January 25, 2020

3193 words 15 mins read

Paper Group ANR 1618

Robust Variational Autoencoder. Catch Me If You Can. A Classification Methodology based on Subspace Graphs Learning. Using Orthophoto for Building Boundary Sharpening in the Digital Surface Model. InferPy: Probabilistic Modeling with Deep Neural Networks Made Easy. Learning to Generate Synthetic Data via Compositing. Constraint Satisfaction Propaga …

Robust Variational Autoencoder


Title	Robust Variational Autoencoder
Authors	Haleh Akrami, Anand A. Joshi, Jian Li, Sergul Aydore, Richard M. Leahy
Abstract	Machine learning methods often need a large amount of labeled training data. Since the training data is assumed to be the ground truth, outliers can severely degrade learned representations and performance of trained models. Here we apply concepts from robust statistics to derive a novel variational autoencoder that is robust to outliers in the training data. Variational autoencoders (VAEs) extract a lower-dimensional encoded feature representation from which we can generate new data samples. Robustness of autoencoders to outliers is critical for generating a reliable representation of particular data types in the encoded space when using corrupted training data. Our robust VAE is based on beta-divergence rather than the standard Kullback-Leibler (KL) divergence. Our proposed lower bound lead to a RVAE model that has the same computational complexity as the VAE and contains a single tuning parameter to control the degree of robustness. We demonstrate the performance of our $\beta$-divergence based autoencoder for a range of image datasets, showing improved robustness to outliers both qualitatively and quantitatively. We also illustrate the use of our robust VAE for outlier detection.
Tasks	Outlier Detection
Published	2019-05-23
URL	https://arxiv.org/abs/1905.09961v2
PDF	https://arxiv.org/pdf/1905.09961v2.pdf
PWC	https://paperswithcode.com/paper/robust-variational-autoencoder
Repo
Framework

Catch Me If You Can


Title	Catch Me If You Can
Authors	Antoine Viscardi, Casey Juanxi Li, Thomas Hollis
Abstract	As advances in signature recognition have reached a new plateau of performance at around 2% error rate, it is interesting to investigate alternative approaches. The approach detailed in this paper looks at using Variational Auto-Encoders (VAEs) to learn a latent space representation of genuine signatures. This is then used to pass unlabelled signatures such that only the genuine ones will successfully be reconstructed by the VAE. This latent space representation and the reconstruction loss is subsequently used by random forest and kNN classifiers for prediction. Subsequently, VAE disentanglement and the possibility of posterior collapse are ascertained and analysed. The final results suggest that while this method performs less well than existing alternatives, further work may allow this to be used as part of an ensemble for future models.
Tasks
Published	2019-04-18
URL	http://arxiv.org/abs/1904.12627v1
PDF	http://arxiv.org/pdf/1904.12627v1.pdf
PWC	https://paperswithcode.com/paper/190412627
Repo
Framework

A Classification Methodology based on Subspace Graphs Learning


Title	A Classification Methodology based on Subspace Graphs Learning
Authors	Riccardo La Grassa, Ignazio Gallo, Alessandro Calefati, Dimitri Ognibene
Abstract	In this paper, we propose a design methodology for one-class classifiers using an ensemble-of-classifiers approach. The objective is to select the best structures created during the training phase using an ensemble of spanning trees. It takes the best classifier, partitioning the area near a pattern into $\gamma^{\gamma-2}$ sub-spaces and combining all possible spanning trees that can be created starting from $\gamma$ nodes. The proposed method leverages on a supervised classification methodology and the concept of minimum distance. We evaluate our approach on well-known benchmark datasets and results obtained demonstrate that it achieves comparable and, in many cases, state-of-the-art results. Moreover, it obtains good performance even with unbalanced datasets.
Tasks
Published	2019-09-09
URL	https://arxiv.org/abs/1909.04078v1
PDF	https://arxiv.org/pdf/1909.04078v1.pdf
PWC	https://paperswithcode.com/paper/a-classification-methodology-based-on
Repo
Framework

Using Orthophoto for Building Boundary Sharpening in the Digital Surface Model


Title	Using Orthophoto for Building Boundary Sharpening in the Digital Surface Model
Authors	Xiaohu Lu, Rongjun Qin, Xu Huang
Abstract	Nowadays dense stereo matching has become one of the dominant tools in 3D reconstruction of urban regions for its low cost and high flexibility in generating dense 3D points. However, state-of-the-art stereo matching algorithms usually apply a semi-global matching (SGM) strategy. This strategy normally assumes the surface geometry pieceswise planar, where a smooth penalty is imposed to deal with non-texture or repeating-texture areas. This on one hand, generates much smooth surface models, while on the other hand, may partially leads to smoothing on depth discontinuities, particularly for fence-shaped regions or densely built areas with narrow streets. To solve this problem, in this work, we propose to use the line segment information extracted from the corresponding orthophoto as a pose-processing tool to sharpen the building boundary of the Digital Surface Model (DSM) generated by SGM. Two methods which are based on graph-cut and plane fitting are proposed and compared. Experimental results on several satellite datasets with ground truth show the robustness and effectiveness of the proposed DSM sharpening method.
Tasks	3D Reconstruction, Stereo Matching, Stereo Matching Hand
Published	2019-05-22
URL	https://arxiv.org/abs/1905.09150v1
PDF	https://arxiv.org/pdf/1905.09150v1.pdf
PWC	https://paperswithcode.com/paper/using-orthophoto-for-building-boundary
Repo
Framework

InferPy: Probabilistic Modeling with Deep Neural Networks Made Easy


Title	InferPy: Probabilistic Modeling with Deep Neural Networks Made Easy
Authors	Javier Cózar, Rafael Cabañas, Antonio Salmerón, Andrés R. Masegosa
Abstract	InferPy is a Python package for probabilistic modeling with deep neural networks. It defines a user-friendly API that trades-off model complexity with ease of use, unlike other libraries whose focus is on dealing with very general probabilistic models at the cost of having a more complex API. In particular, this package allows to define, learn and evaluate general hierarchical probabilistic models containing deep neural networks in a compact and simple way. InferPy is built on top of Tensorflow Probability and Keras.
Tasks
Published	2019-08-29
URL	https://arxiv.org/abs/1908.11161v4
PDF	https://arxiv.org/pdf/1908.11161v4.pdf
PWC	https://paperswithcode.com/paper/inferpy-probabilistic-modeling-with-deep
Repo
Framework

Learning to Generate Synthetic Data via Compositing


Title	Learning to Generate Synthetic Data via Compositing
Authors	Shashank Tripathi, Siddhartha Chandra, Amit Agrawal, Ambrish Tyagi, James M. Rehg, Visesh Chari
Abstract	We present a task-aware approach to synthetic data generation. Our framework employs a trainable synthesizer network that is optimized to produce meaningful training samples by assessing the strengths and weaknesses of a `target’ network. The synthesizer and target networks are trained in an adversarial manner wherein each network is updated with a goal to outdo the other. Additionally, we ensure the synthesizer generates realistic data by pairing it with a discriminator trained on real-world images. Further, to make the target classifier invariant to blending artefacts, we introduce these artefacts to background regions of the training images so the target does not over-fit to them. We demonstrate the efficacy of our approach by applying it to different target networks including a classification network on AffNIST, and two object detection networks (SSD, Faster-RCNN) on different datasets. On the AffNIST benchmark, our approach is able to surpass the baseline results with just half the training examples. On the VOC person detection benchmark, we show improvements of up to 2.7% as a result of our data augmentation. Similarly on the GMU detection benchmark, we report a performance boost of 3.5% in mAP over the baseline method, outperforming the previous state of the art approaches by up to 7.5% on specific categories. \|
Tasks	Data Augmentation, Human Detection, Object Detection, Synthetic Data Generation
Published	2019-04-10
URL	https://arxiv.org/abs/1904.05475v2
PDF	https://arxiv.org/pdf/1904.05475v2.pdf
PWC	https://paperswithcode.com/paper/learning-to-generate-synthetic-data-via
Repo
Framework

Constraint Satisfaction Propagation: Non-stationary Policy Synthesis for Temporal Logic Planning


Title	Constraint Satisfaction Propagation: Non-stationary Policy Synthesis for Temporal Logic Planning
Authors	Thomas J. Ringstrom, Paul R. Schrater
Abstract	Problems arise when using reward functions to capture dependencies between sequential time-constrained goal states because the state-space must be prohibitively expanded to accommodate a history of successfully achieved sub-goals. Also, policies and value functions derived with stationarity assumptions are not readily decomposable, leading to a tension between reward maximization and task generalization. We demonstrate a logic-compatible approach using model-based knowledge of environment dynamics and deadline information to directly infer non-stationary policies composed of reusable stationary policies. The policies are constructed to maximize the probability of satisfying time-sensitive goals while respecting time-varying obstacles. Our approach explicitly maintains two different spaces, a high-level logical task specification where the task-variables are grounded onto the low-level state-space of a Markov decision process. Computing satisfiability at the task-level is made possible by a Bellman-like equation which operates on a tensor that links the temporal relationship between the two spaces; the equation solves for a value function that can be explicitly interpreted as the probability of sub-goal satisfaction under the synthesized non-stationary policy, an approach we term Constraint Satisfaction Propagation (CSP).
Tasks
Published	2019-01-29
URL	http://arxiv.org/abs/1901.10405v3
PDF	http://arxiv.org/pdf/1901.10405v3.pdf
PWC	https://paperswithcode.com/paper/constraint-satisfaction-propagation-non
Repo
Framework

Anti-Money Laundering in Bitcoin: Experimenting with Graph Convolutional Networks for Financial Forensics


Title	Anti-Money Laundering in Bitcoin: Experimenting with Graph Convolutional Networks for Financial Forensics
Authors	Mark Weber, Giacomo Domeniconi, Jie Chen, Daniel Karl I. Weidele, Claudio Bellei, Tom Robinson, Charles E. Leiserson
Abstract	Anti-money laundering (AML) regulations play a critical role in safeguarding financial systems, but bear high costs for institutions and drive financial exclusion for those on the socioeconomic and international margins. The advent of cryptocurrency has introduced an intriguing paradox: pseudonymity allows criminals to hide in plain sight, but open data gives more power to investigators and enables the crowdsourcing of forensic analysis. Meanwhile advances in learning algorithms show great promise for the AML toolkit. In this workshop tutorial, we motivate the opportunity to reconcile the cause of safety with that of financial inclusion. We contribute the Elliptic Data Set, a time series graph of over 200K Bitcoin transactions (nodes), 234K directed payment flows (edges), and 166 node features, including ones based on non-public data; to our knowledge, this is the largest labelled transaction data set publicly available in any cryptocurrency. We share results from a binary classification task predicting illicit transactions using variations of Logistic Regression (LR), Random Forest (RF), Multilayer Perceptrons (MLP), and Graph Convolutional Networks (GCN), with GCN being of special interest as an emergent new method for capturing relational information. The results show the superiority of Random Forest (RF), but also invite algorithmic work to combine the respective powers of RF and graph methods. Lastly, we consider visualization for analysis and explainability, which is difficult given the size and dynamism of real-world transaction graphs, and we offer a simple prototype capable of navigating the graph and observing model performance on illicit activity over time. With this tutorial and data set, we hope to a) invite feedback in support of our ongoing inquiry, and b) inspire others to work on this societally important challenge.
Tasks	Time Series
Published	2019-07-31
URL	https://arxiv.org/abs/1908.02591v1
PDF	https://arxiv.org/pdf/1908.02591v1.pdf
PWC	https://paperswithcode.com/paper/anti-money-laundering-in-bitcoin
Repo
Framework

Emotion Recognition Using Fusion of Audio and Video Features


Title	Emotion Recognition Using Fusion of Audio and Video Features
Authors	Juan D. S. Ortega, Patrick Cardinal, Alessandro L. Koerich
Abstract	In this paper we propose a fusion approach to continuous emotion recognition that combines visual and auditory modalities in their representation spaces to predict the arousal and valence levels. The proposed approach employs a pre-trained convolution neural network and transfer learning to extract features from video frames that capture the emotional content. For the auditory content, a minimalistic set of parameters such as prosodic, excitation, vocal tract, and spectral descriptors are used as features. The fusion of these two modalities is carried out at a feature level, before training a single support vector regressor (SVR) or at a prediction level, after training one SVR for each modality. The proposed approach also includes preprocessing and post-processing techniques which contribute favorably to improving the concordance correlation coefficient (CCC). Experimental results for predicting spontaneous and natural emotions on the RECOLA dataset have shown that the proposed approach takes advantage of the complementary information of visual and auditory modalities and provides CCCs of 0.749 and 0.565 for arousal and valence, respectively.
Tasks	Emotion Recognition, Transfer Learning
Published	2019-06-25
URL	https://arxiv.org/abs/1906.10623v1
PDF	https://arxiv.org/pdf/1906.10623v1.pdf
PWC	https://paperswithcode.com/paper/emotion-recognition-using-fusion-of-audio-and
Repo
Framework

FACSIMILE: Fast and Accurate Scans From an Image in Less Than a Second


Title	FACSIMILE: Fast and Accurate Scans From an Image in Less Than a Second
Authors	David Smith, Matthew Loper, Xiaochen Hu, Paris Mavroidis, Javier Romero
Abstract	Current methods for body shape estimation either lack detail or require many images. They are usually architecturally complex and computationally expensive. We propose FACSIMILE (FAX), a method that estimates a detailed body from a single photo, lowering the bar for creating virtual representations of humans. Our approach is easy to implement and fast to execute, making it easily deployable. FAX uses an image-translation network which recovers geometry at the original resolution of the image. Counterintuitively, the main loss which drives FAX is on per-pixel surface normals instead of per-pixel depth, making it possible to estimate detailed body geometry without any depth supervision. We evaluate our approach both qualitatively and quantitatively, and compare with a state-of-the-art method.
Tasks
Published	2019-09-02
URL	https://arxiv.org/abs/1909.00883v1
PDF	https://arxiv.org/pdf/1909.00883v1.pdf
PWC	https://paperswithcode.com/paper/facsimile-fast-and-accurate-scans-from-an
Repo
Framework

Unsupervised machine learning to analyse city logistics through Twitter


Title	Unsupervised machine learning to analyse city logistics through Twitter
Authors	Simon Tamayo, François Combes, Gaudron Arthur
Abstract	City Logistics is characterized by multiple stakeholders that often have different views of such a complex system. From a public policy perspective, identifying stakeholders, issues and trends is a daunting challenge, only partially addressed by traditional observation systems. Nowadays, social media is one of the biggest channels of public expression and is often used to communicate opinions and content related to City Logistics. The idea of this research is that analysing social media content could help in understanding the public perception of City logistics. This paper offers a methodology for collecting content from Twitter and implementing Machine Learning techniques (Unsupervised Learning and Natural Language Processing), to perform content and sentiment analysis. The proposed methodology is applied to more than 110 000 tweets containing City Logistics key-terms. Results allowed the building of an Interest Map of concepts and a Sentiment Analysis to determine if City Logistics entries are positive, negative or neutral.
Tasks	Sentiment Analysis
Published	2019-06-18
URL	https://arxiv.org/abs/1906.07529v1
PDF	https://arxiv.org/pdf/1906.07529v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-machine-learning-to-analyse-city
Repo
Framework

Prediction-based Resource Allocation using Bayesian Neural Networks and Minimum Cost and Maximum Flow Algorithm


Title	Prediction-based Resource Allocation using Bayesian Neural Networks and Minimum Cost and Maximum Flow Algorithm
Authors	Gyunam Park, Minseok Song
Abstract	Predictive business process monitoring aims at providing predictions about running instances by analyzing logs of completed cases in a business process. Recently, a lot of research focuses on increasing productivity and efficiency in a business process by forecasting potential problems during its executions. However, most of the studies lack suggesting concrete actions to improve the process. They leave it up to the subjective judgment of a user. In this paper, we propose a novel method to connect the results from predictive business process monitoring to actual business process improvements. More in detail, we optimize the resource allocation in a non-clairvoyant online environment, where we have limited information required for scheduling, by exploiting the predictions. The proposed method integrates the offline prediction model construction that predicts the processing time and the next activity of an ongoing instance using Bayesian Neural Networks (BNNs) with the online resource allocation that is extended from the minimum cost and maximum flow algorithm. To validate the proposed method, we performed experiments using an artificial event log and a real-life event log from a global financial organization.
Tasks
Published	2019-10-11
URL	https://arxiv.org/abs/1910.05126v1
PDF	https://arxiv.org/pdf/1910.05126v1.pdf
PWC	https://paperswithcode.com/paper/prediction-based-resource-allocation-using
Repo
Framework

Learning a Controller Fusion Network by Online Trajectory Filtering for Vision-based UAV Racing


Title	Learning a Controller Fusion Network by Online Trajectory Filtering for Vision-based UAV Racing
Authors	Matthias Müller, Guohao Li, Vincent Casser, Neil Smith, Dominik L. Michels, Bernard Ghanem
Abstract	Autonomous UAV racing has recently emerged as an interesting research problem. The dream is to beat humans in this new fast-paced sport. A common approach is to learn an end-to-end policy that directly predicts controls from raw images by imitating an expert. However, such a policy is limited by the expert it imitates and scaling to other environments and vehicle dynamics is difficult. One approach to overcome the drawbacks of an end-to-end policy is to train a network only on the perception task and handle control with a PID or MPC controller. However, a single controller must be extensively tuned and cannot usually cover the whole state space. In this paper, we propose learning an optimized controller using a DNN that fuses multiple controllers. The network learns a robust controller with online trajectory filtering, which suppresses noisy trajectories and imperfections of individual controllers. The result is a network that is able to learn a good fusion of filtered trajectories from different controllers leading to significant improvements in overall performance. We compare our trained network to controllers it has learned from, end-to-end baselines and human pilots in a realistic simulation; our network beats all baselines in extensive experiments and approaches the performance of a professional human pilot. A video summarizing this work is available at https://youtu.be/hGKlE5X9Z5U
Tasks
Published	2019-04-18
URL	http://arxiv.org/abs/1904.08801v1
PDF	http://arxiv.org/pdf/1904.08801v1.pdf
PWC	https://paperswithcode.com/paper/learning-a-controller-fusion-network-by
Repo
Framework

Belief revision and 3-valued logics: Characterization of 19,683 belief change operators


Title	Belief revision and 3-valued logics: Characterization of 19,683 belief change operators
Authors	Nerio Borges, Ramón Pino Pérez
Abstract	In most classical models of belief change, epistemic states are represented by theories (AGM) or formulas (Katsuno-Mendelzon) and the new pieces of information by formulas. The Representation Theorem for revision operators says that operators are represented by total preorders. This important representation is exploited by Darwiche and Pearl to shift the notion of epistemic state to a more abstract one, where the paradigm of epistemic state is indeed that of a total preorder over interpretations. In this work, we introduce a 3-valued logic where the formulas can be identified with a generalisation of total preorders of three levels: a ranking function mapping interpretations into the truth values. Then we analyse some sort of changes in this kind of structures and give syntactical characterizations of them.
Tasks
Published	2019-10-30
URL	https://arxiv.org/abs/1910.14138v1
PDF	https://arxiv.org/pdf/1910.14138v1.pdf
PWC	https://paperswithcode.com/paper/belief-revision-and-3-valued-logics
Repo
Framework

ActiveHARNet: Towards On-Device Deep Bayesian Active Learning for Human Activity Recognition


Title	ActiveHARNet: Towards On-Device Deep Bayesian Active Learning for Human Activity Recognition
Authors	Gautham Krishna Gudur, Prahalathan Sundaramoorthy, Venkatesh Umaashankar
Abstract	Various health-care applications such as assisted living, fall detection etc., require modeling of user behavior through Human Activity Recognition (HAR). HAR using mobile- and wearable-based deep learning algorithms have been on the rise owing to the advancements in pervasive computing. However, there are two other challenges that need to be addressed: first, the deep learning model should support on-device incremental training (model updation) from real-time incoming data points to learn user behavior over time, while also being resource-friendly; second, a suitable ground truthing technique (like Active Learning) should help establish labels on-the-fly while also selecting only the most informative data points to query from an oracle. Hence, in this paper, we propose ActiveHARNet, a resource-efficient deep ensembled model which supports on-device Incremental Learning and inference, with capabilities to represent model uncertainties through approximations in Bayesian Neural Networks using dropout. This is combined with suitable acquisition functions for active learning. Empirical results on two publicly available wrist-worn HAR and fall detection datasets indicate that ActiveHARNet achieves considerable efficiency boost during inference across different users, with a substantially low number of acquired pool points (at least 60% reduction) during incremental learning on both datasets experimented with various acquisition functions, thus demonstrating deployment and Incremental Learning feasibility.
Tasks	Active Learning, Activity Recognition, Human Activity Recognition
Published	2019-05-31
URL	https://arxiv.org/abs/1906.00108v1
PDF	https://arxiv.org/pdf/1906.00108v1.pdf
PWC	https://paperswithcode.com/paper/190600108
Repo
Framework