but additional work is needed to constrain the propagation of errors as simulation time progresses.
Tasks
Published	2018-08-11
URL	http://arxiv.org/abs/1808.03874v1
PDF	http://arxiv.org/pdf/1808.03874v1.pdf
PWC	https://paperswithcode.com/paper/orders-of-magnitude-speedup-in-atmospheric
Repo
Framework

Interpretable Fully Convolutional Classification of Intrapapillary Capillary Loops for Real-Time Detection of Early Squamous Neoplasia


Title	Interpretable Fully Convolutional Classification of Intrapapillary Capillary Loops for Real-Time Detection of Early Squamous Neoplasia
Authors	Luis C. Garcia-Peraza-Herrera, Martin Everson, Wenqi Li, Inmanol Luengo, Lorenz Berger, Omer Ahmad, Laurence Lovat, Hsiu-Po Wang, Wen-Lun Wang, Rehan Haidry, Danail Stoyanov, Tom Vercauteren, Sebastien Ourselin
Abstract	In this work, we have concentrated our efforts on the interpretability of classification results coming from a fully convolutional neural network. Motivated by the classification of oesophageal tissue for real-time detection of early squamous neoplasia, the most frequent kind of oesophageal cancer in Asia, we present a new dataset and a novel deep learning method that by means of deep supervision and a newly introduced concept, the embedded Class Activation Map (eCAM), focuses on the interpretability of results as a design constraint of a convolutional network. We present a new approach to visualise attention that aims to give some insights on those areas of the oesophageal tissue that lead a network to conclude that the images belong to a particular class and compare them with those visual features employed by clinicians to produce a clinical diagnosis. In comparison to a baseline method which does not feature deep supervision but provides attention by grafting Class Activation Maps, we improve the F1-score from 87.3% to 92.7% and provide more detailed attention maps.
Tasks
Published	2018-05-02
URL	http://arxiv.org/abs/1805.00632v1
PDF	http://arxiv.org/pdf/1805.00632v1.pdf
PWC	https://paperswithcode.com/paper/interpretable-fully-convolutional
Repo
Framework

Efficient Linear Bandits through Matrix Sketching


Title	Efficient Linear Bandits through Matrix Sketching
Authors	Ilja Kuzborskij, Leonardo Cella, Nicolò Cesa-Bianchi
Abstract	We prove that two popular linear contextual bandit algorithms, OFUL and Thompson Sampling, can be made efficient using Frequent Directions, a deterministic online sketching technique. More precisely, we show that a sketch of size $m$ allows a $\mathcal{O}(md)$ update time for both algorithms, as opposed to $\Omega(d^2)$ required by their non-sketched versions in general (where $d$ is the dimension of context vectors). This computational speedup is accompanied by regret bounds of order $(1+\varepsilon_m)^{3/2}d\sqrt{T}$ for OFUL and of order $\big((1+\varepsilon_m)d\big)^{3/2}\sqrt{T}$ for Thompson Sampling, where $\varepsilon_m$ is bounded by the sum of the tail eigenvalues not covered by the sketch. In particular, when the selected contexts span a subspace of dimension at most $m$, our algorithms have a regret bound matching that of their slower, non-sketched counterparts. Experiments on real-world datasets corroborate our theoretical results.
Tasks
Published	2018-09-28
URL	http://arxiv.org/abs/1809.11033v2
PDF	http://arxiv.org/pdf/1809.11033v2.pdf
PWC	https://paperswithcode.com/paper/efficient-linear-bandits-through-matrix
Repo
Framework

EFSIS: Ensemble Feature Selection Integrating Stability


Title	EFSIS: Ensemble Feature Selection Integrating Stability
Authors	Xiaokang Zhang, Inge Jonassen
Abstract	Ensemble learning that can be used to combine the predictions from multiple learners has been widely applied in pattern recognition, and has been reported to be more robust and accurate than the individual learners. This ensemble logic has recently also been more applied in feature selection. There are basically two strategies for ensemble feature selection, namely data perturbation and function perturbation. Data perturbation performs feature selection on data subsets sampled from the original dataset and then selects the features consistently ranked highly across those data subsets. This has been found to improve both the stability of the selector and the prediction accuracy for a classifier. Function perturbation frees the user from having to decide on the most appropriate selector for any given situation and works by aggregating multiple selectors. This has been found to maintain or improve classification performance. Here we propose a framework, EFSIS, combining these two strategies. Empirical results indicate that EFSIS gives both high prediction accuracy and stability.
Tasks	Feature Selection
Published	2018-11-19
URL	http://arxiv.org/abs/1811.07939v1
PDF	http://arxiv.org/pdf/1811.07939v1.pdf
PWC	https://paperswithcode.com/paper/efsis-ensemble-feature-selection-integrating
Repo
Framework

Sensors, SLAM and Long-term Autonomy: A Review


Title	Sensors, SLAM and Long-term Autonomy: A Review
Authors	Mubariz Zaffar, Shoaib Ehsan, Rustam Stolkin, Klaus McDonald Maier
Abstract	Simultaneous Localization and Mapping, commonly known as SLAM, has been an active research area in the field of Robotics over the past three decades. For solving the SLAM problem, every robot is equipped with either a single sensor or a combination of similar/different sensors. This paper attempts to review, discuss, evaluate and compare these sensors. Keeping an eye on future, this paper also assesses the characteristics of these sensors against factors critical to the long-term autonomy challenge.
Tasks	Simultaneous Localization and Mapping
Published	2018-07-04
URL	http://arxiv.org/abs/1807.01605v1
PDF	http://arxiv.org/pdf/1807.01605v1.pdf
PWC	https://paperswithcode.com/paper/sensors-slam-and-long-term-autonomy-a-review
Repo
Framework

On the Strength of Character Language Models for Multilingual Named Entity Recognition


Title	On the Strength of Character Language Models for Multilingual Named Entity Recognition
Authors	Xiaodong Yu, Stephen Mayhew, Mark Sammons, Dan Roth
Abstract	Character-level patterns have been widely used as features in English Named Entity Recognition (NER) systems. However, to date there has been no direct investigation of the inherent differences between name and non-name tokens in text, nor whether this property holds across multiple languages. This paper analyzes the capabilities of corpus-agnostic Character-level Language Models (CLMs) in the binary task of distinguishing name tokens from non-name tokens. We demonstrate that CLMs provide a simple and powerful model for capturing these differences, identifying named entity tokens in a diverse set of languages at close to the performance of full NER systems. Moreover, by adding very simple CLM-based features we can significantly improve the performance of an off-the-shelf NER system for multiple languages.
Tasks	Named Entity Recognition
Published	2018-09-13
URL	http://arxiv.org/abs/1809.05157v2
PDF	http://arxiv.org/pdf/1809.05157v2.pdf
PWC	https://paperswithcode.com/paper/on-the-strength-of-character-language-models
Repo
Framework

A Dataset for Lane Instance Segmentation in Urban Environments


Title	A Dataset for Lane Instance Segmentation in Urban Environments
Authors	Brook Roberts, Sebastian Kaltwang, Sina Samangooei, Mark Pender-Bare, Konstantinos Tertikas, John Redford
Abstract	Autonomous vehicles require knowledge of the surrounding road layout, which can be predicted by state-of-the-art CNNs. This work addresses the current lack of data for determining lane instances, which are needed for various driving manoeuvres. The main issue is the time-consuming manual labelling process, typically applied per image. We notice that driving the car is itself a form of annotation. Therefore, we propose a semi-automated method that allows for efficient labelling of image sequences by utilising an estimated road plane in 3D based on where the car has driven and projecting labels from this plane into all images of the sequence. The average labelling time per image is reduced to 5 seconds and only an inexpensive dash-cam is required for data capture. We are releasing a dataset of 24,000 images and additionally show experimental semantic segmentation and instance segmentation results.
Tasks	Autonomous Vehicles, Instance Segmentation, Semantic Segmentation
Published	2018-07-03
URL	http://arxiv.org/abs/1807.01347v2
PDF	http://arxiv.org/pdf/1807.01347v2.pdf
PWC	https://paperswithcode.com/paper/a-dataset-for-lane-instance-segmentation-in
Repo
Framework

Rendition: Reclaiming what a black box takes away


Title	Rendition: Reclaiming what a black box takes away
Authors	Peyman Milanfar
Abstract	The premise of our work is deceptively familiar: A black box $f(\cdot)$ has altered an image $\mathbf{x} \rightarrow f(\mathbf{x})$. Recover the image $\mathbf{x}$. This black box might be any number of simple or complicated things: a linear or non-linear filter, some app on your phone, etc. The latter is a good canonical example for the problem we address: Given only “the app” and an image produced by the app, find the image that was fed to the app. You can run the given image (or any other image) through the app as many times as you like, but you can not look inside the (code for the) app to see how it works. At first blush, the problem sounds a lot like a standard inverse problem, but it is not in the following sense: While we have access to the black box $f(\cdot)$ and can run any image through it and observe the output, we do not know how the block box alters the image. Therefore we have no explicit form or model of $f(\cdot)$. Nor are we necessarily interested in the internal workings of the black box. We are simply happy to reverse its effect on a particular image, to whatever extent possible. This is what we call the “rendition” (rather than restoration) problem, as it does not fit the mold of an inverse problem (blind or otherwise). We describe general conditions under which rendition is possible, and provide a remarkably simple algorithm that works for both contractive and expansive black box operators. The principal and novel take-away message from our work is this surprising fact: One simple algorithm can reliably undo a wide class of (not too violent) image distortions. A higher quality pdf of this paper is available at http://www.milanfar.org
Tasks
Published	2018-04-23
URL	http://arxiv.org/abs/1804.08651v1
PDF	http://arxiv.org/pdf/1804.08651v1.pdf
PWC	https://paperswithcode.com/paper/rendition-reclaiming-what-a-black-box-takes
Repo
Framework

A Roadmap Towards Resilient Internet of Things for Cyber-Physical Systems


Title	A Roadmap Towards Resilient Internet of Things for Cyber-Physical Systems
Authors	Denise Ratasich, Faiq Khalid, Florian Geissler, Radu Grosu, Muhammad Shafique, Ezio Bartocci
Abstract	The Internet of Things (IoT) is a ubiquitous system connecting many different devices - the things - which can be accessed from the distance. The cyber-physical systems (CPS) monitor and control the things from the distance. As a result, the concepts of dependability and security get deeply intertwined. The increasing level of dynamicity, heterogeneity, and complexity adds to the system’s vulnerability, and challenges its ability to react to faults. This paper summarizes state-of-the-art of existing work on anomaly detection, fault-tolerance and self-healing, and adds a number of other methods applicable to achieve resilience in an IoT. We particularly focus on non-intrusive methods ensuring data integrity in the network. Furthermore, this paper presents the main challenges in building a resilient IoT for CPS which is crucial in the era of smart CPS with enhanced connectivity (an excellent example of such a system is connected autonomous vehicles). It further summarizes our solutions, work-in-progress and future work to this topic to enable “Trustworthy IoT for CPS”. Finally, this framework is illustrated on a selected use case: A smart sensor infrastructure in the transport domain.
Tasks	Anomaly Detection, Autonomous Vehicles
Published	2018-10-16
URL	http://arxiv.org/abs/1810.06870v2
PDF	http://arxiv.org/pdf/1810.06870v2.pdf
PWC	https://paperswithcode.com/paper/a-roadmap-towards-resilient-internet-of
Repo
Framework

Recommender system for learning SQL using hints


Title	Recommender system for learning SQL using hints
Authors	Dejan Lavbič, Tadej Matek, Aljaž Zrnec
Abstract	Today’s software industry requires individuals who are proficient in as many programming languages as possible. Structured query language (SQL), as an adopted standard, is no exception, as it is the most widely used query language to retrieve and manipulate data. However, the process of learning SQL turns out to be challenging. The need for a computer-aided solution to help users learn SQL and improve their proficiency is vital. In this study, we present a new approach to help users conceptualize basic building blocks of the language faster and more efficiently. The adaptive design of the proposed approach aids users in learning SQL by supporting their own path to the solution and employing successful previous attempts, while not enforcing the ideal solution provided by the instructor. Furthermore, we perform an empirical evaluation with 93 participants and demonstrate that the employment of hints is successful, being especially beneficial for users with lower prior knowledge.
Tasks	Recommendation Systems
Published	2018-07-07
URL	http://arxiv.org/abs/1807.02637v1
PDF	http://arxiv.org/pdf/1807.02637v1.pdf
PWC	https://paperswithcode.com/paper/recommender-system-for-learning-sql-using
Repo
Framework

Three Tools for Practical Differential Privacy


Title	Three Tools for Practical Differential Privacy
Authors	Koen Lennart van der Veen, Ruben Seggers, Peter Bloem, Giorgio Patrini
Abstract	Differentially private learning on real-world data poses challenges for standard machine learning practice: privacy guarantees are difficult to interpret, hyperparameter tuning on private data reduces the privacy budget, and ad-hoc privacy attacks are often required to test model privacy. We introduce three tools to make differentially private machine learning more practical: (1) simple sanity checks which can be carried out in a centralized manner before training, (2) an adaptive clipping bound to reduce the effective number of tuneable privacy parameters, and (3) we show that large-batch training improves model performance.
Tasks
Published	2018-12-07
URL	http://arxiv.org/abs/1812.02890v1
PDF	http://arxiv.org/pdf/1812.02890v1.pdf
PWC	https://paperswithcode.com/paper/three-tools-for-practical-differential
Repo
Framework

FigureNet: A Deep Learning model for Question-Answering on Scientific Plots


Title	FigureNet: A Deep Learning model for Question-Answering on Scientific Plots
Authors	Revanth Reddy, Rahul Ramesh, Ameet Deshpande, Mitesh M. Khapra
Abstract	Deep Learning has managed to push boundaries in a wide variety of tasks. One area of interest is to tackle problems in reasoning and understanding, with an aim to emulate human intelligence. In this work, we describe a deep learning model that addresses the reasoning task of question-answering on categorical plots. We introduce a novel architecture FigureNet, that learns to identify various plot elements, quantify the represented values and determine a relative ordering of these statistical values. We test our model on the FigureQA dataset which provides images and accompanying questions for scientific plots like bar graphs and pie charts, augmented with rich annotations. Our approach outperforms the state-of-the-art Relation Networks baseline by approximately $7%$ on this dataset, with a training time that is over an order of magnitude lesser.
Tasks	Question Answering
Published	2018-06-12
URL	http://arxiv.org/abs/1806.04655v2
PDF	http://arxiv.org/pdf/1806.04655v2.pdf
PWC	https://paperswithcode.com/paper/a-question-answering-framework-for-plots
Repo
Framework