April 1, 2020

3225 words 16 mins read

Paper Group ANR 500

Online Guest Detection in a Smart Home using Pervasive Sensors and Probabilistic Reasoning. Connecting GANs and MFGs. AU-AIR: A Multi-modal Unmanned Aerial Vehicle Dataset for Low Altitude Traffic Surveillance. Synthesis of Brain Tumor MR Images for Learning Data Augmentation. Meta-Learning Initializations for Low-Resource Drug Discovery. Bridging …

Online Guest Detection in a Smart Home using Pervasive Sensors and Probabilistic Reasoning


Title	Online Guest Detection in a Smart Home using Pervasive Sensors and Probabilistic Reasoning
Authors	Jennifer Renoux, Uwe Köckemann, Amy Loutfi
Abstract	Smart home environments equipped with distributed sensor networks are capable of helping people by providing services related to health, emergency detection or daily routine management. A backbone to these systems relies often on the system’s ability to track and detect activities performed by the users in their home. Despite the continuous progress in the area of activity recognition in smart homes, many systems make a strong underlying assumption that the number of occupants in the home at any given moment of time is always known. Estimating the number of persons in a Smart Home at each time step remains a challenge nowadays. Indeed, unlike most (crowd) counting solution which are based on computer vision techniques, the sensors considered in a Smart Home are often very simple and do not offer individually a good overview of the situation. The data gathered needs therefore to be fused in order to infer useful information. This paper aims at addressing this challenge and presents a probabilistic approach able to estimate the number of persons in the environment at each time step. This approach works in two steps: first, an estimate of the number of persons present in the environment is done using a Constraint Satisfaction Problem solver, based on the topology of the sensor network and the sensor activation pattern at this time point. Then, a Hidden Markov Model refines this estimate by considering the uncertainty related to the sensors. Using both simulated and real data, our method has been tested and validated on two smart homes of different sizes and configuration and demonstrates the ability to accurately estimate the number of inhabitants.
Tasks	Activity Recognition, Crowd Counting
Published	2020-03-13
URL	https://arxiv.org/abs/2003.06347v1
PDF	https://arxiv.org/pdf/2003.06347v1.pdf
PWC	https://paperswithcode.com/paper/online-guest-detection-in-a-smart-home-using
Repo
Framework

Connecting GANs and MFGs


Title	Connecting GANs and MFGs
Authors	Haoyang Cao, Xin Guo, Mathieu Laurière
Abstract	Generative Adversarial Networks (GANs), introduced in 2014 [12], have celebrated great empirical success, especially in image generation and processing. Meanwhile, Mean-Field Games (MFGs), established in [17] and [16] as analytically feasible approximations for N-player games, have experienced rapid growth in theoretical studies. In this paper, we establish theoretical connections between GANs and MFGs. Interpreting MFGs as GANs, on one hand, allows us to devise GANs-based algorithm to solve MFGs. Interpreting GANs as MFGs, on the other hand, provides a new and probabilistic foundation for GANs. Moreover, this interpretation helps establish an analytical connection between GANs and Optimal Transport (OT) problems.
Tasks	Image Generation
Published	2020-02-10
URL	https://arxiv.org/abs/2002.04112v1
PDF	https://arxiv.org/pdf/2002.04112v1.pdf
PWC	https://paperswithcode.com/paper/connecting-gans-and-mfgs
Repo
Framework


Title	AU-AIR: A Multi-modal Unmanned Aerial Vehicle Dataset for Low Altitude Traffic Surveillance
Authors	Ilker Bozcan, Erdal Kayacan
Abstract	Unmanned aerial vehicles (UAVs) with mounted cameras have the advantage of capturing aerial (bird-view) images. The availability of aerial visual data and the recent advances in object detection algorithms led the computer vision community to focus on object detection tasks on aerial images. As a result of this, several aerial datasets have been introduced, including visual data with object annotations. UAVs are used solely as flying-cameras in these datasets, discarding different data types regarding the flight (e.g., time, location, internal sensors). In this work, we propose a multi-purpose aerial dataset (AU-AIR) that has multi-modal sensor data (i.e., visual, time, location, altitude, IMU, velocity) collected in real-world outdoor environments. The AU-AIR dataset includes meta-data for extracted frames (i.e., bounding box annotations for traffic-related object category) from recorded RGB videos. Moreover, we emphasize the differences between natural and aerial images in the context of object detection task. For this end, we train and test mobile object detectors (including YOLOv3-Tiny and MobileNetv2-SSDLite) on the AU-AIR dataset, which are applicable for real-time object detection using on-board computers with UAVs. Since our dataset has diversity in recorded data types, it contributes to filling the gap between computer vision and robotics. The dataset is available at https://bozcani.github.io/auairdataset.
Tasks	Object Detection, Real-Time Object Detection
Published	2020-01-31
URL	https://arxiv.org/abs/2001.11737v2
PDF	https://arxiv.org/pdf/2001.11737v2.pdf
PWC	https://paperswithcode.com/paper/au-air-a-multi-modal-unmanned-aerial-vehicle
Repo
Framework

Synthesis of Brain Tumor MR Images for Learning Data Augmentation


Title	Synthesis of Brain Tumor MR Images for Learning Data Augmentation
Authors	Sunho Kim, Byungjai Kim, HyunWook Park
Abstract	Medical image analysis using deep neural networks has been actively studied. Deep neural networks are trained by learning data. For accurate training of deep neural networks, the learning data should be sufficient, of good quality, and should have a generalized property. However, in medical images, it is difficult to acquire sufficient patient data because of the difficulty of patient recruitment, the burden of annotation of lesions by experts, and the invasion of patients’ privacy. In comparison, the medical images of healthy volunteers can be easily acquired. Using healthy brain images, the proposed method synthesizes multi-contrast magnetic resonance images of brain tumors. Because tumors have complex features, the proposed method simplifies them into concentric circles that are easily controllable. Then it converts the concentric circles into various realistic shapes of tumors through deep neural networks. Because numerous healthy brain images are easily available, our method can synthesize a huge number of the brain tumor images with various concentric circles. We performed qualitative and quantitative analysis to assess the usefulness of augmented data from the proposed method. Intuitive and interesting experimental results are available online at https://github.com/KSH0660/BrainTumor
Tasks	Data Augmentation
Published	2020-03-17
URL	https://arxiv.org/abs/2003.07526v1
PDF	https://arxiv.org/pdf/2003.07526v1.pdf
PWC	https://paperswithcode.com/paper/synthesis-of-brain-tumor-mr-images-for
Repo
Framework

Meta-Learning Initializations for Low-Resource Drug Discovery


Title	Meta-Learning Initializations for Low-Resource Drug Discovery
Authors	Cuong Q. Nguyen, Constantine Kreatsoulas, Kim M. Branson
Abstract	Building in silico models to predict chemical properties and activities is a crucial step in drug discovery. However, drug discovery projects are often characterized by limited labeled data, hindering the applications of deep learning in this setting. Meanwhile advances in meta-learning have enabled state-of-the-art performances in few-shot learning benchmarks, naturally prompting the question: Can meta-learning improve deep learning performance in low-resource drug discovery projects? In this work, we assess the efficiency of the Model-Agnostic Meta-Learning (MAML) algorithm - along with its variants FO-MAML and ANIL - at learning to predict chemical properties and activities. Using the ChEMBL20 dataset to emulate low-resource settings, our benchmark shows that meta-initializations perform comparably to or outperform multi-task pre-training baselines on 16 out of 20 in-distribution tasks and on all out-of-distribution tasks, providing an average improvement in AUPRC of 7.2% and 14.9% respectively. Finally, we observe that meta-initializations consistently result in the best performing models across fine-tuning sets with $k \in {16, 32, 64, 128, 256}$ instances.
Tasks	Drug Discovery, Few-Shot Learning, Meta-Learning
Published	2020-03-12
URL	https://arxiv.org/abs/2003.05996v1
PDF	https://arxiv.org/pdf/2003.05996v1.pdf
PWC	https://paperswithcode.com/paper/meta-learning-initializations-for-low
Repo
Framework

Bridging the Gap: Providing Post-Hoc Symbolic Explanations for Sequential Decision-Making Problems with Black Box Simulators


Title	Bridging the Gap: Providing Post-Hoc Symbolic Explanations for Sequential Decision-Making Problems with Black Box Simulators
Authors	Sarath Sreedharan, Utkash Soni, Mudit Verma, Siddharth Srivastava, Subbarao Kambhampati
Abstract	As more and more complex AI systems are introduced into our day-to-day lives, it becomes important that everyday users can work and interact with such systems with relative ease. Orchestrating such interactions require the system to be capable of providing explanations and rationale for its decisions and be able to field queries about alternative decisions. A significant hurdle to allowing for such explanatory dialogue could be the mismatch between the complex representations that the systems use to reason about the task and the terms in which the user may be viewing the task. This paper introduces methods that can be leveraged to provide contrastive explanations in terms of user-specified concepts for deterministic sequential decision-making settings where the system dynamics may be best represented in terms of black box simulators. We do this by assuming that system dynamics can at least be partly captured in terms of symbolic planning models, and we provide explanations in terms of these models. We implement this method using a simulator for a popular Atari game (Montezuma’s Revenge) and perform user studies to verify whether people would find explanations generated in this form useful.
Tasks	Decision Making, Montezuma’s Revenge
Published	2020-02-04
URL	https://arxiv.org/abs/2002.01080v1
PDF	https://arxiv.org/pdf/2002.01080v1.pdf
PWC	https://paperswithcode.com/paper/bridging-the-gap-providing-post-hoc-symbolic
Repo
Framework

P$^2$-GAN: Efficient Style Transfer Using Single Style Image


Title	P$^2$-GAN: Efficient Style Transfer Using Single Style Image
Authors	Zhentan Zheng, Jianyi Liu
Abstract	Style transfer is a useful image synthesis technique that can re-render given image into another artistic style while preserving its content information. Generative Adversarial Network (GAN) is a widely adopted framework toward this task for its better representation ability on local style patterns than the traditional Gram-matrix based methods. However, most previous methods rely on sufficient amount of pre-collected style images to train the model. In this paper, a novel Patch Permutation GAN (P$^2$-GAN) network that can efficiently learn the stroke style from a single style image is proposed. We use patch permutation to generate multiple training samples from the given style image. A patch discriminator that can simultaneously process patch-wise images and natural images seamlessly is designed. We also propose a local texture descriptor based criterion to quantitatively evaluate the style transfer quality. Experimental results showed that our method can produce finer quality re-renderings from single style image with improved computational efficiency compared with many state-of-the-arts methods.
Tasks	Image Generation, Style Transfer
Published	2020-01-21
URL	https://arxiv.org/abs/2001.07466v2
PDF	https://arxiv.org/pdf/2001.07466v2.pdf
PWC	https://paperswithcode.com/paper/p2-gan-efficient-style-transfer-using-single
Repo
Framework

Seismic horizon detection with neural networks


Title	Seismic horizon detection with neural networks
Authors	Alexander Koryagin, Darima Mylzenova, Roman Khudorozhkov, Sergey Tsimfer
Abstract	Over the last few years, Convolutional Neural Networks (CNNs) were successfully adopted in numerous domains to solve various image-related tasks, ranging from simple classification to fine borders annotation. Tracking seismic horizons is no different, and there are a lot of papers proposing the usage of such models to avoid time-consuming hand-picking. Unfortunately, most of them are (i) either trained on synthetic data, which can’t fully represent the complexity of subterranean structures, (ii) trained and tested on the same cube, or (iii) lack reproducibility and precise descriptions of the model-building process. With all that in mind, the main contribution of this paper is an open-sourced research of applying binary segmentation approach to the task of horizon detection on multiple real seismic cubes with a focus on inter-cube generalization of the predictive model.
Tasks
Published	2020-01-10
URL	https://arxiv.org/abs/2001.03390v1
PDF	https://arxiv.org/pdf/2001.03390v1.pdf
PWC	https://paperswithcode.com/paper/seismic-horizon-detection-with-neural
Repo
Framework

Compressed Sensing with Invertible Generative Models and Dependent Noise


Title	Compressed Sensing with Invertible Generative Models and Dependent Noise
Authors	Jay Whang, Qi Lei, Alexandros G. Dimakis
Abstract	We study image inverse problems with invertible generative priors, specifically normalizing flow models. Our formulation views the solution as the Maximum a Posteriori (MAP) estimate of the image given the measurements. Our general formulation allows for non-linear differentiable forward operators and noise distributions with long-range dependencies. We establish theoretical recovery guarantees for denoising and compressed sensing under our framework. We also empirically validate our method on various inverse problems including compressed sensing with quantized measurements and denoising with dependent noise patterns.
Tasks	Denoising
Published	2020-03-18
URL	https://arxiv.org/abs/2003.08089v1
PDF	https://arxiv.org/pdf/2003.08089v1.pdf
PWC	https://paperswithcode.com/paper/compressed-sensing-with-invertible-generative
Repo
Framework

Directionally Dependent Multi-View Clustering Using Copula Model


Title	Directionally Dependent Multi-View Clustering Using Copula Model
Authors	Kahkashan Afrin, Ashif S. Iquebal, Mostafa Karimi, Allyson Souris, Se Yoon Lee, Bani K. Mallick
Abstract	In recent biomedical scientific problems, it is a fundamental issue to integratively cluster a set of objects from multiple sources of datasets. Such problems are mostly encountered in genomics, where data is collected from various sources, and typically represent distinct yet complementary information. Integrating these data sources for multi-source clustering is challenging due to their complex dependence structure including directional dependency. Particularly in genomics studies, it is known that there is certain directional dependence between DNA expression, DNA methylation, and RNA expression, widely called The Central Dogma. Most of the existing multi-view clustering methods either assume an independent structure or pair-wise (non-directional) dependency, thereby ignoring the directional relationship. Motivated by this, we propose a copula-based multi-view clustering model where a copula enables the model to accommodate the directional dependence existing in the datasets. We conduct a simulation experiment where the simulated datasets exhibiting inherent directional dependence: it turns out that ignoring the directional dependence negatively affects the clustering performance. As a real application, we applied our model to the breast cancer tumor samples collected from The Cancer Genome Altas (TCGA).
Tasks
Published	2020-03-17
URL	https://arxiv.org/abs/2003.07494v1
PDF	https://arxiv.org/pdf/2003.07494v1.pdf
PWC	https://paperswithcode.com/paper/directionally-dependent-multi-view-clustering
Repo
Framework

Cloth in the Wind: A Case Study of Physical Measurement through Simulation


Title	Cloth in the Wind: A Case Study of Physical Measurement through Simulation
Authors	Tom F. H. Runia, Kirill Gavrilyuk, Cees G. M. Snoek, Arnold W. M. Smeulders
Abstract	For many of the physical phenomena around us, we have developed sophisticated models explaining their behavior. Nevertheless, measuring physical properties from visual observations is challenging due to the high number of causally underlying physical parameters – including material properties and external forces. In this paper, we propose to measure latent physical properties for cloth in the wind without ever having seen a real example before. Our solution is an iterative refinement procedure with simulation at its core. The algorithm gradually updates the physical model parameters by running a simulation of the observed phenomenon and comparing the current simulation to a real-world observation. The correspondence is measured using an embedding function that maps physically similar examples to nearby points. We consider a case study of cloth in the wind, with curling flags as our leading example – a seemingly simple phenomena but physically highly involved. Based on the physics of cloth and its visual manifestation, we propose an instantiation of the embedding function. For this mapping, modeled as a deep network, we introduce a spectral layer that decomposes a video volume into its temporal spectral power and corresponding frequencies. Our experiments demonstrate that the proposed method compares favorably to prior work on the task of measuring cloth material properties and external wind force from a real-world video.
Tasks
Published	2020-03-09
URL	https://arxiv.org/abs/2003.05065v1
PDF	https://arxiv.org/pdf/2003.05065v1.pdf
PWC	https://paperswithcode.com/paper/cloth-in-the-wind-a-case-study-of-physical
Repo
Framework

Background Matting


Title	Background Matting
Authors	Hossein Javidnia, François Pitié
Abstract	The current state of the art alpha matting methods mainly rely on the trimap as the secondary and only guidance to estimate alpha. This paper investigates the effects of utilising the background information as well as trimap in the process of alpha calculation. To achieve this goal, a state of the art method, AlphaGan is adopted and modified to process the background information as an extra input channel. Extensive experiments are performed to analyse the effect of the background information in image and video matting such as training with mildly and heavily distorted backgrounds. Based on the quantitative evaluations performed on Adobe Composition-1k dataset, the proposed pipeline significantly outperforms the state of the art methods using AlphaMatting benchmark metrics.
Tasks
Published	2020-02-11
URL	https://arxiv.org/abs/2002.04433v1
PDF	https://arxiv.org/pdf/2002.04433v1.pdf
PWC	https://paperswithcode.com/paper/background-matting
Repo
Framework

Learning Syntactic and Dynamic Selective Encoding for Document Summarization


Title	Learning Syntactic and Dynamic Selective Encoding for Document Summarization
Authors	Haiyang Xu, Yahao He, Kun Han, Junwen Chen, Xiangang Li
Abstract	Text summarization aims to generate a headline or a short summary consisting of the major information of the source text. Recent studies employ the sequence-to-sequence framework to encode the input with a neural network and generate abstractive summary. However, most studies feed the encoder with the semantic word embedding but ignore the syntactic information of the text. Further, although previous studies proposed the selective gate to control the information flow from the encoder to the decoder, it is static during the decoding and cannot differentiate the information based on the decoder states. In this paper, we propose a novel neural architecture for document summarization. Our approach has the following contributions: first, we incorporate syntactic information such as constituency parsing trees into the encoding sequence to learn both the semantic and syntactic information from the document, resulting in more accurate summary; second, we propose a dynamic gate network to select the salient information based on the context of the decoder state, which is essential to document summarization. The proposed model has been evaluated on CNN/Daily Mail summarization datasets and the experimental results show that the proposed approach outperforms baseline approaches.
Tasks	Constituency Parsing, Document Summarization, Text Summarization
Published	2020-03-25
URL	https://arxiv.org/abs/2003.11173v1
PDF	https://arxiv.org/pdf/2003.11173v1.pdf
PWC	https://paperswithcode.com/paper/learning-syntactic-and-dynamic-selective
Repo
Framework

Resolving learning rates adaptively by locating Stochastic Non-Negative Associated Gradient Projection Points using line searches


Title	Resolving learning rates adaptively by locating Stochastic Non-Negative Associated Gradient Projection Points using line searches
Authors	Dominic Kafka, Daniel N. Wilke
Abstract	Learning rates in stochastic neural network training are currently determined a priori to training, using expensive manual or automated iterative tuning. This study proposes gradient-only line searches to resolve the learning rate for neural network training algorithms. Stochastic sub-sampling during training decreases computational cost and allows the optimization algorithms to progress over local minima. However, it also results in discontinuous cost functions. Minimization line searches are not effective in this context, as they use a vanishing derivative (first order optimality condition), which often do not exist in a discontinuous cost function and therefore converge to discontinuities as opposed to minima from the data trends. Instead, we base candidate solutions along a search direction purely on gradient information, in particular by a directional derivative sign change from negative to positive (a Non-negative Associative Gradient Projection Point (NN- GPP)). Only considering a sign change from negative to positive always indicates a minimum, thus NN-GPPs contain second order information. Conversely, a vanishing gradient is purely a first order condition, which may indicate a minimum, maximum or saddle point. This insight allows the learning rate of an algorithm to be reliably resolved as the step size along a search direction, increasing convergence performance and eliminating an otherwise expensive hyperparameter.
Tasks
Published	2020-01-15
URL	https://arxiv.org/abs/2001.05113v1
PDF	https://arxiv.org/pdf/2001.05113v1.pdf
PWC	https://paperswithcode.com/paper/resolving-learning-rates-adaptively-by
Repo
Framework

Verification and Design Methods for the BrainScaleS Neuromorphic Hardware System


Title	Verification and Design Methods for the BrainScaleS Neuromorphic Hardware System
Authors	Andreas Grübl, Sebastian Billaudelle, Benjamin Cramer, Vitali Karasenko, Johannes Schemmel
Abstract	This paper presents verification and implementation methods that have been developed for the design of the BrainScaleS-2 65nm ASICs. The 2nd generation BrainScaleS chips are mixed-signal devices with tight coupling between full-custom analog neuromorphic circuits and two general purpose microprocessors (PPU) with SIMD extension for on-chip learning and plasticity. Simulation methods for automated analysis and pre-tapeout calibration of the highly parameterizable analog neuron and synapse circuits and for hardware-software co-development of the digital logic and software stack are presented. Accelerated operation of neuromorphic circuits and highly-parallel digital data buses between the full-custom neuromorphic part and the PPU require custom methodologies to close the digital signal timing at the interfaces. Novel extensions to the standard digital physical implementation design flow are highlighted. We present early results from the first full-size BrainScaleS-2 ASIC containing 512 neurons and 130K synapses, demonstrating the successful application of these methods. An application example illustrates the full functionality of the BrainScaleS-2 hybrid plasticity architecture.
Tasks	Calibration
Published	2020-03-25
URL	https://arxiv.org/abs/2003.11455v1
PDF	https://arxiv.org/pdf/2003.11455v1.pdf
PWC	https://paperswithcode.com/paper/verification-and-design-methods-for-the
Repo
Framework