April 1, 2020

3039 words 15 mins read

Paper Group ANR 430

D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry. A multi-layer approach to disinformation detection on Twitter. Disease Detection from Lung X-ray Images based on Hybrid Deep Learning. Mech-Elites: Illuminating the Mechanic Space of GVGAI. Finding Fair and Efficient Allocations When Valuations Don’t Add Up. Re-Training …

D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry


Title	D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry
Authors	Nan Yang, Lukas von Stumberg, Rui Wang, Daniel Cremers
Abstract	We propose D3VO as a novel framework for monocular visual odometry that exploits deep networks on three levels – deep depth, pose and uncertainty estimation. We first propose a novel self-supervised monocular depth estimation network trained on stereo videos without any external supervision. In particular, it aligns the training image pairs into similar lighting condition with predictive brightness transformation parameters. Besides, we model the photometric uncertainties of pixels on the input images, which improves the depth estimation accuracy and provides a learned weighting function for the photometric residuals in direct (feature-less) visual odometry. Evaluation results show that the proposed network outperforms state-of-the-art self-supervised depth estimation networks. D3VO tightly incorporates the predicted depth, pose and uncertainty into a direct visual odometry method to boost both the front-end tracking as well as the back-end non-linear optimization. We evaluate D3VO in terms of monocular visual odometry on both the KITTI odometry benchmark and the EuRoC MAV dataset.The results show that D3VO outperforms state-of-the-art traditional monocular VO methods by a large margin. It also achieves comparable results to state-of-the-art stereo/LiDAR odometry on KITTI and to the state-of-the-art visual-inertial odometry on EuRoC MAV, while using only a single camera.
Tasks	Depth Estimation, Monocular Depth Estimation, Monocular Visual Odometry, Visual Odometry
Published	2020-03-02
URL	https://arxiv.org/abs/2003.01060v2
PDF	https://arxiv.org/pdf/2003.01060v2.pdf
PWC	https://paperswithcode.com/paper/d3vo-deep-depth-deep-pose-and-deep
Repo
Framework

A multi-layer approach to disinformation detection on Twitter


Title	A multi-layer approach to disinformation detection on Twitter
Authors	Francesco Pierri, Carlo Piccardi, Stefano Ceri
Abstract	We tackle the problem of classifying news articles pertaining to disinformation vs mainstream news by solely inspecting their diffusion mechanisms on Twitter. Our technique is inherently simple compared to existing text-based approaches, as it allows to by-pass the multiple levels of complexity which are found in news content (e.g. grammar, syntax, style). We employ a multi-layer representation of Twitter diffusion networks, and we compute for each layer a set of global network features which quantify different aspects of the sharing process. Experimental results with two large-scale datasets, corresponding to diffusion cascades of news shared respectively in the United States and Italy, show that a simple Logistic Regression model is able to classify disinformation vs mainstream networks with high accuracy (AUROC up to 94%), also when considering the political bias of different sources in the classification task. We also highlight differences in the sharing patterns of the two news domains which appear to be country-independent. We believe that our network-based approach provides useful insights which pave the way to the future development of a system to detect misleading and harmful information spreading on social media.
Tasks
Published	2020-02-28
URL	https://arxiv.org/abs/2002.12612v1
PDF	https://arxiv.org/pdf/2002.12612v1.pdf
PWC	https://paperswithcode.com/paper/a-multi-layer-approach-to-disinformation
Repo
Framework

Disease Detection from Lung X-ray Images based on Hybrid Deep Learning


Title	Disease Detection from Lung X-ray Images based on Hybrid Deep Learning
Authors	Subrato Bharati, Prajoy Podder
Abstract	Lung Disease can be considered as the second most common type of disease for men and women. Many people die of lung disease such as lung cancer, Asthma, CPD (Chronic pulmonary disease) etc. in every year. Early detection of lung cancer can lessen the probability of deaths. In this paper, a chest X ray image dataset has been used in order to diagnosis properly and analysis the lung disease. For binary classification, some important is selected. The criteria include precision, recall, F beta score and accuracy. The fusion of AI and cancer diagnosis are acquiring huge interest as a cancer diagnostic tool. In recent days, deep learning based AI for example Convolutional neural network (CNN) can be successfully applied for disease classification and prediction. This paper mainly focuses the performance of Vanilla neural network, CNN, fusion of CNN and Visual Geometry group based neural network (VGG), fusion of CNN, VGG, STN and finally Capsule network. Normally basic CNN has poor performance for rotated, tilted or other abnormal image orientation. As a result, hybrid systems have been exhibited in order to enhance the accuracy with the maintenance of less training time. All models have been implemented in two groups of data sets: full dataset and sample dataset. Therefore, a comparative analysis has been developed in this paper. Some visualization of the attributes of the dataset has also been showed in this paper
Tasks
Published	2020-03-02
URL	https://arxiv.org/abs/2003.00682v1
PDF	https://arxiv.org/pdf/2003.00682v1.pdf
PWC	https://paperswithcode.com/paper/disease-detection-from-lung-x-ray-images
Repo
Framework

Mech-Elites: Illuminating the Mechanic Space of GVGAI


Title	Mech-Elites: Illuminating the Mechanic Space of GVGAI
Authors	Megan Charity, Michael Cerny Green, Ahmed Khalifa, Julian Togelius
Abstract	This paper introduces a fully automatic method of mechanic illumination for general video game level generation. Using the Constrained MAP-Elites algorithm and the GVG-AI framework, this system generates the simplest tile based levels that contain specific sets of game mechanics and also satisfy playability constraints. We apply this method to illuminate mechanic space for $4$ different games in GVG-AI: Zelda, Solarfox, Plants, and RealPortals.
Tasks
Published	2020-02-11
URL	https://arxiv.org/abs/2002.04733v1
PDF	https://arxiv.org/pdf/2002.04733v1.pdf
PWC	https://paperswithcode.com/paper/mech-elites-illuminating-the-mechanic-space
Repo
Framework

Finding Fair and Efficient Allocations When Valuations Don’t Add Up


Title	Finding Fair and Efficient Allocations When Valuations Don’t Add Up
Authors	Nawal Benabbou, Mithun Chakraborty, Ayumi Igarashi, Yair Zick
Abstract	In this paper, we present new results on the fair and efficient allocation of indivisible goods to agents that have monotone, submodular, non-additive valuation functions over bundles. Despite their simple structure, these agent valuations are a natural model for several real-world domains. We show that, if such a valuation function has binary marginal gains, a socially optimal (i.e. utilitarian social welfare-maximizing) allocation that achieves envy-freeness up to one item (EF1) exists and is computationally tractable. We also prove that the Nash welfare-maximizing and the leximin allocations both exhibit this fairness-efficiency combination, by showing that they can be achieved by minimizing any symmetric strictly convex function over utilitarian optimal outcomes. To the best of our knowledge, this is the first valuation function class not subsumed by additive valuations for which it has been established that an allocation maximizing Nash welfare is EF1. Moreover, for a subclass of these valuation functions based on maximum (unweighted) bipartite matching, we show that a leximin allocation can be computed in polynomial time.
Tasks
Published	2020-03-16
URL	https://arxiv.org/abs/2003.07060v2
PDF	https://arxiv.org/pdf/2003.07060v2.pdf
PWC	https://paperswithcode.com/paper/finding-fair-and-efficient-allocations-when
Repo
Framework

Re-Training StyleGAN – A First Step Towards Building Large, Scalable Synthetic Facial Datasets


Title	Re-Training StyleGAN – A First Step Towards Building Large, Scalable Synthetic Facial Datasets
Authors	Viktor Varkarakis, Shabab Bazrafkan, Peter Corcoran
Abstract	StyleGAN is a state-of-art generative adversarial network architecture that generates random 2D high-quality synthetic facial data samples. In this paper, we recap the StyleGAN architecture and training methodology and present our experiences of retraining it on a number of alternative public datasets. Practical issues and challenges arising from the retraining process are discussed. Tests and validation results are presented and a comparative analysis of several different re-trained StyleGAN weightings is provided 1. The role of this tool in building large, scalable datasets of synthetic facial data is also discussed.
Tasks
Published	2020-03-24
URL	https://arxiv.org/abs/2003.10847v1
PDF	https://arxiv.org/pdf/2003.10847v1.pdf
PWC	https://paperswithcode.com/paper/re-training-stylegan-a-first-step-towards
Repo
Framework

RSL-Net: Localising in Satellite Images From a Radar on the Ground


Title	RSL-Net: Localising in Satellite Images From a Radar on the Ground
Authors	Tim Y. Tang, Daniele De Martini, Dan Barnes, Paul Newman
Abstract	This paper is about localising a vehicle in an overhead image using FMCW radar mounted on a ground vehicle. FMCW radar offers extraordinary promise and efficacy for vehicle localisation. It is impervious to all weather types and lighting conditions. However the complexity of the interactions between millimetre radar wave and the physical environment makes it a challenging domain. Infrastructure-free large-scale radar-based localisation is in its infancy. Typically here a map is built and suitable techniques, compatible with the nature of sensor, are brought to bear. In this work we eschew the need for a radar-based map; instead we simply use an overhead image – a resource readily available everywhere. This paper introduces a method that not only naturally deals with the complexity of the signal type but does so in the context of cross modal processing.
Tasks
Published	2020-01-09
URL	https://arxiv.org/abs/2001.03233v2
PDF	https://arxiv.org/pdf/2001.03233v2.pdf
PWC	https://paperswithcode.com/paper/rsl-net-localising-in-satellite-images-from-a
Repo
Framework

Deeply Activated Salient Region for Instance Search


Title	Deeply Activated Salient Region for Instance Search
Authors	Hui-Chu Xiao, Wan-Lei Zhao, Jie Lin, Chong-Wah Ngo
Abstract	The performance of instance search depends heavily on the ability to locate and describe a wide variety of object instances in a video/image collection. Due to the lack of proper mechanism in locating instances and deriving feature representation, instance search is generally only effective for retrieving instances of known object categories. In this paper, a simple but effective instance-level feature representation is presented. Different from other approaches, the issues in class-agnostic instance localization and distinctive feature representation are considered. The former is achieved by detecting salient instance regions from an image by a layer-wise back-propagation process. The back-propagation starts from the last convolution layer of a pre-trained CNN that is originally used for classification. The back-propagation proceeds layer-by-layer until it reaches the input layer. This allows the salient instance regions in the input image from both known and unknown categories to be activated. Each activated salient region covers the full or more usually a major range of an instance. The distinctive feature representation is produced by average-pooling on the feature map of certain layer with the detected instance region. Experiments show that such kind of feature representation demonstrates considerably better performance over most of the existing approaches. In addition, we show that the proposed feature descriptor is also suitable for content-based image search.
Tasks	Image Retrieval, Instance Search
Published	2020-02-01
URL	https://arxiv.org/abs/2002.00185v3
PDF	https://arxiv.org/pdf/2002.00185v3.pdf
PWC	https://paperswithcode.com/paper/deeply-activated-salient-region-for-instance
Repo
Framework

Multi-layer Optimizations for End-to-End Data Analytics


Title	Multi-layer Optimizations for End-to-End Data Analytics
Authors	Amir Shaikhha, Maximilian Schleich, Alexandru Ghita, Dan Olteanu
Abstract	We consider the problem of training machine learning models over multi-relational data. The mainstream approach is to first construct the training dataset using a feature extraction query over input database and then use a statistical software package of choice to train the model. In this paper we introduce Iterative Functional Aggregate Queries (IFAQ), a framework that realizes an alternative approach. IFAQ treats the feature extraction query and the learning task as one program given in the IFAQ’s domain-specific language, which captures a subset of Python commonly used in Jupyter notebooks for rapid prototyping of machine learning applications. The program is subject to several layers of IFAQ optimizations, such as algebraic transformations, loop transformations, schema specialization, data layout optimizations, and finally compilation into efficient low-level C++ code specialized for the given workload and data. We show that a Scala implementation of IFAQ can outperform mlpack, Scikit, and TensorFlow by several orders of magnitude for linear regression and regression tree models over several relational datasets.
Tasks
Published	2020-01-10
URL	https://arxiv.org/abs/2001.03541v1
PDF	https://arxiv.org/pdf/2001.03541v1.pdf
PWC	https://paperswithcode.com/paper/multi-layer-optimizations-for-end-to-end-data
Repo
Framework

Offensive Language Detection: A Comparative Analysis


Title	Offensive Language Detection: A Comparative Analysis
Authors	Vyshnav M T, Sachin Kumar S, Soman K P
Abstract	Offensive behaviour has become pervasive in the Internet community. Individuals take the advantage of anonymity in the cyber world and indulge in offensive communications which they may not consider in the real life. Governments, online communities, companies etc are investing into prevention of offensive behaviour content in social media. One of the most effective solution for tacking this enigmatic problem is the use of computational techniques to identify offensive content and take action. The current work focuses on detecting offensive language in English tweets. The dataset used for the experiment is obtained from SemEval-2019 Task 6 on Identifying and Categorizing Offensive Language in Social Media (OffensEval). The dataset contains 14,460 annotated English tweets. The present paper provides a comparative analysis and Random kitchen sink (RKS) based approach for offensive language detection. We explore the effectiveness of Google sentence encoder, Fasttext, Dynamic mode decomposition (DMD) based features and Random kitchen sink (RKS) method for offensive language detection. From the experiments and evaluation we observed that RKS with fastetxt achieved competing results. The evaluation measures used are accuracy, precision, recall, f1-score.
Tasks
Published	2020-01-09
URL	https://arxiv.org/abs/2001.03131v1
PDF	https://arxiv.org/pdf/2001.03131v1.pdf
PWC	https://paperswithcode.com/paper/offensive-language-detection-a-comparative
Repo
Framework

Finite Hilbert Transform in Weighted L2 Spaces


Title	Finite Hilbert Transform in Weighted L2 Spaces
Authors	Jason You
Abstract	Several new properties of weighted Hilbert transform are obtained. If mu is zero, two Plancherel-like equations and the isotropic properties are derived. For mu is real number, a coerciveness is derived and two iterative sequences are constructed to find the inversion. The proposed iterative sequences are applicable to the case of pure imaginary constant mu=i*eta with eta<pi/4 . For mu=0.0 and 3.0 , we present the computer simulation results by using the Chebyshev series representation of finite Hilbert transform. The results in this paper are useful to the half scan in several imaging applications.
Tasks	Image Reconstruction
Published	2020-02-06
URL	https://arxiv.org/abs/2002.02071v2
PDF	https://arxiv.org/pdf/2002.02071v2.pdf
PWC	https://paperswithcode.com/paper/finite-hilbert-transform-in-weighted-l2
Repo
Framework

A Content Transformation Block For Image Style Transfer


Title	A Content Transformation Block For Image Style Transfer
Authors	Dmytro Kotovenko, Artsiom Sanakoyeu, Pingchuan Ma, Sabine Lang, Björn Ommer
Abstract	Style transfer has recently received a lot of attention, since it allows to study fundamental challenges in image understanding and synthesis. Recent work has significantly improved the representation of color and texture and computational speed and image resolution. The explicit transformation of image content has, however, been mostly neglected: while artistic style affects formal characteristics of an image, such as color, shape or texture, it also deforms, adds or removes content details. This paper explicitly focuses on a content-and style-aware stylization of a content image. Therefore, we introduce a content transformation module between the encoder and decoder. Moreover, we utilize similar content appearing in photographs and style samples to learn how style alters content details and we generalize this to other class details. Additionally, this work presents a novel normalization layer critical for high resolution image synthesis. The robustness and speed of our model enables a video stylization in real-time and high definition. We perform extensive qualitative and quantitative evaluations to demonstrate the validity of our approach.
Tasks	Image Generation, Style Transfer
Published	2020-03-18
URL	https://arxiv.org/abs/2003.08407v1
PDF	https://arxiv.org/pdf/2003.08407v1.pdf
PWC	https://paperswithcode.com/paper/a-content-transformation-block-for-image-1
Repo
Framework

Composing Molecules with Multiple Property Constraints


Title	Composing Molecules with Multiple Property Constraints
Authors	Wengong Jin, Regina Barzilay, Tommi Jaakkola
Abstract	Drug discovery aims to find novel compounds with specified chemical property profiles. In terms of generative modeling, the goal is to learn to sample molecules in the intersection of multiple property constraints. This task becomes increasingly challenging when there are many property constraints. We propose to offset this complexity by composing molecules from a vocabulary of substructures that we call molecular rationales. These rationales are identified from molecules as substructures that are likely responsible for each property of interest. We then learn to expand rationales into a full molecule using graph generative models. Our final generative model composes molecules as mixtures of multiple rationale completions, and this mixture is fine-tuned to preserve the properties of interest. We evaluate our model on various drug design tasks and demonstrate significant improvements over state-of-the-art baselines in terms of accuracy, diversity, and novelty of generated compounds.
Tasks	Drug Discovery
Published	2020-02-08
URL	https://arxiv.org/abs/2002.03244v1
PDF	https://arxiv.org/pdf/2002.03244v1.pdf
PWC	https://paperswithcode.com/paper/composing-molecules-with-multiple-property
Repo
Framework

Statistical Guarantees of Generative Adversarial Networks for Distribution Estimation


Title	Statistical Guarantees of Generative Adversarial Networks for Distribution Estimation
Authors	Minshuo Chen, Wenjing Liao, Hongyuan Zha, Tuo Zhao
Abstract	Generative Adversarial Networks (GANs) have achieved great success in unsupervised learning. Despite the remarkable empirical performance, there are limited theoretical understandings on the statistical properties of GANs. This paper provides statistical guarantees of GANs for the estimation of data distributions which have densities in a H"{o}lder space. Our main result shows that, if the generator and discriminator network architectures are properly chosen (universally for all distributions with H"{o}lder densities), GANs are consistent estimators of the data distributions under strong discrepancy metrics, such as the Wasserstein distance. To our best knowledge, this is the first statistical theory of GANs for H"{o}lder densities. In comparison with existing works, our theory requires minimum assumptions on data distributions. Our generator and discriminator networks utilize general weight matrices and the non-invertible ReLU activation function, while many existing works only apply to invertible weight matrices and invertible activation functions. In our analysis, we decompose the error into a statistical error and an approximation error by a new oracle inequality, which may be of independent interest.
Tasks
Published	2020-02-10
URL	https://arxiv.org/abs/2002.03938v1
PDF	https://arxiv.org/pdf/2002.03938v1.pdf
PWC	https://paperswithcode.com/paper/statistical-guarantees-of-generative
Repo
Framework

Meta Pseudo Labels


Title	Meta Pseudo Labels
Authors	Hieu Pham, Qizhe Xie, Zihang Dai, Quoc V. Le
Abstract	Many training algorithms of a deep neural network can be interpreted as minimizing the cross entropy loss between the prediction made by the network and a target distribution. In supervised learning, this target distribution is typically the ground-truth one-hot vector. In semi-supervised learning, this target distribution is typically generated by a pre-trained teacher model to train the main network. In this work, instead of using such predefined target distributions, we show that learning to adjust the target distribution based on the learning state of the main network can lead to better performances. In particular, we propose an efficient meta-learning algorithm, which encourages the teacher to adjust the target distributions of training examples in the manner that improves the learning of the main network. The teacher is updated by policy gradients computed by evaluating the main network on a held-out validation set. Our experiments demonstrate substantial improvements over strong baselines and establish state-ofthe-art performance on CIFAR-10, SVHN, and ImageNet. For instance, with ResNets on small datasets, we achieve 96.1% on CIFAR-10 with 4,000 labeled examples and 73.9% top-1 on ImageNet with 10% examples. Meanwhile, with EfficientNet on full datasets plus extra unlabeled data, we attain 98.6% accuracy on CIFAR-10 and 86.9% top-1 accuracy on ImageNet.
Tasks	Meta-Learning
Published	2020-03-23
URL	https://arxiv.org/abs/2003.10580v1
PDF	https://arxiv.org/pdf/2003.10580v1.pdf
PWC	https://paperswithcode.com/paper/meta-pseudo-labels
Repo
Framework