April 2, 2020

3293 words 16 mins read

Paper Group ANR 95

A Critical Look at the Applicability of Markov Logic Networks for Music Signal Analysis. Machine Learning in Thermodynamics: Prediction of Activity Coefficients by Matrix Completion. Semantic Change Pattern Analysis. Toward fast and accurate human pose estimation via soft-gated skip connections. Fast local linear regression with anchor regularizati …

A Critical Look at the Applicability of Markov Logic Networks for Music Signal Analysis


Title	A Critical Look at the Applicability of Markov Logic Networks for Music Signal Analysis
Authors	Johan Pauwels, György Fazekas, Mark B. Sandler
Abstract	In recent years, Markov logic networks (MLNs) have been proposed as a potentially useful paradigm for music signal analysis. Because all hidden Markov models can be reformulated as MLNs, the latter can provide an all-encompassing framework that reuses and extends previous work in the field. However, just because it is theoretically possible to reformulate previous work as MLNs, does not mean that it is advantageous. In this paper, we analyse some proposed examples of MLNs for musical analysis and consider their practical disadvantages when compared to formulating the same musical dependence relationships as (dynamic) Bayesian networks. We argue that a number of practical hurdles such as the lack of support for sequences and for arbitrary continuous probability distributions make MLNs less than ideal for the proposed musical applications, both in terms of easy of formulation and computational requirements due to their required inference algorithms. These conclusions are not specific to music, but apply to other fields as well, especially when sequential data with continuous observations is involved. Finally, we show that the ideas underlying the proposed examples can be expressed perfectly well in the more commonly used framework of (dynamic) Bayesian networks.
Tasks
Published	2020-01-16
URL	https://arxiv.org/abs/2001.06086v1
PDF	https://arxiv.org/pdf/2001.06086v1.pdf
PWC	https://paperswithcode.com/paper/a-critical-look-at-the-applicability-of
Repo
Framework

Machine Learning in Thermodynamics: Prediction of Activity Coefficients by Matrix Completion


Title	Machine Learning in Thermodynamics: Prediction of Activity Coefficients by Matrix Completion
Authors	Fabian Jirasek, Rodrigo A. S. Alves, Julie Damay, Robert A. Vandermeulen, Robert Bamler, Michael Bortz, Stephan Mandt, Marius Kloft, Hans Hasse
Abstract	Activity coefficients, which are a measure of the non-ideality of liquid mixtures, are a key property in chemical engineering with relevance to modeling chemical and phase equilibria as well as transport processes. Although experimental data on thousands of binary mixtures are available, prediction methods are needed to calculate the activity coefficients in many relevant mixtures that have not been explored to-date. In this report, we propose a probabilistic matrix factorization model for predicting the activity coefficients in arbitrary binary mixtures. Although no physical descriptors for the considered components were used, our method outperforms the state-of-the-art method that has been refined over three decades while requiring much less training effort. This opens perspectives to novel methods for predicting physico-chemical properties of binary mixtures with the potential to revolutionize modeling and simulation in chemical engineering.
Tasks	Matrix Completion
Published	2020-01-29
URL	https://arxiv.org/abs/2001.10675v1
PDF	https://arxiv.org/pdf/2001.10675v1.pdf
PWC	https://paperswithcode.com/paper/machine-learning-in-thermodynamics-prediction
Repo
Framework

Semantic Change Pattern Analysis


Title	Semantic Change Pattern Analysis
Authors	Wensheng Cheng, Yan Zhang, Xu Lei, Wen Yang, Guisong Xia
Abstract	Change detection is an important problem in vision field, especially for aerial images. However, most works focus on traditional change detection, i.e., where changes happen, without considering the change type information, i.e., what changes happen. Although a few works have tried to apply semantic information to traditional change detection, they either only give the label of emerging objects without taking the change type into consideration, or set some kinds of change subjectively without specifying semantic information. To make use of semantic information and analyze change types comprehensively, we propose a new task called semantic change pattern analysis for aerial images. Given a pair of co-registered aerial images, the task requires a result including both where and what changes happen. We then describe the metric adopted for the task, which is clean and interpretable. We further provide the first well-annotated aerial image dataset for this task. Extensive baseline experiments are conducted as reference for following works. The aim of this work is to explore high-level information based on change detection and facilitate the development of this field with the publicly available dataset.
Tasks
Published	2020-03-07
URL	https://arxiv.org/abs/2003.03492v1
PDF	https://arxiv.org/pdf/2003.03492v1.pdf
PWC	https://paperswithcode.com/paper/semantic-change-pattern-analysis
Repo
Framework

Toward fast and accurate human pose estimation via soft-gated skip connections


Title	Toward fast and accurate human pose estimation via soft-gated skip connections
Authors	Adrian Bulat, Jean Kossaifi, Georgios Tzimiropoulos, Maja Pantic
Abstract	This paper is on highly accurate and highly efficient human pose estimation. Recent works based on Fully Convolutional Networks (FCNs) have demonstrated excellent results for this difficult problem. While residual connections within FCNs have proved to be quintessential for achieving high accuracy, we re-analyze this design choice in the context of improving both the accuracy and the efficiency over the state-of-the-art. In particular, we make the following contributions: (a) We propose gated skip connections with per-channel learnable parameters to control the data flow for each channel within the module within the macro-module. (b) We introduce a hybrid network that combines the HourGlass and U-Net architectures which minimizes the number of identity connections within the network and increases the performance for the same parameter budget. Our model achieves state-of-the-art results on the MPII and LSP datasets. In addition, with a reduction of 3x in model size and complexity, we show no decrease in performance when compared to the original HourGlass network.
Tasks	Pose Estimation
Published	2020-02-25
URL	https://arxiv.org/abs/2002.11098v1
PDF	https://arxiv.org/pdf/2002.11098v1.pdf
PWC	https://paperswithcode.com/paper/toward-fast-and-accurate-human-pose
Repo
Framework

Fast local linear regression with anchor regularization


Title	Fast local linear regression with anchor regularization
Authors	Mathis Petrovich, Makoto Yamada
Abstract	Regression is an important task in machine learning and data mining. It has several applications in various domains, including finance, biomedical, and computer vision. Recently, network Lasso, which estimates local models by making clusters using the network information, was proposed and its superior performance was demonstrated. In this study, we propose a simple yet effective local model training algorithm called the fast anchor regularized local linear method (FALL). More specifically, we train a local model for each sample by regularizing it with precomputed anchor models. The key advantage of the proposed algorithm is that we can obtain a closed-form solution with only matrix multiplication; additionally, the proposed algorithm is easily interpretable, fast to compute and parallelizable. Through experiments on synthetic and real-world datasets, we demonstrate that FALL compares favorably in terms of accuracy with the state-of-the-art network Lasso algorithm with significantly smaller training time (two orders of magnitude).
Tasks
Published	2020-02-21
URL	https://arxiv.org/abs/2003.05747v1
PDF	https://arxiv.org/pdf/2003.05747v1.pdf
PWC	https://paperswithcode.com/paper/fast-local-linear-regression-with-anchor
Repo
Framework

Data Set Description: Identifying the Physics Behind an Electric Motor – Data-Driven Learning of the Electrical Behavior (Part II)


Title	Data Set Description: Identifying the Physics Behind an Electric Motor – Data-Driven Learning of the Electrical Behavior (Part II)
Authors	Sören Hanke, Oliver Wallscheid, Joachim Böcker
Abstract	A data set was recorded to evaluate different methods for extracting mathematical models for a three-phase permanent magnet synchronous motor (PMSM) and a two-level IGBT inverter from measurement data. It consists of approximately 40 million multidimensional samples from a defined operating range of the drive. This document describes how to use the published data set \cite{Dataset} and how to extract models using introductory examples. The examples are based on known ordinary differential equations, the least squares method or on (deep) machine learning methods. The extracted models are used for the prediction of system states in a model predictive control (MPC) environment of the drive. In case of model deviations, the performance utilizing MPC remains below its potential. This is the case for state-of-the-art white-box models that are based only on nominal drive parameters and are valid in only limited operation regions. Moreover, many parasitic effects (e.g. from the feeding inverter) are normally not covered in white-box models. In order to achieve a high control performance, it is necessary to use models that cover the motor behavior in all operating points sufficiently well.
Tasks
Published	2020-03-13
URL	https://arxiv.org/abs/2003.06268v3
PDF	https://arxiv.org/pdf/2003.06268v3.pdf
PWC	https://paperswithcode.com/paper/data-set-description-identifying-the-physics
Repo
Framework

UniPose: Unified Human Pose Estimation in Single Images and Videos


Title	UniPose: Unified Human Pose Estimation in Single Images and Videos
Authors	Bruno Artacho, Andreas Savakis
Abstract	We propose UniPose, a unified framework for human pose estimation, based on our “Waterfall” Atrous Spatial Pooling architecture, that achieves state-of-art-results on several pose estimation metrics. Current pose estimation methods utilizing standard CNN architectures heavily rely on statistical postprocessing or predefined anchor poses for joint localization. UniPose incorporates contextual segmentation and joint localization to estimate the human pose in a single stage, with high accuracy, without relying on statistical postprocessing methods. The Waterfall module in UniPose leverages the efficiency of progressive filtering in the cascade architecture, while maintaining multi-scale fields-of-view comparable to spatial pyramid configurations. Additionally, our method is extended to UniPose-LSTM for multi-frame processing and achieves state-of-the-art results for temporal pose estimation in Video. Our results on multiple datasets demonstrate that UniPose, with a ResNet backbone and Waterfall module, is a robust and efficient architecture for pose estimation obtaining state-of-the-art results in single person pose detection for both single images and videos.
Tasks	Pose Estimation, Skeleton Based Action Recognition
Published	2020-01-22
URL	https://arxiv.org/abs/2001.08095v1
PDF	https://arxiv.org/pdf/2001.08095v1.pdf
PWC	https://paperswithcode.com/paper/unipose-unified-human-pose-estimation-in
Repo
Framework

Latent Embedding Feedback and Discriminative Features for Zero-Shot Classification


Title	Latent Embedding Feedback and Discriminative Features for Zero-Shot Classification
Authors	Sanath Narayan, Akshita Gupta, Fahad Shahbaz Khan, Cees G. M. Snoek, Ling Shao
Abstract	Zero-shot learning strives to classify unseen categories for which no data is available during training. In the generalized variant, the test samples can further belong to seen or unseen categories. The state-of-the-art relies on Generative Adversarial Networks that synthesize unseen class features by leveraging class-specific semantic embeddings. During training, they generate semantically consistent features, but discard this constraint during feature synthesis and classification. We propose to enforce semantic consistency at all stages of (generalized) zero-shot learning: training, feature synthesis and classification. We further introduce a feedback loop, from a semantic embedding decoder, that iteratively refines the generated features during both the training and feature synthesis stages. The synthesized features together with their corresponding latent embeddings from the decoder are transformed into discriminative features and utilized during classification to reduce ambiguities among categories. Experiments on (generalized) zero-shot learning for object and action classification reveal the benefit of semantic consistency and iterative feedback for GAN-based networks, outperforming existing methods on six zero-shot learning benchmarks.
Tasks	Action Classification, Zero-Shot Learning
Published	2020-03-17
URL	https://arxiv.org/abs/2003.07833v1
PDF	https://arxiv.org/pdf/2003.07833v1.pdf
PWC	https://paperswithcode.com/paper/latent-embedding-feedback-and-discriminative
Repo
Framework

Implementations in Machine Ethics: A Survey


Title	Implementations in Machine Ethics: A Survey
Authors	Suzanne Tolmeijer, Markus Kneer, Cristina Sarasua, Markus Christen, Abraham Bernstein
Abstract	Increasingly complex and autonomous systems require machine ethics to maximize the benefits and minimize the risks to society arising from the new technology. It is challenging to decide which type of ethical theory to employ and how to implement it effectively. This survey provides a threefold contribution. Firstly, it introduces a taxonomy to analyze the field of machine ethics from an ethical, implementational, and technical perspective. Secondly, an exhaustive selection and description of relevant works is presented. Thirdly, applying the new taxonomy to the selected works, dominant research patterns and lessons for the field are identified, and future directions for research are suggested.
Tasks
Published	2020-01-21
URL	https://arxiv.org/abs/2001.07573v1
PDF	https://arxiv.org/pdf/2001.07573v1.pdf
PWC	https://paperswithcode.com/paper/implementations-in-machine-ethics-a-survey
Repo
Framework

Weakly Supervised Dataset Collection for Robust Person Detection


Title	Weakly Supervised Dataset Collection for Robust Person Detection
Authors	Munetaka Minoguchi, Ken Okayama, Yutaka Satoh, Hirokatsu Kataoka
Abstract	To construct an algorithm that can provide robust person detection, we present a dataset with over 8 million images that was produced in a weakly supervised manner. Through labor-intensive human annotation, the person detection research community has produced relatively small datasets containing on the order of 100,000 images, such as the EuroCity Persons dataset, which includes 240,000 bounding boxes. Therefore, we have collected 8.7 million images of persons based on a two-step collection process, namely person detection with an existing detector and data refinement for false positive suppression. According to the experimental results, the Weakly Supervised Person Dataset (WSPD) is simple yet effective for person detection pre-training. In the context of pre-trained person detection algorithms, our WSPD pre-trained model has 13.38 and 6.38% better accuracy than the same model trained on the fully supervised ImageNet and EuroCity Persons datasets, respectively, when verified with the Caltech Pedestrian.
Tasks	Human Detection
Published	2020-03-27
URL	https://arxiv.org/abs/2003.12263v1
PDF	https://arxiv.org/pdf/2003.12263v1.pdf
PWC	https://paperswithcode.com/paper/weakly-supervised-dataset-collection-for
Repo
Framework

Detect and Correct Bias in Multi-Site Neuroimaging Datasets


Title	Detect and Correct Bias in Multi-Site Neuroimaging Datasets
Authors	Christian Wachinger, Anna Rieckmann, Sebastian Pölsterl
Abstract	The desire to train complex machine learning algorithms and to increase the statistical power in association studies drives neuroimaging research to use ever-larger datasets. The most obvious way to increase sample size is by pooling scans from independent studies. However, simple pooling is often ill-advised as selection, measurement, and confounding biases may creep in and yield spurious correlations. In this work, we combine 35,320 magnetic resonance images of the brain from 17 studies to examine bias in neuroimaging. In the first experiment, Name That Dataset, we provide empirical evidence for the presence of bias by showing that scans can be correctly assigned to their respective dataset with 71.5% accuracy. Given such evidence, we take a closer look at confounding bias, which is often viewed as the main shortcoming in observational studies. In practice, we neither know all potential confounders nor do we have data on them. Hence, we model confounders as unknown, latent variables. Kolmogorov complexity is then used to decide whether the confounded or the causal model provides the simplest factorization of the graphical model. Finally, we present methods for dataset harmonization and study their ability to remove bias in imaging features. In particular, we propose an extension of the recently introduced ComBat algorithm to control for global variation across image features, inspired by adjusting for population stratification in genetics. Our results demonstrate that harmonization can reduce dataset-specific information in image features. Further, confounding bias can be reduced and even turned into a causal relationship. However, harmonziation also requires caution as it can easily remove relevant subject-specific information.
Tasks
Published	2020-02-12
URL	https://arxiv.org/abs/2002.05049v1
PDF	https://arxiv.org/pdf/2002.05049v1.pdf
PWC	https://paperswithcode.com/paper/detect-and-correct-bias-in-multi-site
Repo
Framework

On the Need of Removing Last Releases of Data When Using or Validating Defect Prediction Models


Title	On the Need of Removing Last Releases of Data When Using or Validating Defect Prediction Models
Authors	Aalok Ahluwalia, Massimiliano Di Penta, Davide Falessi
Abstract	To develop and train defect prediction models, researchers rely on datasets in which a defect is attributed to an artifact, e.g., a class of a given release. However, the creation of such datasets is far from being perfect. It can happen that a defect is discovered several releases after its introduction: this phenomenon has been called “dormant defects”. This means that, if we observe today the status of a class in its current version, it can be considered as defect-free while this is not the case. We call “snoring” the noise consisting of such classes, affected by dormant defects only. We conjecture that the presence of snoring negatively impacts the classifiers’ accuracy and their evaluation. Moreover, earlier releases likely contain more snoring classes than older releases, thus, removing the most recent releases from a dataset could reduce the snoring effect and improve the accuracy of classifiers. In this paper we investigate the impact of the snoring noise on classifiers’ accuracy and their evaluation, and the effectiveness of a possible countermeasure consisting in removing the last releases of data. We analyze the accuracy of 15 machine learning defect prediction classifiers on data from more than 4,000 bugs and 600 releases of 19 open source projects from the Apache ecosystem. Our results show that, on average across projects: (i) the presence of snoring decreases the recall of defect prediction classifiers; (ii) evaluations affected by snoring are likely unable to identify the best classifiers, and (iii) removing data from recent releases helps to significantly improve the accuracy of the classifiers. On summary, this paper provides insights on how to create a software defect dataset by mitigating the effect of snoring.
Tasks
Published	2020-03-31
URL	https://arxiv.org/abs/2003.14376v1
PDF	https://arxiv.org/pdf/2003.14376v1.pdf
PWC	https://paperswithcode.com/paper/on-the-need-of-removing-last-releases-of-data
Repo
Framework

Crossing the Reality Gap with Evolved Plastic Neurocontrollers


Title	Crossing the Reality Gap with Evolved Plastic Neurocontrollers
Authors	Huanneng Qiu, Matthew Garratt, David Howard, Sreenatha Anavatti
Abstract	A critical issue in evolutionary robotics is the transfer of controllers learned in simulation to reality. This is especially the case for small Unmanned Aerial Vehicles (UAVs), as the platforms are highly dynamic and susceptible to breakage. Previous approaches often require simulation models with a high level of accuracy, otherwise significant errors may arise when the well-designed controller is being deployed onto the targeted platform. Here we try to overcome the transfer problem from a different perspective, by designing a spiking neurocontroller which uses synaptic plasticity to cross the reality gap via online adaptation. Through a set of experiments we show that the evolved plastic spiking controller can maintain its functionality by self-adapting to model changes that take place after evolutionary training, and consequently exhibit better performance than its non-plastic counterpart.
Tasks
Published	2020-02-23
URL	https://arxiv.org/abs/2002.09854v1
PDF	https://arxiv.org/pdf/2002.09854v1.pdf
PWC	https://paperswithcode.com/paper/crossing-the-reality-gap-with-evolved-plastic
Repo
Framework

DeepMAL – Deep Learning Models for Malware Traffic Detection and Classification


Title	DeepMAL – Deep Learning Models for Malware Traffic Detection and Classification
Authors	Gonzalo Marín, Pedro Casas, Germán Capdehourat
Abstract	Robust network security systems are essential to prevent and mitigate the harming effects of the ever-growing occurrence of network attacks. In recent years, machine learning-based systems have gain popularity for network security applications, usually considering the application of shallow models, which rely on the careful engineering of expert, handcrafted input features. The main limitation of this approach is that handcrafted features can fail to perform well under different scenarios and types of attacks. Deep Learning (DL) models can solve this limitation using their ability to learn feature representations from raw, non-processed data. In this paper we explore the power of DL models on the specific problem of detection and classification of malware network traffic. As a major advantage with respect to the state of the art, we consider raw measurements coming directly from the stream of monitored bytes as input to the proposed models, and evaluate different raw-traffic feature representations, including packet and flow-level ones. We introduce DeepMAL, a DL model which is able to capture the underlying statistics of malicious traffic, without any sort of expert handcrafted features. Using publicly available traffic traces containing different families of malware traffic, we show that DeepMAL can detect and classify malware flows with high accuracy, outperforming traditional, shallow-like models.
Tasks
Published	2020-03-03
URL	https://arxiv.org/abs/2003.04079v2
PDF	https://arxiv.org/pdf/2003.04079v2.pdf
PWC	https://paperswithcode.com/paper/deepmal-deep-learning-models-for-malware
Repo
Framework

StyleRig: Rigging StyleGAN for 3D Control over Portrait Images


Title	StyleRig: Rigging StyleGAN for 3D Control over Portrait Images
Authors	Ayush Tewari, Mohamed Elgharib, Gaurav Bharaj, Florian Bernard, Hans-Peter Seidel, Patrick Pérez, Michael Zollhöfer, Christian Theobalt
Abstract	StyleGAN generates photorealistic portrait images of faces with eyes, teeth, hair and context (neck, shoulders, background), but lacks a rig-like control over semantic face parameters that are interpretable in 3D, such as face pose, expressions, and scene illumination. Three-dimensional morphable face models (3DMMs) on the other hand offer control over the semantic parameters, but lack photorealism when rendered and only model the face interior, not other parts of a portrait image (hair, mouth interior, background). We present the first method to provide a face rig-like control over a pretrained and fixed StyleGAN via a 3DMM. A new rigging network, RigNet is trained between the 3DMM’s semantic parameters and StyleGAN’s input. The network is trained in a self-supervised manner, without the need for manual annotations. At test time, our method generates portrait images with the photorealism of StyleGAN and provides explicit control over the 3D semantic parameters of the face.
Tasks
Published	2020-03-31
URL	https://arxiv.org/abs/2004.00121v1
PDF	https://arxiv.org/pdf/2004.00121v1.pdf
PWC	https://paperswithcode.com/paper/stylerig-rigging-stylegan-for-3d-control-over
Repo
Framework