January 30, 2020

2980 words 14 mins read

Paper Group ANR 448

A Deep Learning-based Framework for the Detection of Schools of Herring in Echograms. Estimation of Utility-Maximizing Bounds on Potential Outcomes. What Synthesis is Missing: Depth Adaptation Integrated with Weak Supervision for Indoor Scene Parsing. Deep Representation Learning for Road Detection through Siamese Network. CWAE-IRL: Formulating a s …

A Deep Learning-based Framework for the Detection of Schools of Herring in Echograms


Title	A Deep Learning-based Framework for the Detection of Schools of Herring in Echograms
Authors	Alireza Rezvanifar, Tunai Porto Marques, Melissa Cote, Alexandra Branzan Albu, Alex Slonimer, Thomas Tolhurst, Kaan Ersahin, Todd Mudge, Stephane Gauthier
Abstract	Tracking the abundance of underwater species is crucial for understanding the effects of climate change on marine ecosystems. Biologists typically monitor underwater sites with echosounders and visualize data as 2D images (echograms); they interpret these data manually or semi-automatically, which is time-consuming and prone to inconsistencies. This paper proposes a deep learning framework for the automatic detection of schools of herring from echograms. Experiments demonstrated that our approach outperforms a traditional machine learning algorithm using hand-crafted features. Our framework could easily be expanded to detect more species of interest to sustainable fisheries.
Tasks
Published	2019-10-18
URL	https://arxiv.org/abs/1910.08215v1
PDF	https://arxiv.org/pdf/1910.08215v1.pdf
PWC	https://paperswithcode.com/paper/a-deep-learning-based-framework-for-the
Repo
Framework

Estimation of Utility-Maximizing Bounds on Potential Outcomes


Title	Estimation of Utility-Maximizing Bounds on Potential Outcomes
Authors	Maggie Makar, Fredrik D. Johansson, John Guttag, David Sontag
Abstract	Estimation of individual treatment effects is often used as the basis for contextual decision making in fields such as healthcare, education, and economics. However, in many real-world applications it is sufficient for the decision maker to have upper and lower bounds on the potential outcomes of decision alternatives, allowing them to evaluate the trade-off between benefit and risk. With this in mind, we develop an algorithm for directly learning upper and lower bounds on the potential outcomes under treatment and non-treatment. Our theoretical analysis highlights a trade-off between the complexity of the learning task and the confidence with which the resulting bounds cover the true potential outcomes; the more confident we wish to be, the more complex the learning task is. We suggest a novel algorithm that maximizes a utility function while maintaining valid potential outcome bounds. We illustrate different properties of our algorithm, and highlight how it can be used to guide decision making using two semi-simulated datasets.
Tasks	Decision Making
Published	2019-10-10
URL	https://arxiv.org/abs/1910.04817v1
PDF	https://arxiv.org/pdf/1910.04817v1.pdf
PWC	https://paperswithcode.com/paper/estimation-of-utility-maximizing-bounds-on
Repo
Framework

What Synthesis is Missing: Depth Adaptation Integrated with Weak Supervision for Indoor Scene Parsing


Title	What Synthesis is Missing: Depth Adaptation Integrated with Weak Supervision for Indoor Scene Parsing
Authors	Keng-Chi Liu, Yi-Ting Shen, Jan P. Klopp, Liang-Gee Chen
Abstract	Scene Parsing is a crucial step to enable autonomous systems to understand and interact with their surroundings. Supervised deep learning methods have made great progress in solving scene parsing problems, however, come at the cost of laborious manual pixel-level annotation. To alleviate this effort synthetic data as well as weak supervision have both been investigated. Nonetheless, synthetically generated data still suffers from severe domain shift while weak labels are often imprecise. Moreover, most existing works for weakly supervised scene parsing are limited to salient foreground objects. The aim of this work is hence twofold: Exploit synthetic data where feasible and integrate weak supervision where necessary. More concretely, we address this goal by utilizing depth as transfer domain because its synthetic-to-real discrepancy is much lower than for color. At the same time, we perform weak localization from easily obtainable image level labels and integrate both using a novel contour-based scheme. Our approach is implemented as a teacher-student learning framework to solve the transfer learning problem by generating a pseudo ground truth. Using only depth-based adaptation, this approach already outperforms previous transfer learning approaches on the popular indoor scene parsing SUN RGB-D dataset. Our proposed two-stage integration more than halves the gap towards fully supervised methods when compared to previous state-of-the-art in transfer learning.
Tasks	Scene Parsing, Transfer Learning
Published	2019-03-23
URL	http://arxiv.org/abs/1903.09781v1
PDF	http://arxiv.org/pdf/1903.09781v1.pdf
PWC	https://paperswithcode.com/paper/what-synthesis-is-missing-depth-adaptation
Repo
Framework

Deep Representation Learning for Road Detection through Siamese Network


Title	Deep Representation Learning for Road Detection through Siamese Network
Authors	Huafeng Liu, Xiaofeng Han, Xiangrui Li, Yazhou Yao, Pu Huang, Zhenming Tang
Abstract	Robust road detection is a key challenge in safe autonomous driving. Recently, with the rapid development of 3D sensors, more and more researchers are trying to fuse information across different sensors to improve the performance of road detection. Although many successful works have been achieved in this field, methods for data fusion under deep learning framework is still an open problem. In this paper, we propose a Siamese deep neural network based on FCN-8s to detect road region. Our method uses data collected from a monocular color camera and a Velodyne-64 LiDAR sensor. We project the LiDAR point clouds onto the image plane to generate LiDAR images and feed them into one of the branches of the network. The RGB images are fed into another branch of our proposed network. The feature maps that these two branches extract in multiple scales are fused before each pooling layer, via padding additional fusion layers. Extensive experimental results on public dataset KITTI ROAD demonstrate the effectiveness of our proposed approach.
Tasks	Autonomous Driving, Representation Learning
Published	2019-05-26
URL	https://arxiv.org/abs/1905.13394v1
PDF	https://arxiv.org/pdf/1905.13394v1.pdf
PWC	https://paperswithcode.com/paper/190513394
Repo
Framework

CWAE-IRL: Formulating a supervised approach to Inverse Reinforcement Learning problem


Title	CWAE-IRL: Formulating a supervised approach to Inverse Reinforcement Learning problem
Authors	Arpan Kusari
Abstract	Inverse reinforcement learning (IRL) is used to infer the reward function from the actions of an expert running a Markov Decision Process (MDP). A novel approach using variational inference for learning the reward function is proposed in this research. Using this technique, the intractable posterior distribution of the continuous latent variable (the reward function in this case) is analytically approximated to appear to be as close to the prior belief while trying to reconstruct the future state conditioned on the current state and action. The reward function is derived using a well-known deep generative model known as Conditional Variational Auto-encoder (CVAE) with Wasserstein loss function, thus referred to as Conditional Wasserstein Auto-encoder-IRL (CWAE-IRL), which can be analyzed as a combination of the backward and forward inference. This can then form an efficient alternative to the previous approaches to IRL while having no knowledge of the system dynamics of the agent. Experimental results on standard benchmarks such as objectworld and pendulum show that the proposed algorithm can effectively learn the latent reward function in complex, high-dimensional environments.
Tasks
Published	2019-10-02
URL	https://arxiv.org/abs/1910.00584v1
PDF	https://arxiv.org/pdf/1910.00584v1.pdf
PWC	https://paperswithcode.com/paper/cwae-irl-formulating-a-supervised-approach-to-1
Repo
Framework

Towards Understanding and Detecting Fake Reviews in App Stores


Title	Towards Understanding and Detecting Fake Reviews in App Stores
Authors	Daniel Martens, Walid Maalej
Abstract	App stores include an increasing amount of user feedback in form of app ratings and reviews. Research and recently also tool vendors have proposed analytics and data mining solutions to leverage this feedback to developers and analysts, e.g., for supporting release decisions. Research also showed that positive feedback improves apps’ downloads and sales figures and thus their success. As a side effect, a market for fake, incentivized app reviews emerged with yet unclear consequences for developers, app users, and app store operators. This paper studies fake reviews, their providers, characteristics, and how well they can be automatically detected. We conducted disguised questionnaires with 43 fake review providers and studied their review policies to understand their strategies and offers. By comparing 60,000 fake reviews with 62 million reviews from the Apple App Store we found significant differences, e.g., between the corresponding apps, reviewers, rating distribution, and frequency. This inspired the development of a simple classifier to automatically detect fake reviews in app stores. On a labelled and imbalanced dataset including one-tenth of fake reviews, as reported in other domains, our classifier achieved a recall of 91% and an AUC/ROC value of 98%. We discuss our findings and their impact on software engineering, app users, and app store operators.
Tasks
Published	2019-04-11
URL	http://arxiv.org/abs/1904.12607v1
PDF	http://arxiv.org/pdf/1904.12607v1.pdf
PWC	https://paperswithcode.com/paper/190412607
Repo
Framework

Frequency vs. Association for Constraint Selection in Usage-Based Construction Grammar


Title	Frequency vs. Association for Constraint Selection in Usage-Based Construction Grammar
Authors	Jonathan Dunn
Abstract	A usage-based Construction Grammar (CxG) posits that slot-constraints generalize from common exemplar constructions. But what is the best model of constraint generalization? This paper evaluates competing frequency-based and association-based models across eight languages using a metric derived from the Minimum Description Length paradigm. The experiments show that association-based models produce better generalizations across all languages by a significant margin.
Tasks
Published	2019-04-11
URL	http://arxiv.org/abs/1904.05529v1
PDF	http://arxiv.org/pdf/1904.05529v1.pdf
PWC	https://paperswithcode.com/paper/frequency-vs-association-for-constraint
Repo
Framework

A deep surrogate approach to efficient Bayesian inversion in PDE and integral equation models


Title	A deep surrogate approach to efficient Bayesian inversion in PDE and integral equation models
Authors	Teo Deveney, Eike Mueller, Tony Shardlow
Abstract	We propose a novel deep learning approach to efficiently perform Bayesian inference in partial differential equation (PDE) and integral equation models over potentially high-dimensional parameter spaces. The contributions of this paper are two-fold; the first is the introduction of a neural network approach to approximating the solutions of Fredholm and Volterra integral equations of the first and second kind. The second is the description of a deep surrogate model which allows for efficient sampling from a Bayesian posterior distribution in which the likelihood depends on the solutions of PDEs or integral equations. For the latter, our method relies on the approximate representation of parametric solutions by neural networks. This deep learning approach allows the accurate and efficient approximation of parametric solutions in significantly higher dimensions than is possible using classical techniques. Since the approximated solutions are very cheap to evaluate, the solutions of Bayesian inverse problems over large parameter spaces are tractable using Markov chain Monte Carlo. We demonstrate the efficiency of our method using two real-world examples; these include Bayesian inference in the PDE and integral equation case for an example from electrochemistry, and Bayesian inference of a function-valued heat-transfer parameter with applications in aviation.
Tasks	Bayesian Inference
Published	2019-10-03
URL	https://arxiv.org/abs/1910.01547v3
PDF	https://arxiv.org/pdf/1910.01547v3.pdf
PWC	https://paperswithcode.com/paper/a-deep-surrogate-approach-to-efficient
Repo
Framework

Manifold Fitting in Ambient Space


Title	Manifold Fitting in Ambient Space
Authors	Zhigang Yao, Wee Chin Tan
Abstract	Modern data sets in many applications no longer comprise samples of real vectors in a real vector space but samples of much more complex structures which may be represented as points in a space with certain underlying geometric structure, namely a manifold. Manifold learning is an emerging field for learning the underlying structure. The study of manifold learning can be split into two main branches, namely dimension reduction and manifold fitting. With the aim of interacting statistics and geometry, we tackle the problem of manifold fitting in the ambient space. Inspired by the relation between the eigenvalues of the Laplace-Beltrami operator and the geometry of a manifold, we aim to find a small set of points that preserve the geometry of the underlying manifold. Based on this relationship, we extend the idea of subsampling to noisy datasets in high dimensional space and utilize the Moving Least Squares (MLS) approach to approximate the underlying manifold. We analyze the two core steps in our proposed method theoretically and also provide the bounds for the MLS approach. Our simulation results and real data analysis demonstrate the superiority of our method in estimating the underlying manifold from noisy data.
Tasks	Dimensionality Reduction
Published	2019-09-30
URL	https://arxiv.org/abs/1909.13492v1
PDF	https://arxiv.org/pdf/1909.13492v1.pdf
PWC	https://paperswithcode.com/paper/manifold-fitting-in-ambient-space
Repo
Framework

VoxSRC 2019: The first VoxCeleb Speaker Recognition Challenge


Title	VoxSRC 2019: The first VoxCeleb Speaker Recognition Challenge
Authors	Joon Son Chung, Arsha Nagrani, Ernesto Coto, Weidi Xie, Mitchell McLaren, Douglas A Reynolds, Andrew Zisserman
Abstract	The VoxCeleb Speaker Recognition Challenge 2019 aimed to assess how well current speaker recognition technology is able to identify speakers in unconstrained or `in the wild’ data. It consisted of: (i) a publicly available speaker recognition dataset from YouTube videos together with ground truth annotation and standardised evaluation software; and (ii) a public challenge and workshop held at Interspeech 2019 in Graz, Austria. This paper outlines the challenge and provides its baselines, results and discussions. \|
Tasks	Speaker Recognition
Published	2019-12-05
URL	https://arxiv.org/abs/1912.02522v1
PDF	https://arxiv.org/pdf/1912.02522v1.pdf
PWC	https://paperswithcode.com/paper/voxsrc-2019-the-first-voxceleb-speaker
Repo
Framework

A Stochastic Trust Region Method for Non-convex Minimization


Title	A Stochastic Trust Region Method for Non-convex Minimization
Authors	Zebang Shen, Pan Zhou, Cong Fang, Alejandro Ribeiro
Abstract	We target the problem of finding a local minimum in non-convex finite-sum minimization. Towards this goal, we first prove that the trust region method with inexact gradient and Hessian estimation can achieve a convergence rate of order $\mathcal{O}(1/{k^{2/3}})$ as long as those differential estimations are sufficiently accurate. Combining such result with a novel Hessian estimator, we propose the sample-efficient stochastic trust region (STR) algorithm which finds an $(\epsilon, \sqrt{\epsilon})$-approximate local minimum within $\mathcal{O}({\sqrt{n}}/{\epsilon^{1.5}})$ stochastic Hessian oracle queries. This improves state-of-the-art result by $\mathcal{O}(n^{1/6})$. Experiments verify theoretical conclusions and the efficiency of STR.
Tasks
Published	2019-03-04
URL	http://arxiv.org/abs/1903.01540v1
PDF	http://arxiv.org/pdf/1903.01540v1.pdf
PWC	https://paperswithcode.com/paper/a-stochastic-trust-region-method-for-non
Repo
Framework

Machine Learning Meets Quantitative Planning: Enabling Self-Adaptation in Autonomous Robots


Title	Machine Learning Meets Quantitative Planning: Enabling Self-Adaptation in Autonomous Robots
Authors	Pooyan Jamshidi, Javier Cámara, Bradley Schmerl, Christian Kästner, David Garlan
Abstract	Modern cyber-physical systems (e.g., robotics systems) are typically composed of physical and software components, the characteristics of which are likely to change over time. Assumptions about parts of the system made at design time may not hold at run time, especially when a system is deployed for long periods (e.g., over decades). Self-adaptation is designed to find reconfigurations of systems to handle such run-time inconsistencies. Planners can be used to find and enact optimal reconfigurations in such an evolving context. However, for systems that are highly configurable, such planning becomes intractable due to the size of the adaptation space. To overcome this challenge, in this paper we explore an approach that (a) uses machine learning to find Pareto-optimal configurations without needing to explore every configuration and (b) restricts the search space to such configurations to make planning tractable. We explore this in the context of robot missions that need to consider task timeliness and energy consumption. An independent evaluation shows that our approach results in high-quality adaptation plans in uncertain and adversarial environments.
Tasks
Published	2019-03-10
URL	http://arxiv.org/abs/1903.03920v1
PDF	http://arxiv.org/pdf/1903.03920v1.pdf
PWC	https://paperswithcode.com/paper/machine-learning-meets-quantitative-planning
Repo
Framework

On Better Exploring and Exploiting Task Relationships in Multi-Task Learning: Joint Model and Feature Learning


Title	On Better Exploring and Exploiting Task Relationships in Multi-Task Learning: Joint Model and Feature Learning
Authors	Ya Li, Xinmei Tian, Tongliang Liu, Dacheng Tao
Abstract	Multitask learning (MTL) aims to learn multiple tasks simultaneously through the interdependence between different tasks. The way to measure the relatedness between tasks is always a popular issue. There are mainly two ways to measure relatedness between tasks: common parameters sharing and common features sharing across different tasks. However, these two types of relatedness are mainly learned independently, leading to a loss of information. In this paper, we propose a new strategy to measure the relatedness that jointly learns shared parameters and shared feature representations. The objective of our proposed method is to transform the features from different tasks into a common feature space in which the tasks are closely related and the shared parameters can be better optimized. We give a detailed introduction to our proposed multitask learning method. Additionally, an alternating algorithm is introduced to optimize the nonconvex objection. A theoretical bound is given to demonstrate that the relatedness between tasks can be better measured by our proposed multitask learning algorithm. We conduct various experiments to verify the superiority of the proposed joint model and feature a multitask learning method.
Tasks	Multi-Task Learning
Published	2019-04-03
URL	http://arxiv.org/abs/1904.01747v1
PDF	http://arxiv.org/pdf/1904.01747v1.pdf
PWC	https://paperswithcode.com/paper/on-better-exploring-and-exploiting-task
Repo
Framework

A Reinforcement Learning Perspective on the Optimal Control of Mutation Probabilities for the (1+1) Evolutionary Algorithm: First Results on the OneMax Problem


Title	A Reinforcement Learning Perspective on the Optimal Control of Mutation Probabilities for the (1+1) Evolutionary Algorithm: First Results on the OneMax Problem
Authors	Luca Mossina, Emmanuel Rachelson, Daniel Delahaye
Abstract	We study how Reinforcement Learning can be employed to optimally control parameters in evolutionary algorithms. We control the mutation probability of a (1+1) evolutionary algorithm on the OneMax function. This problem is modeled as a Markov Decision Process and solved with Value Iteration via the known transition probabilities. It is then solved via Q-Learning, a Reinforcement Learning algorithm, where the exact transition probabilities are not needed. This approach also allows previous expert or empirical knowledge to be included into learning. It opens new perspectives, both formally and computationally, for the problem of parameter control in optimization.
Tasks	Q-Learning
Published	2019-05-09
URL	https://arxiv.org/abs/1905.03726v1
PDF	https://arxiv.org/pdf/1905.03726v1.pdf
PWC	https://paperswithcode.com/paper/190503726
Repo
Framework

Evolutionary Multi-Objective Optimization Driven by Generative Adversarial Networks


Title	Evolutionary Multi-Objective Optimization Driven by Generative Adversarial Networks
Authors	Cheng He, Shihua Huang, Ran Cheng, Kay Chen Tan, Yaochu Jin
Abstract	Recently, more and more works have proposed to drive evolutionary algorithms using machine learning models.Usually, the performance of such model based evolutionary algorithms is highly dependent on the training qualities of the adopted models.Since it usually requires a certain amount of data (i.e. the candidate solutions generated by the algorithms) for model training, the performance deteriorates rapidly with the increase of the problem scales, due to the curse of dimensionality.To address this issue, we propose a multi-objective evolutionary algorithm driven by the generative adversarial networks (GANs).At each generation of the proposed algorithm, the parent solutions are first classified into \emph{real} and \emph{fake} samples to train the GANs; then the offspring solutions are sampled by the trained GANs.Thanks to the powerful generative ability of the GANs, our proposed algorithm is capable of generating promising offspring solutions in high-dimensional decision space with limited training data.The proposed algorithm is tested on 10 benchmark problems with up to 200 decision variables.Experimental results on these test problems demonstrate the effectiveness of the proposed algorithm.
Tasks
Published	2019-07-10
URL	https://arxiv.org/abs/1907.04482v1
PDF	https://arxiv.org/pdf/1907.04482v1.pdf
PWC	https://paperswithcode.com/paper/evolutionary-multi-objective-optimization
Repo
Framework