January 25, 2020

3445 words 17 mins read

Paper Group ANR 1746

A Study of Deep Learning for Network Traffic Data Forecasting. Generation & Evaluation of Adversarial Examples for Malware Obfuscation. ES-MAML: Simple Hessian-Free Meta Learning. Learning to Reconstruct and Understand Indoor Scenes from Sparse Views. Tell-the-difference: Fine-grained Visual Descriptor via a Discriminating Referee. Automated Multid …

A Study of Deep Learning for Network Traffic Data Forecasting


Title	A Study of Deep Learning for Network Traffic Data Forecasting
Authors	Benedikt Pfülb, Christoph Hardegen, Alexander Gepperth, Sebastian Rieger
Abstract	We present a study of deep learning applied to the domain of network traffic data forecasting. This is a very important ingredient for network traffic engineering, e.g., intelligent routing, which can optimize network performance, especially in large networks. In a nutshell, we wish to predict, in advance, the bit rate for a transmission, based on low-dimensional connection metadata (“flows”) that is available whenever a communication is initiated. Our study has several genuinely new points: First, it is performed on a large dataset (~50 million flows), which requires a new training scheme that operates on successive blocks of data since the whole dataset is too large for in-memory processing. Additionally, we are the first to propose and perform a more fine-grained prediction that distinguishes between low, medium and high bit rates instead of just “mice” and “elephant” flows. Lastly, we apply state-of-the-art visualization and clustering techniques to flow data and show that visualizations are insightful despite the heterogeneous and non-metric nature of the data. We developed a processing pipeline to handle the highly non-trivial acquisition process and allow for proper data preprocessing to be able to apply DNNs to network traffic data. We conduct DNN hyper-parameter optimization as well as feature selection experiments, which clearly show that fine-grained network traffic forecasting is feasible, and that domain-dependent data enrichment and augmentation strategies can improve results. An outlook about the fundamental challenges presented by network traffic analysis (high data throughput, unbalanced and dynamic classes, changing statistics, outlier detection) concludes the article.
Tasks	Feature Selection, Outlier Detection
Published	2019-09-10
URL	https://arxiv.org/abs/1909.04501v2
PDF	https://arxiv.org/pdf/1909.04501v2.pdf
PWC	https://paperswithcode.com/paper/a-study-of-deep-learning-for-network-traffic
Repo
Framework

Generation & Evaluation of Adversarial Examples for Malware Obfuscation


Title	Generation & Evaluation of Adversarial Examples for Malware Obfuscation
Authors	Daniel Park, Haidar Khan, Bülent Yener
Abstract	There has been an increased interest in the application of convolutional neural networks for image based malware classification, but the susceptibility of neural networks to adversarial examples allows malicious actors to evade classifiers. Adversarial examples are usually generated by adding small perturbations to the input that are unrecognizable to humans, but the same approach is not effective with malware. In general, these perturbations cause changes in the byte sequences that change the initial functionality or result in un-executable binaries. We present a generative model for executable adversarial malware examples using obfuscation that achieves a high misclassification rate, up to 100% and 98% in white-box and black-box settings respectively, and demonstrates transferability. We further evaluate the effectiveness of the proposed method by reporting insignificant change in the evasion rate of our adversarial examples against popular defense strategies.
Tasks	Malware Classification
Published	2019-04-09
URL	https://arxiv.org/abs/1904.04802v3
PDF	https://arxiv.org/pdf/1904.04802v3.pdf
PWC	https://paperswithcode.com/paper/short-paper-creating-adversarial-malware
Repo
Framework

ES-MAML: Simple Hessian-Free Meta Learning


Title	ES-MAML: Simple Hessian-Free Meta Learning
Authors	Xingyou Song, Wenbo Gao, Yuxiang Yang, Krzysztof Choromanski, Aldo Pacchiano, Yunhao Tang
Abstract	We introduce ES-MAML, a new framework for solving the model agnostic meta learning (MAML) problem based on Evolution Strategies (ES). Existing algorithms for MAML are based on policy gradients, and incur significant difficulties when attempting to estimate second derivatives using backpropagation on stochastic policies. We show how ES can be applied to MAML to obtain an algorithm which avoids the problem of estimating second derivatives, and is also conceptually simple and easy to implement. Moreover, ES-MAML can handle new types of nonsmooth adaptation operators, and other techniques for improving performance and estimation of ES methods become applicable. We show empirically that ES-MAML is competitive with existing methods and often yields better adaptation with fewer queries.
Tasks	Meta-Learning
Published	2019-09-25
URL	https://arxiv.org/abs/1910.01215v3
PDF	https://arxiv.org/pdf/1910.01215v3.pdf
PWC	https://paperswithcode.com/paper/es-maml-simple-hessian-free-meta-learning
Repo
Framework

Learning to Reconstruct and Understand Indoor Scenes from Sparse Views


Title	Learning to Reconstruct and Understand Indoor Scenes from Sparse Views
Authors	Jingyu Yang, Ji Xu, Kun Li, Yu-Kun Lai, Huanjing Yue, Jianzhi Lu, Hao Wu, Yebin Liu
Abstract	This paper proposes a new method for simultaneous 3D reconstruction and semantic segmentation of indoor scenes. Unlike existing methods that require recording a video using a color camera and/or a depth camera, our method only needs a small number of (e.g., 3-5) color images from uncalibrated sparse views as input, which greatly simplifies data acquisition and extends applicable scenarios. Since different views have limited overlaps, our method allows a single image as input to discern the depth and semantic information of the scene. The key issue is how to recover relatively accurate depth from single images and reconstruct a 3D scene by fusing very few depth maps. To address this problem, we first design an iterative deep architecture, IterNet, that estimates depth and semantic segmentation alternately, so that they benefit each other. To deal with the little overlap and non-rigid transformation between views, we further propose a joint global and local registration method to reconstruct a 3D scene with semantic information from sparse views. We also make available a new indoor synthetic dataset simultaneously providing photorealistic high-resolution RGB images, accurate depth maps and pixel-level semantic labels for thousands of complex layouts, useful for training and evaluation. Experimental results on public datasets and our dataset demonstrate that our method achieves more accurate depth estimation, smaller semantic segmentation errors and better 3D reconstruction results, compared with state-of-the-art methods.
Tasks	3D Reconstruction, Depth Estimation, Semantic Segmentation
Published	2019-06-19
URL	https://arxiv.org/abs/1906.07892v1
PDF	https://arxiv.org/pdf/1906.07892v1.pdf
PWC	https://paperswithcode.com/paper/learning-to-reconstruct-and-understand-indoor
Repo
Framework

Tell-the-difference: Fine-grained Visual Descriptor via a Discriminating Referee


Title	Tell-the-difference: Fine-grained Visual Descriptor via a Discriminating Referee
Authors	Shuangjie Xu, Feng Xu, Yu Cheng, Pan Zhou
Abstract	In this paper, we investigate a novel problem of telling the difference between image pairs in natural language. Compared to previous approaches for single image captioning, it is challenging to fetch linguistic representation from two independent visual information. To this end, we have proposed an effective encoder-decoder caption framework based on Hyper Convolution Net. In addition, a series of novel feature fusing techniques for pairwise visual information fusing are introduced and a discriminating referee is proposed to evaluate the pipeline. Because of the lack of appropriate datasets to support this task, we have collected and annotated a large new dataset with Amazon Mechanical Turk (AMT) for generating captions in a pairwise manner (with 14764 images and 26710 image pairs in total). The dataset is the first one on the relative difference caption task that provides descriptions in free language. We evaluate the effectiveness of our model on two datasets in the field and it outperforms the state-of-the-art approach by a large margin.
Tasks	Image Captioning
Published	2019-10-14
URL	https://arxiv.org/abs/1910.06426v1
PDF	https://arxiv.org/pdf/1910.06426v1.pdf
PWC	https://paperswithcode.com/paper/tell-the-difference-fine-grained-visual
Repo
Framework

Automated Multidisciplinary Design and Control of Hopping Robots for Exploration of Extreme Environments on the Moon and Mars


Title	Automated Multidisciplinary Design and Control of Hopping Robots for Exploration of Extreme Environments on the Moon and Mars
Authors	Himangshu Kalita, Jekan Thangavelautham
Abstract	The next frontier in solar system exploration will be missions targeting extreme and rugged environments such as caves, canyons, cliffs and crater rims of the Moon, Mars and icy moons. These environments are time capsules into early formation of the solar system and will provide vital clues of how our early solar system gave way to the current planets and moons. These sites will also provide vital clues to the past and present habitability of these environments. Current landers and rovers are unable to access these areas of high interest due to limitations in precision landing techniques, need for large and sophisticated science instruments and a mission assurance and operations culture where risks are minimized at all costs. Our past work has shown the advantages of using multiple spherical hopping robots called SphereX for exploring these extreme environments. Our previous work was based on performing exploration with a human-designed baseline design of a SphereX robot. However, the design of SphereX is a complex task that involves a large number of design variables and multiple engineering disciplines. In this work we propose to use Automated Multidisciplinary Design and Control Optimization (AMDCO) techniques to find near optimal design solutions in terms of mass, volume, power, and control for SphereX for different mission scenarios.
Tasks
Published	2019-10-09
URL	https://arxiv.org/abs/1910.03827v1
PDF	https://arxiv.org/pdf/1910.03827v1.pdf
PWC	https://paperswithcode.com/paper/automated-multidisciplinary-design-and
Repo
Framework

Adversarial Attacks in Sound Event Classification


Title	Adversarial Attacks in Sound Event Classification
Authors	Vinod Subramanian, Emmanouil Benetos, Ning Xu, SKoT McDonald, Mark Sandler
Abstract	Adversarial attacks refer to a set of methods that perturb the input to a classification model in order to fool the classifier. In this paper we apply different gradient based adversarial attack algorithms on five deep learning models trained for sound event classification. Four of the models use mel-spectrogram input and one model uses raw audio input. The models represent standard architectures such as convolutional, recurrent and dense networks. The dataset used for training is the Freesound dataset released for task 2 of the DCASE 2018 challenge and the models used are from participants of the challenge who open sourced their code. Our experiments show that adversarial attacks can be generated with high confidence and low perturbation. In addition, we show that the adversarial attacks are very effective across the different models.
Tasks	Adversarial Attack
Published	2019-07-04
URL	https://arxiv.org/abs/1907.02477v2
PDF	https://arxiv.org/pdf/1907.02477v2.pdf
PWC	https://paperswithcode.com/paper/adversarial-attacks-in-sound-event
Repo
Framework

Weakly Supervised Segmentation by A Deep Geodesic Prior


Title	Weakly Supervised Segmentation by A Deep Geodesic Prior
Authors	Aliasghar Mortazi, Naji Khosravan, Drew A. Torigian, Sila Kurugol, Ulas Bagci
Abstract	The performance of the state-of-the-art image segmentation methods heavily relies on the high-quality annotations, which are not easily affordable, particularly for medical data. To alleviate this limitation, in this study, we propose a weakly supervised image segmentation method based on a deep geodesic prior. We hypothesize that integration of this prior information can reduce the adverse effects of weak labels in segmentation accuracy. Our proposed algorithm is based on a prior information, extracted from an auto-encoder, trained to map objects geodesic maps to their corresponding binary maps. The obtained information is then used as an extra term in the loss function of the segmentor. In order to show efficacy of the proposed strategy, we have experimented segmentation of cardiac substructures with clean and two levels of noisy labels (L1, L2). Our experiments showed that the proposed algorithm boosted the performance of baseline deep learning-based segmentation for both clean and noisy labels by 4.4%, 4.6%(L1), and 6.3%(L2) in dice score, respectively. We also showed that the proposed method was more robust in the presence of high-level noise due to the existence of shape priors.
Tasks	Semantic Segmentation
Published	2019-08-18
URL	https://arxiv.org/abs/1908.06498v1
PDF	https://arxiv.org/pdf/1908.06498v1.pdf
PWC	https://paperswithcode.com/paper/weakly-supervised-segmentation-by-a-deep
Repo
Framework

STYLE-ANALYZER: fixing code style inconsistencies with interpretable unsupervised algorithms


Title	STYLE-ANALYZER: fixing code style inconsistencies with interpretable unsupervised algorithms
Authors	Vadim Markovtsev, Waren Long, Hugo Mougard, Konstantin Slavnov, Egor Bulychev
Abstract	Source code reviews are manual, time-consuming, and expensive. Human involvement should be focused on analyzing the most relevant aspects of the program, such as logic and maintainability, rather than amending style, syntax, or formatting defects. Some tools with linting capabilities can format code automatically and report various stylistic violations for supported programming languages. They are based on rules written by domain experts, hence, their configuration is often tedious, and it is impractical for the given set of rules to cover all possible corner cases. Some machine learning-based solutions exist, but they remain uninterpretable black boxes. This paper introduces STYLE-ANALYZER, a new open source tool to automatically fix code formatting violations using the decision tree forest model which adapts to each codebase and is fully unsupervised. STYLE-ANALYZER is built on top of our novel assisted code review framework, Lookout. It accurately mines the formatting style of each analyzed Git repository and expresses the found format patterns with compact human-readable rules. STYLE-ANALYZER can then suggest style inconsistency fixes in the form of code review comments. We evaluate the output quality and practical relevance of STYLE-ANALYZER by demonstrating that it can reproduce the original style with high precision, measured on 19 popular JavaScript projects, and by showing that it yields promising results in fixing real style mistakes. STYLE-ANALYZER includes a web application to visualize how the rules are triggered. We release STYLE-ANALYZER as a reusable and extendable open source software package on GitHub for the benefit of the community.
Tasks
Published	2019-04-01
URL	http://arxiv.org/abs/1904.00935v1
PDF	http://arxiv.org/pdf/1904.00935v1.pdf
PWC	https://paperswithcode.com/paper/style-analyzer-fixing-code-style
Repo
Framework

Deep Mesh Reconstruction from Single RGB Images via Topology Modification Networks


Title	Deep Mesh Reconstruction from Single RGB Images via Topology Modification Networks
Authors	Junyi Pan, Xiaoguang Han, Weikai Chen, Jiapeng Tang, Kui Jia
Abstract	Reconstructing the 3D mesh of a general object from a single image is now possible thanks to the latest advances of deep learning technologies. However, due to the nontrivial difficulty of generating a feasible mesh structure, the state-of-the-art approaches often simplify the problem by learning the displacements of a template mesh that deforms it to the target surface. Though reconstructing a 3D shape with complex topology can be achieved by deforming multiple mesh patches, it remains difficult to stitch the results to ensure a high meshing quality. In this paper, we present an end-to-end single-view mesh reconstruction framework that is able to generate high-quality meshes with complex topologies from a single genus-0 template mesh. The key to our approach is a novel progressive shaping framework that alternates between mesh deformation and topology modification. While a deformation network predicts the per-vertex translations that reduce the gap between the reconstructed mesh and the ground truth, a novel topology modification network is employed to prune the error-prone faces, enabling the evolution of topology. By iterating over the two procedures, one can progressively modify the mesh topology while achieving higher reconstruction accuracy. Moreover, a boundary refinement network is designed to refine the boundary conditions to further improve the visual quality of the reconstructed mesh. Extensive experiments demonstrate that our approach outperforms the current state-of-the-art methods both qualitatively and quantitatively, especially for the shapes with complex topologies.
Tasks
Published	2019-09-01
URL	https://arxiv.org/abs/1909.00321v1
PDF	https://arxiv.org/pdf/1909.00321v1.pdf
PWC	https://paperswithcode.com/paper/deep-mesh-reconstruction-from-single-rgb
Repo
Framework

Estimating regression errors without ground truth values


Title	Estimating regression errors without ground truth values
Authors	Henri Tiittanen, Emilia Oikarinen, Andreas Henelius, Kai Puolamäki
Abstract	Regression analysis is a standard supervised machine learning method used to model an outcome variable in terms of a set of predictor variables. In most real-world applications we do not know the true value of the outcome variable being predicted outside the training data, i.e., the ground truth is unknown. It is hence not straightforward to directly observe when the estimate from a model potentially is wrong, due to phenomena such as overfitting and concept drift. In this paper we present an efficient framework for estimating the generalization error of regression functions, applicable to any family of regression functions when the ground truth is unknown. We present a theoretical derivation of the framework and empirically evaluate its strengths and limitations. We find that it performs robustly and is useful for detecting concept drift in datasets in several real-world domains.
Tasks
Published	2019-10-09
URL	https://arxiv.org/abs/1910.04069v1
PDF	https://arxiv.org/pdf/1910.04069v1.pdf
PWC	https://paperswithcode.com/paper/estimating-regression-errors-without-ground
Repo
Framework

Improving Universal Sound Separation Using Sound Classification


Title	Improving Universal Sound Separation Using Sound Classification
Authors	Efthymios Tzinis, Scott Wisdom, John R. Hershey, Aren Jansen, Daniel P. W. Ellis
Abstract	Deep learning approaches have recently achieved impressive performance on both audio source separation and sound classification. Most audio source separation approaches focus only on separating sources belonging to a restricted domain of source classes, such as speech and music. However, recent work has demonstrated the possibility of “universal sound separation”, which aims to separate acoustic sources from an open domain, regardless of their class. In this paper, we utilize the semantic information learned by sound classifier networks trained on a vast amount of diverse sounds to improve universal sound separation. In particular, we show that semantic embeddings extracted from a sound classifier can be used to condition a separation network, providing it with useful additional information. This approach is especially useful in an iterative setup, where source estimates from an initial separation stage and their corresponding classifier-derived embeddings are fed to a second separation network. By performing a thorough hyperparameter search consisting of over a thousand experiments, we find that classifier embeddings from clean sources provide nearly one dB of SNR gain, and our best iterative models achieve a significant fraction of this oracle performance, establishing a new state-of-the-art for universal sound separation.
Tasks
Published	2019-11-18
URL	https://arxiv.org/abs/1911.07951v1
PDF	https://arxiv.org/pdf/1911.07951v1.pdf
PWC	https://paperswithcode.com/paper/improving-universal-sound-separation-using
Repo
Framework

Causal bootstrapping


Title	Causal bootstrapping
Authors	Max A. Little, Reham Badawy
Abstract	To draw scientifically meaningful conclusions and build reliable models of quantitative phenomena, cause and effect must be taken into consideration (either implicitly or explicitly). This is particularly challenging when the measurements are not from controlled experimental (interventional) settings, since cause and effect can be obscured by spurious, indirect influences. Modern predictive techniques from machine learning are capable of capturing high-dimensional, nonlinear relationships between variables while relying on few parametric or probabilistic model assumptions. However, since these techniques are associational, applied to observational data they are prone to picking up spurious influences from non-experimental (observational) data, making their predictions unreliable. Techniques from causal inference, such as probabilistic causal diagrams and do-calculus, provide powerful (nonparametric) tools for drawing causal inferences from such observational data. However, these techniques are often incompatible with modern, nonparametric machine learning algorithms since they typically require explicit probabilistic models. Here, we develop causal bootstrapping for augmenting classical nonparametric bootstrap resampling with information on the causal relationship between variables. This makes it possible to resample observational data such that, if it is possible to identify an interventional relationship from that data, new data representing that relationship can be simulated from the original observational data. In this way, we can use modern machine learning algorithms unaltered to make statistically powerful, yet causally-robust, predictions. We develop several causal bootstrapping algorithms for drawing interventional inferences from observational data, for classification and regression problems, and demonstrate, using synthetic and real-world examples, the value of this approach.
Tasks	Causal Inference
Published	2019-10-21
URL	https://arxiv.org/abs/1910.09648v2
PDF	https://arxiv.org/pdf/1910.09648v2.pdf
PWC	https://paperswithcode.com/paper/causal-bootstrapping
Repo
Framework


Title	Repositioning Bikes with Carrier Vehicles and Bike Trailers in Bike Sharing Systems
Authors	Xinghua Zheng, Ming Tang, Hankz Hankui Zhuo, Kevin X. Wen
Abstract	Bike Sharing Systems (BSSs) have been adopted in many major cities of the world due to traffic congestion and carbon emissions. Although there have been approaches to exploiting either bike trailers via crowdsourcing or carrier vehicles to reposition bikes in the `right'' stations in the` right’’ time, they do not jointly consider the usage of both bike trailers and carrier vehicles. In this paper, we aim to take advantage of both bike trailers and carrier vehicles to reduce the loss of demand with regard to the crowdsourcing of bike trailers and the fuel cost of carrier vehicles. In the experiment, we exhibit that our approach outperforms baselines in several datasets from bike sharing companies.
Tasks
Published	2019-09-20
URL	https://arxiv.org/abs/1909.09616v1
PDF	https://arxiv.org/pdf/1909.09616v1.pdf
PWC	https://paperswithcode.com/paper/repositioning-bikes-with-carrier-vehicles-and
Repo
Framework

Self-Ensembling with GAN-based Data Augmentation for Domain Adaptation in Semantic Segmentation


Title	Self-Ensembling with GAN-based Data Augmentation for Domain Adaptation in Semantic Segmentation
Authors	Jaehoon Choi, Taekyung Kim, Changick Kim
Abstract	Deep learning-based semantic segmentation methods have an intrinsic limitation that training a model requires a large amount of data with pixel-level annotations. To address this challenging issue, many researchers give attention to unsupervised domain adaptation for semantic segmentation. Unsupervised domain adaptation seeks to adapt the model trained on the source domain to the target domain. In this paper, we introduce a self-ensembling technique, one of the successful methods for domain adaptation in classification. However, applying self-ensembling to semantic segmentation is very difficult because heavily-tuned manual data augmentation used in self-ensembling is not useful to reduce the large domain gap in the semantic segmentation. To overcome this limitation, we propose a novel framework consisting of two components, which are complementary to each other. First, we present a data augmentation method based on Generative Adversarial Networks (GANs), which is computationally efficient and effective to facilitate domain alignment. Given those augmented images, we apply self-ensembling to enhance the performance of the segmentation network on the target domain. The proposed method outperforms state-of-the-art semantic segmentation methods on unsupervised domain adaptation benchmarks.
Tasks	Data Augmentation, Domain Adaptation, Semantic Segmentation, Unsupervised Domain Adaptation
Published	2019-09-02
URL	https://arxiv.org/abs/1909.00589v1
PDF	https://arxiv.org/pdf/1909.00589v1.pdf
PWC	https://paperswithcode.com/paper/self-ensembling-with-gan-based-data
Repo
Framework