January 30, 2020

3160 words 15 mins read

Paper Group ANR 365

Analyzing the Cross-Sensor Portability of Neural Network Architectures for LiDAR-based Semantic Labeling. A Theory of Uncertainty Variables for State Estimation and Inference. Applying Abstract Argumentation Theory to Cooperative Game Theory. Towards Realistic Practices In Low-Resource Natural Language Processing: The Development Set. Enhancing the …

Analyzing the Cross-Sensor Portability of Neural Network Architectures for LiDAR-based Semantic Labeling


Title	Analyzing the Cross-Sensor Portability of Neural Network Architectures for LiDAR-based Semantic Labeling
Authors	Florian Piewak, Peter Pinggera, Marius Zöllner
Abstract	State-of-the-art approaches for the semantic labeling of LiDAR point clouds heavily rely on the use of deep Convolutional Neural Networks (CNNs). However, transferring network architectures across different LiDAR sensor types represents a significant challenge, especially due to sensor specific design choices with regard to network architecture as well as data representation. In this paper we propose a new CNN architecture for the point-wise semantic labeling of LiDAR data which achieves state-of-the-art results while increasing portability across sensor types. This represents a significant advantage given the fast-paced development of LiDAR hardware technology. We perform a thorough quantitative cross-sensor analysis of semantic labeling performance in comparison to a state-of-the-art reference method. Our evaluation shows that the proposed architecture is indeed highly portable, yielding an improvement of 10 percentage points in the Intersection-over-Union (IoU) score when compared to the reference approach. Further, the results indicate that the proposed network architecture can provide an efficient way for the automated generation of large-scale training data for novel LiDAR sensor types without the need for extensive manual annotation or multi-modal label transfer.
Tasks
Published	2019-07-03
URL	https://arxiv.org/abs/1907.02149v1
PDF	https://arxiv.org/pdf/1907.02149v1.pdf
PWC	https://paperswithcode.com/paper/analyzing-the-cross-sensor-portability-of
Repo
Framework

A Theory of Uncertainty Variables for State Estimation and Inference


Title	A Theory of Uncertainty Variables for State Estimation and Inference
Authors	Rajat Talak, Sertac Karaman, Eytan Modiano
Abstract	We develop a new framework of uncertainty variables to model uncertainty. An uncertainty variable is characterized by an uncertainty set, in which its realization is bound to lie, while the conditional uncertainty is characterized by a set map, from a given realization of a variable to a set of possible realizations of another variable. We prove Bayes’ law and the law of total probability equivalents for uncertainty variables. We define a notion of independence, conditional independence, and pairwise independence for a collection of uncertainty variables, and show that this new notion of independence preserves the properties of independence defined over random variables. We then develop a graphical model, namely Bayesian uncertainty network, a Bayesian network equivalent defined over a collection of uncertainty variables, and show that all the natural conditional independence properties, expected out of a Bayesian network, hold for the Bayesian uncertainty network. We also define the notion of point estimate, and show its relation with the maximum a posteriori estimate. Probability theory starts with a distribution function (equivalently a probability measure) as a primitive and builds all other useful concepts, such as law of total probability, Bayes’ law, independence, graphical models, point estimate, on it. Our work shows that it is perfectly possible to start with a set, instead of a distribution function, and retain all the useful ideas needed for state estimation and inference.
Tasks
Published	2019-09-24
URL	https://arxiv.org/abs/1909.10673v2
PDF	https://arxiv.org/pdf/1909.10673v2.pdf
PWC	https://paperswithcode.com/paper/a-theory-of-uncertainty-variables-for-state
Repo
Framework

Applying Abstract Argumentation Theory to Cooperative Game Theory


Title	Applying Abstract Argumentation Theory to Cooperative Game Theory
Authors	Anthony P. Young, David Kohan Marzagao, Josh Murphy
Abstract	We apply ideas from abstract argumentation theory to study cooperative game theory. Building on Dung’s results in his seminal paper, we further the correspondence between Dung’s four argumentation semantics and solution concepts in cooperative game theory by showing that complete extensions (the grounded extension) correspond to Roth’s subsolutions (respectively, the supercore). We then investigate the relationship between well-founded argumentation frameworks and convex games, where in each case the semantics (respectively, solution concepts) coincide; we prove that three-player convex games do not in general have well-founded argumentation frameworks.
Tasks	Abstract Argumentation
Published	2019-05-15
URL	https://arxiv.org/abs/1905.10922v3
PDF	https://arxiv.org/pdf/1905.10922v3.pdf
PWC	https://paperswithcode.com/paper/190510922
Repo
Framework

Towards Realistic Practices In Low-Resource Natural Language Processing: The Development Set


Title	Towards Realistic Practices In Low-Resource Natural Language Processing: The Development Set
Authors	Katharina Kann, Kyunghyun Cho, Samuel R. Bowman
Abstract	Development sets are impractical to obtain for real low-resource languages, since using all available data for training is often more effective. However, development sets are widely used in research papers that purport to deal with low-resource natural language processing (NLP). Here, we aim to answer the following questions: Does using a development set for early stopping in the low-resource setting influence results as compared to a more realistic alternative, where the number of training epochs is tuned on development languages? And does it lead to overestimation or underestimation of performance? We repeat multiple experiments from recent work on neural models for low-resource NLP and compare results for models obtained by training with and without development sets. On average over languages, absolute accuracy differs by up to 1.4%. However, for some languages and tasks, differences are as big as 18.0% accuracy. Our results highlight the importance of realistic experimental setups in the publication of low-resource NLP research results.
Tasks
Published	2019-09-04
URL	https://arxiv.org/abs/1909.01522v2
PDF	https://arxiv.org/pdf/1909.01522v2.pdf
PWC	https://paperswithcode.com/paper/towards-realistic-practices-in-low-resource
Repo
Framework

Enhancing the Robustness of Deep Neural Networks by Boundary Conditional GAN


Title	Enhancing the Robustness of Deep Neural Networks by Boundary Conditional GAN
Authors	Ke Sun, Zhanxing Zhu, Zhouchen Lin
Abstract	Deep neural networks have been widely deployed in various machine learning tasks. However, recent works have demonstrated that they are vulnerable to adversarial examples: carefully crafted small perturbations to cause misclassification by the network. In this work, we propose a novel defense mechanism called Boundary Conditional GAN to enhance the robustness of deep neural networks against adversarial examples. Boundary Conditional GAN, a modified version of Conditional GAN, can generate boundary samples with true labels near the decision boundary of a pre-trained classifier. These boundary samples are fed to the pre-trained classifier as data augmentation to make the decision boundary more robust. We empirically show that the model improved by our approach consistently defenses against various types of adversarial attacks successfully. Further quantitative investigations about the improvement of robustness and visualization of decision boundaries are also provided to justify the effectiveness of our strategy. This new defense mechanism that uses boundary samples to enhance the robustness of networks opens up a new way to defense adversarial attacks consistently.
Tasks	Data Augmentation
Published	2019-02-28
URL	http://arxiv.org/abs/1902.11029v1
PDF	http://arxiv.org/pdf/1902.11029v1.pdf
PWC	https://paperswithcode.com/paper/enhancing-the-robustness-of-deep-neural
Repo
Framework

Directional Adversarial Training for Cost Sensitive Deep Learning Classification Applications


Title	Directional Adversarial Training for Cost Sensitive Deep Learning Classification Applications
Authors	Matteo Terzi, Gian Antonio Susto, Pratik Chaudhari
Abstract	In many real-world applications of Machine Learning it is of paramount importance not only to provide accurate predictions, but also to ensure certain levels of robustness. Adversarial Training is a training procedure aiming at providing models that are robust to worst-case perturbations around predefined points. Unfortunately, one of the main issues in adversarial training is that robustness w.r.t. gradient-based attackers is always achieved at the cost of prediction accuracy. In this paper, a new algorithm, called Wasserstein Projected Gradient Descent (WPGD), for adversarial training is proposed. WPGD provides a simple way to obtain cost-sensitive robustness, resulting in a finer control of the robustness-accuracy trade-off. Moreover, WPGD solves an optimal transport problem on the output space of the network and it can efficiently discover directions where robustness is required, allowing to control the directional trade-off between accuracy and robustness. The proposed WPGD is validated in this work on image recognition tasks with different benchmark datasets and architectures. Moreover, real world-like datasets are often unbalanced: this paper shows that when dealing with such type of datasets, the performance of adversarial training are mainly affected in term of standard accuracy.
Tasks
Published	2019-10-08
URL	https://arxiv.org/abs/1910.03468v1
PDF	https://arxiv.org/pdf/1910.03468v1.pdf
PWC	https://paperswithcode.com/paper/directional-adversarial-training-for-cost
Repo
Framework

Unsupervised Abnormality Detection through Mixed Structure Regularization (MSR) in Deep Sparse Autoencoders


Title	Unsupervised Abnormality Detection through Mixed Structure Regularization (MSR) in Deep Sparse Autoencoders
Authors	Moti Freiman, Ravindra Manjeshwar, Liran Goshen
Abstract	Deep sparse auto-encoders with mixed structure regularization (MSR) in addition to explicit sparsity regularization term and stochastic corruption of the input data with Gaussian noise have the potential to improve unsupervised abnormality detection. Unsupervised abnormality detection based on identifying outliers using deep sparse auto-encoders is a very appealing approach for medical computer aided detection systems as it requires only healthy data for training rather than expert annotated abnormality. In the task of detecting coronary artery disease from Coronary Computed Tomography Angiography (CCTA), our results suggests that the MSR has the potential to improve overall performance by 20-30% compared to deep sparse and denoising auto-encoders.
Tasks	Anomaly Detection, Denoising
Published	2019-02-28
URL	http://arxiv.org/abs/1902.11036v1
PDF	http://arxiv.org/pdf/1902.11036v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-abnormality-detection-through
Repo
Framework

Power Control for Wireless VBR Video Streaming: From Optimization to Reinforcement Learning


Title	Power Control for Wireless VBR Video Streaming: From Optimization to Reinforcement Learning
Authors	Chuang Ye, M. Cenk Gursoy, Senem Velipasalar
Abstract	In this paper, we investigate the problem of power control for streaming variable bit rate (VBR) videos over wireless links. A system model involving a transmitter (e.g., a base station) that sends VBR video data to a receiver (e.g., a mobile user) equipped with a playout buffer is adopted, as used in dynamic adaptive streaming video applications. In this setting, we analyze power control policies considering the following two objectives: 1) the minimization of the transmit power consumption, and 2) the minimization of the transmission completion time of the communication session. In order to play the video without interruptions, the power control policy should also satisfy the requirement that the VBR video data is delivered to the mobile user without causing playout buffer underflow or overflows. A directional water-filling algorithm, which provides a simple and concise interpretation of the necessary optimality conditions, is identified as the optimal offline policy. Following this, two online policies are proposed for power control based on channel side information (CSI) prediction within a short time window. Dynamic programming is employed to implement the optimal offline and the initial online power control policies that minimize the transmit power consumption in the communication session. Subsequently, reinforcement learning (RL) based approach is employed for the second online power control policy. Via simulation results, we show that the optimal offline power control policy that minimizes the overall power consumption leads to substantial energy savings compared to the strategy of minimizing the time duration of video streaming. We also demonstrate that the RL algorithm performs better than the dynamic programming based online grouped water-filling (GWF) strategy unless the channel is highly correlated.
Tasks
Published	2019-03-31
URL	http://arxiv.org/abs/1904.00327v1
PDF	http://arxiv.org/pdf/1904.00327v1.pdf
PWC	https://paperswithcode.com/paper/power-control-for-wireless-vbr-video
Repo
Framework

Zero-shot Learning and Knowledge Transfer in Music Classification and Tagging


Title	Zero-shot Learning and Knowledge Transfer in Music Classification and Tagging
Authors	Jeong Choi, Jongpil Lee, Jiyoung Park, Juhan Nam
Abstract	Music classification and tagging is conducted through categorical supervised learning with a fixed set of labels. In principle, this cannot make predictions on unseen labels. Zero-shot learning is an approach to solve the problem by using side information about the semantic labels. We recently investigated this concept of zero-shot learning in music classification and tagging task by projecting both audio and label space on a single semantic space. In this work, we extend the work to verify the generalization ability of zero-shot learning model by conducting knowledge transfer to different music corpora.
Tasks	Music Classification, Transfer Learning, Zero-Shot Learning
Published	2019-06-20
URL	https://arxiv.org/abs/1906.08615v1
PDF	https://arxiv.org/pdf/1906.08615v1.pdf
PWC	https://paperswithcode.com/paper/zero-shot-learning-and-knowledge-transfer-in
Repo
Framework

Zero-Shot Image Classification Using Coupled Dictionary Embedding


Title	Zero-Shot Image Classification Using Coupled Dictionary Embedding
Authors	Mohammad Rostami, Soheil Kolouri, Zak Murez, Yuri Owekcho, Eric Eaton, Kuyngnam Kim
Abstract	Zero-shot learning (ZSL) is a framework to classify images belonging to unseen classes based on solely semantic information about these unseen classes. In this paper, we propose a new ZSL algorithm using coupled dictionary learning. The core idea is that the visual features and the semantic attributes of an image can share the same sparse representation in an intermediate space. We use images from seen classes and semantic attributes from seen and unseen classes to learn two dictionaries that can represent sparsely the visual and semantic feature vectors of an image. In the ZSL testing stage and in the absence of labeled data, images from unseen classes can be mapped into the attribute space by finding the joint sparse representation using solely the visual data. The image is then classified in the attribute space given semantic descriptions of unseen classes. We also provide an attribute-aware formulation to tackle domain shift and hubness problems in ZSL. Extensive experiments are provided to demonstrate the superior performance of our approach against the state of the art ZSL algorithms on benchmark ZSL datasets.
Tasks	Dictionary Learning, Image Classification, Zero-Shot Learning
Published	2019-06-10
URL	https://arxiv.org/abs/1906.10509v1
PDF	https://arxiv.org/pdf/1906.10509v1.pdf
PWC	https://paperswithcode.com/paper/zero-shot-image-classification-using-coupled
Repo
Framework

Sentiment Analysis at SEPLN (TASS)-2019: Sentiment Analysis at Tweet level using Deep Learning


Title	Sentiment Analysis at SEPLN (TASS)-2019: Sentiment Analysis at Tweet level using Deep Learning
Authors	Avishek Garain, Sainik Kumar Mahata
Abstract	This paper describes the system submitted to “Sentiment Analysis at SEPLN (TASS)-2019” shared task. The task includes sentiment analysis of Spanish tweets, where the tweets are in different dialects spoken in Spain, Peru, Costa Rica, Uruguay and Mexico. The tweets are short (up to 240 characters) and the language is informal, i.e., it contains misspellings, emojis, onomatopeias etc. Sentiment analysis includes classification of the tweets into 4 classes, viz., Positive, Negative, Neutral and None. For preparing the proposed system, we use Deep Learning networks like LSTMs.
Tasks	Sentiment Analysis
Published	2019-08-01
URL	https://arxiv.org/abs/1908.00321v1
PDF	https://arxiv.org/pdf/1908.00321v1.pdf
PWC	https://paperswithcode.com/paper/sentiment-analysis-at-sepln-tass-2019
Repo
Framework

On the Analysis of EM for truncated mixtures of two Gaussians


Title	On the Analysis of EM for truncated mixtures of two Gaussians
Authors	Sai Ganesh Nagarajan, Ioannis Panageas
Abstract	Motivated by a recent result of Daskalakis et al. 2018, we analyze the population version of Expectation-Maximization (EM) algorithm for the case of \textit{truncated} mixtures of two Gaussians. Truncated samples from a $d$-dimensional mixture of two Gaussians $\frac{1}{2} \mathcal{N}(\vec{\mu}, \vec{\Sigma})+ \frac{1}{2} \mathcal{N}(-\vec{\mu}, \vec{\Sigma})$ means that a sample is only revealed if it falls in some subset $S \subset \mathbb{R}^d$ of positive (Lebesgue) measure. We show that for $d=1$, EM converges almost surely (under random initialization) to the true mean (variance $\sigma^2$ is known) for any measurable set $S$. Moreover, for $d>1$ we show EM almost surely converges to the true mean for any measurable set $S$ when the map of EM has only three fixed points, namely $-\vec{\mu}, \vec{0}, \vec{\mu}$ (covariance matrix $\vec{\Sigma}$ is known), and prove local convergence if there are more than three fixed points. We also provide convergence rates of our findings. Our techniques deviate from those of Daskalakis et al. 2017, which heavily depend on symmetry that the untruncated problem exhibits. For example, for an arbitrary measurable set $S$, it is impossible to compute a closed form of the update rule of EM. Moreover, arbitrarily truncating the mixture, induces further correlations among the variables. We circumvent these challenges by using techniques from dynamical systems, probability and statistics; implicit function theorem, stability analysis around the fixed points of the update rule of EM and correlation inequalities (FKG).
Tasks
Published	2019-02-19
URL	https://arxiv.org/abs/1902.06958v5
PDF	https://arxiv.org/pdf/1902.06958v5.pdf
PWC	https://paperswithcode.com/paper/on-the-convergence-of-em-for-truncated
Repo
Framework

An unsupervised approach to Geographical Knowledge Discovery using street level and street network images


Title	An unsupervised approach to Geographical Knowledge Discovery using street level and street network images
Authors	Stephen Law, Mateo Neira
Abstract	Recent researches have shown the increasing use of machine learn-ing methods in geography and urban analytics, primarily to extract features and patterns from spatial and temporal data using a supervised approach. Researches integrating geographical processes in machine learning models and the use of unsupervised approacheson geographical data for knowledge discovery had been sparse. This research contributes to the ladder, where we show how latent variables learned from unsupervised learning methods on urbanimages can be used for geographic knowledge discovery. In particular, we propose a simple approach called Convolutional-PCA(ConvPCA) which are applied on both street level and street network images to find a set of uncorrelated and ordered visual latentcomponents. The approach allows for meaningful explanations using a combination of geographical and generative visualisations to explore the latent space, and to show how the learned representation can be used to predict urban characteristics such as streetquality and street network attributes. The research also finds that the visual components from the ConvPCA model achieves similaraccuracy when compared to less interpretable dimension reduction techniques.
Tasks	Dimensionality Reduction
Published	2019-06-18
URL	https://arxiv.org/abs/1906.11907v2
PDF	https://arxiv.org/pdf/1906.11907v2.pdf
PWC	https://paperswithcode.com/paper/learning-from-discovering-an-unsupervised
Repo
Framework

Shallow Water Bathymetry Mapping from UAV Imagery based on Machine Learning


Title	Shallow Water Bathymetry Mapping from UAV Imagery based on Machine Learning
Authors	Panagiotis Agrafiotis, Dimitrios Skarlatos, Andreas Georgopoulos, Konstantinos Karantzalos
Abstract	The determination of accurate bathymetric information is a key element for near offshore activities, hydrological studies such as coastal engineering applications, sedimentary processes, hydrographic surveying as well as archaeological mapping and biological research. UAV imagery processed with Structure from Motion (SfM) and Multi View Stereo (MVS) techniques can provide a low-cost alternative to established shallow seabed mapping techniques offering as well the important visual information. Nevertheless, water refraction poses significant challenges on depth determination. Till now, this problem has been addressed through customized image-based refraction correction algorithms or by modifying the collinearity equation. In this paper, in order to overcome the water refraction errors, we employ machine learning tools that are able to learn the systematic underestimation of the estimated depths. In the proposed approach, based on known depth observations from bathymetric LiDAR surveys, an SVR model was developed able to estimate more accurately the real depths of point clouds derived from SfM-MVS procedures. Experimental results over two test sites along with the performed quantitative validation indicated the high potential of the developed approach.
Tasks
Published	2019-02-27
URL	https://arxiv.org/abs/1902.10733v3
PDF	https://arxiv.org/pdf/1902.10733v3.pdf
PWC	https://paperswithcode.com/paper/shallow-water-bathymetry-mapping-from-uav
Repo
Framework

SafeCritic: Collision-Aware Trajectory Prediction


Title	SafeCritic: Collision-Aware Trajectory Prediction
Authors	Tessa van der Heiden, Naveen Shankar Nagaraja, Christian Weiss, Efstratios Gavves
Abstract	Navigating complex urban environments safely is a key to realize fully autonomous systems. Predicting future locations of vulnerable road users, such as pedestrians and cyclists, thus, has received a lot of attention in the recent years. While previous works have addressed modeling interactions with the static (obstacles) and dynamic (humans) environment agents, we address an important gap in trajectory prediction. We propose SafeCritic, a model that synergizes generative adversarial networks for generating multiple “real” trajectories with reinforcement learning to generate “safe” trajectories. The Discriminator evaluates the generated candidates on whether they are consistent with the observed inputs. The Critic network is environmentally aware to prune trajectories that are in collision or are in violation with the environment. The auto-encoding loss stabilizes training and prevents mode-collapse. We demonstrate results on two large scale data sets with a considerable improvement over state-of-the-art. We also show that the Critic is able to classify the safety of trajectories.
Tasks	Trajectory Prediction
Published	2019-10-15
URL	https://arxiv.org/abs/1910.06673v1
PDF	https://arxiv.org/pdf/1910.06673v1.pdf
PWC	https://paperswithcode.com/paper/safecritic-collision-aware-trajectory
Repo
Framework