January 30, 2020

3299 words 16 mins read

Paper Group ANR 470

A Data Science Approach for Honeypot Detection in Ethereum. How to Estimate the Ability of a Metaheuristic Algorithm to Guide Heuristics During Optimization. 3DQ: Compact Quantized Neural Networks for Volumetric Whole Brain Segmentation. Understanding the Limitations of CNN-based Absolute Camera Pose Regression. Interestingness Elements for Explain …

A Data Science Approach for Honeypot Detection in Ethereum


Title	A Data Science Approach for Honeypot Detection in Ethereum
Authors	Ramiro Camino, Christof Ferreira Torres, Mathis Baden, Radu State
Abstract	Ethereum smart contracts have recently drawn a considerable amount of attention from the media, the financial industry and academia. With the increase in popularity, malicious users found new opportunities to profit by deceiving newcomers. Consequently, attackers started luring other attackers into contracts that seem to have exploitable flaws, but that actually contain a complex hidden trap that in the end benefits the contract creator. In the blockchain community, these contracts are known as honeypots. A recent study presented a tool called HONEYBADGER that uses symbolic execution to detect honeypots by analyzing contract bytecode. In this paper, we present a data science detection approach based foremost on the contract transaction behavior. We create a partition of all the possible cases of fund movements between the contract creator, the contract, the transaction sender and other participants. To this end, we add transaction aggregated features, such as the number of transactions and the corresponding mean value and other contract features, for example compilation information and source code length. We find that all aforementioned categories of features contain useful information for the detection of honeypots. Moreover, our approach allows us to detect new, previously undetected honeypots of already known techniques. We furthermore employ our method to test the detection of unknown honeypot techniques by sequentially removing one technique from the training set. We show that our method is capable of discovering the removed honeypot techniques. Finally, we discovered two new techniques that were previously not known.
Tasks
Published	2019-10-03
URL	https://arxiv.org/abs/1910.01449v2
PDF	https://arxiv.org/pdf/1910.01449v2.pdf
PWC	https://paperswithcode.com/paper/a-data-science-approach-for-honeypot
Repo
Framework

How to Estimate the Ability of a Metaheuristic Algorithm to Guide Heuristics During Optimization


Title	How to Estimate the Ability of a Metaheuristic Algorithm to Guide Heuristics During Optimization
Authors	Miloš Simić
Abstract	Metaheuristics are general methods that guide application of concrete heuristic(s) to problems that are too hard to solve using exact algorithms. However, even though a growing body of literature has been devoted to their statistical evaluation, the approaches proposed so far are able to assess only coupled effects of metaheuristics and heuristics. They do not reveal us anything about how efficient the examined metaheuristic is at guiding its subordinate heuristic(s), nor do they provide us information about how much the heuristic component of the combined algorithm contributes to the overall performance. In this paper, we propose a simple yet effective methodology of doing so by deriving a naive, placebo metaheuristic from the one being studied and comparing the distributions of chosen performance metrics for the two methods. We propose three measures of difference between the two distributions. Those measures, which we call BER values (benefit, equivalence, risk) are based on a preselected threshold of practical significance which represents the minimal difference between two performance scores required for them to be considered practically different. We illustrate usefulness of our methodology on the example of Simulated Annealing, Boolean Satisfiability Problem, and the Flip heuristic.
Tasks
Published	2019-03-29
URL	http://arxiv.org/abs/1904.00103v1
PDF	http://arxiv.org/pdf/1904.00103v1.pdf
PWC	https://paperswithcode.com/paper/how-to-estimate-the-ability-of-a
Repo
Framework

3DQ: Compact Quantized Neural Networks for Volumetric Whole Brain Segmentation


Title	3DQ: Compact Quantized Neural Networks for Volumetric Whole Brain Segmentation
Authors	Magdalini Paschali, Stefano Gasperini, Abhijit Guha Roy, Michael Y. -S. Fang, Nassir Navab
Abstract	Model architectures have been dramatically increasing in size, improving performance at the cost of resource requirements. In this paper we propose 3DQ, a ternary quantization method, applied for the first time to 3D Fully Convolutional Neural Networks (F-CNNs), enabling 16x model compression while maintaining performance on par with full precision models. We extensively evaluate 3DQ on two datasets for the challenging task of whole brain segmentation. Additionally, we showcase our method’s ability to generalize on two common 3D architectures, namely 3D U-Net and V-Net. Outperforming a variety of baselines, the proposed method is capable of compressing large 3D models to a few MBytes, alleviating the storage needs in space critical applications.
Tasks	Brain Segmentation, Model Compression, Quantization
Published	2019-04-05
URL	https://arxiv.org/abs/1904.03110v3
PDF	https://arxiv.org/pdf/1904.03110v3.pdf
PWC	https://paperswithcode.com/paper/3dq-compact-quantized-neural-networks-for
Repo
Framework

Understanding the Limitations of CNN-based Absolute Camera Pose Regression


Title	Understanding the Limitations of CNN-based Absolute Camera Pose Regression
Authors	Torsten Sattler, Qunjie Zhou, Marc Pollefeys, Laura Leal-Taixe
Abstract	Visual localization is the task of accurate camera pose estimation in a known scene. It is a key problem in computer vision and robotics, with applications including self-driving cars, Structure-from-Motion, SLAM, and Mixed Reality. Traditionally, the localization problem has been tackled using 3D geometry. Recently, end-to-end approaches based on convolutional neural networks have become popular. These methods learn to directly regress the camera pose from an input image. However, they do not achieve the same level of pose accuracy as 3D structure-based methods. To understand this behavior, we develop a theoretical model for camera pose regression. We use our model to predict failure cases for pose regression techniques and verify our predictions through experiments. We furthermore use our model to show that pose regression is more closely related to pose approximation via image retrieval than to accurate pose estimation via 3D structure. A key result is that current approaches do not consistently outperform a handcrafted image retrieval baseline. This clearly shows that additional research is needed before pose regression algorithms are ready to compete with structure-based methods.
Tasks	Image Retrieval, Pose Estimation, Self-Driving Cars, Visual Localization
Published	2019-03-18
URL	http://arxiv.org/abs/1903.07504v1
PDF	http://arxiv.org/pdf/1903.07504v1.pdf
PWC	https://paperswithcode.com/paper/understanding-the-limitations-of-cnn-based
Repo
Framework

Interestingness Elements for Explainable Reinforcement Learning: Understanding Agents’ Capabilities and Limitations


Title	Interestingness Elements for Explainable Reinforcement Learning: Understanding Agents’ Capabilities and Limitations
Authors	Pedro Sequeira, Melinda Gervasio
Abstract	We propose an explainable reinforcement learning (XRL) framework that analyzes an agent’s history of interaction with the environment to extract interestingness elements that help explain its behavior. The framework relies on data readily available from standard RL algorithms, augmented with data that can easily be collected by the agent while learning. We describe how to create visual explanations of an agent’s behavior in the form of short video-clips highlighting key interaction moments, based on the proposed elements. We also report on a user study where we evaluated the ability of humans in correctly perceiving the aptitude of agents with different characteristics, including their capabilities and limitations, given explanations automatically generated by our framework. The results show that the diversity of aspects captured by the different interestingness elements is crucial to help humans correctly identify the agents’ aptitude in the task, and determine when they might need adjustments to improve their performance.
Tasks
Published	2019-12-19
URL	https://arxiv.org/abs/1912.09007v1
PDF	https://arxiv.org/pdf/1912.09007v1.pdf
PWC	https://paperswithcode.com/paper/interestingness-elements-for-explainable
Repo
Framework

Image inpainting: A review


Title	Image inpainting: A review
Authors	Omar Elharrouss, Noor Almaadeed, Somaya Al-Maadeed, Younes Akbari
Abstract	Although image inpainting, or the art of repairing the old and deteriorated images, has been around for many years, it has gained even more popularity because of the recent development in image processing techniques. With the improvement of image processing tools and the flexibility of digital image editing, automatic image inpainting has found important applications in computer vision and has also become an important and challenging topic of research in image processing. This paper is a brief review of the existing image inpainting approaches we first present a global vision on the existing methods for image inpainting. We attempt to collect most of the existing approaches and classify them into three categories, namely, sequential-based, CNN-based and GAN-based methods. In addition, for each category, a list of methods for the different types of distortion on the images is presented. Furthermore, collect a list of the available datasets and discuss these in our paper. This is a contribution for digital image inpainting researchers trying to look for the available datasets because there is a lack of datasets available for image inpainting. As the final step in this overview, we present the results of real evaluations of the three categories of image inpainting methods performed on the datasets used, for the different types of image distortion. In the end, we also present the evaluations metrics and discuss the performance of these methods in terms of these metrics. This overview can be used as a reference for image inpainting researchers, and it can also facilitate the comparison of the methods as well as the datasets used. The main contribution of this paper is the presentation of the three categories of image inpainting methods along with a list of available datasets that the researchers can use to evaluate their proposed methodology against.
Tasks	Image Inpainting
Published	2019-09-13
URL	https://arxiv.org/abs/1909.06399v1
PDF	https://arxiv.org/pdf/1909.06399v1.pdf
PWC	https://paperswithcode.com/paper/image-inpainting-a-review
Repo
Framework

Mercem: Method Name Recommendation Based on Call Graph Embedding


Title	Mercem: Method Name Recommendation Based on Call Graph Embedding
Authors	Hiroshi Yonai, Yasuhiro Hayase, Hiroyuki Kitagawa
Abstract	Comprehensibility of source code is strongly affected by identifier names, therefore software developers need to give good (e.g. meaningful but short) names to identifiers. On the other hand, giving a good name is sometimes a difficult and time-consuming task even for experienced developers. To support naming identifiers, several techniques for recommending identifier name candidates have been proposed. These techniques, however, still have challenges on the goodness of suggested candidates and limitations on applicable situations. This paper proposes a new approach to recommending method names by applying graph embedding techniques to the method call graph. The evaluation experiment confirms that the proposed technique can suggest more appropriate method name candidates in difficult situations than the state of the art approach.
Tasks	Graph Embedding
Published	2019-07-12
URL	https://arxiv.org/abs/1907.05690v1
PDF	https://arxiv.org/pdf/1907.05690v1.pdf
PWC	https://paperswithcode.com/paper/mercem-method-name-recommendation-based-on
Repo
Framework

Neural Point Cloud Rendering via Multi-Plane Projection


Title	Neural Point Cloud Rendering via Multi-Plane Projection
Authors	Peng Dai, Yinda Zhang, Zhuwen Li, Shuaicheng Liu, Bing Zeng
Abstract	We present a new deep point cloud rendering pipeline through multi-plane projections. The input to the network is the raw point cloud of a scene and the output are image or image sequences from a novel view or along a novel camera trajectory. Unlike previous approaches that directly project features from 3D points onto 2D image domain, we propose to project these features into a layered volume of camera frustum. In this way, the visibility of 3D points can be automatically learnt by the network, such that ghosting effects due to false visibility check as well as occlusions caused by noise interferences are both avoided successfully. Next, the 3D feature volume is fed into a 3D CNN to produce multiple layers of images w.r.t. the space division in the depth directions. The layered images are then blended based on learned weights to produce the final rendering results. Experiments show that our network produces more stable renderings compared to previous methods, especially near the object boundaries. Moreover, our pipeline is robust to noisy and relatively sparse point cloud for a variety of challenging scenes.
Tasks
Published	2019-12-10
URL	https://arxiv.org/abs/1912.04645v1
PDF	https://arxiv.org/pdf/1912.04645v1.pdf
PWC	https://paperswithcode.com/paper/neural-point-cloud-rendering-via-multi-plane
Repo
Framework

An Investigation of Transfer Learning-Based Sentiment Analysis in Japanese


Title	An Investigation of Transfer Learning-Based Sentiment Analysis in Japanese
Authors	Enkhbold Bataa, Joshua Wu
Abstract	Text classification approaches have usually required task-specific model architectures and huge labeled datasets. Recently, thanks to the rise of text-based transfer learning techniques, it is possible to pre-train a language model in an unsupervised manner and leverage them to perform effective on downstream tasks. In this work we focus on Japanese and show the potential use of transfer learning techniques in text classification. Specifically, we perform binary and multi-class sentiment classification on the Rakuten product review and Yahoo movie review datasets. We show that transfer learning-based approaches perform better than task-specific models trained on 3 times as much data. Furthermore, these approaches perform just as well for language modeling pre-trained on only 1/30 of the data. We release our pre-trained models and code as open source.
Tasks	Language Modelling, Sentiment Analysis, Text Classification, Transfer Learning
Published	2019-05-23
URL	https://arxiv.org/abs/1905.09642v3
PDF	https://arxiv.org/pdf/1905.09642v3.pdf
PWC	https://paperswithcode.com/paper/an-investigation-of-transfer-learning-based
Repo
Framework

PSACNN: Pulse Sequence Adaptive Fast Whole Brain Segmentation


Title	PSACNN: Pulse Sequence Adaptive Fast Whole Brain Segmentation
Authors	Amod Jog, Andrew Hoopes, Douglas N. Greve, Koen Van Leemput, Bruce Fischl
Abstract	With the advent of convolutional neural networks~(CNN), supervised learning methods are increasingly being used for whole brain segmentation. However, a large, manually annotated training dataset of labeled brain images required to train such supervised methods is frequently difficult to obtain or create. In addition, existing training datasets are generally acquired with a homogeneous magnetic resonance imaging~(MRI) acquisition protocol. CNNs trained on such datasets are unable to generalize on test data with different acquisition protocols. Modern neuroimaging studies and clinical trials are necessarily multi-center initiatives with a wide variety of acquisition protocols. Despite stringent protocol harmonization practices, it is very difficult to standardize the gamut of MRI imaging parameters across scanners, field strengths, receive coils etc., that affect image contrast. In this paper we propose a CNN-based segmentation algorithm that, in addition to being highly accurate and fast, is also resilient to variation in the input acquisition. Our approach relies on building approximate forward models of pulse sequences that produce a typical test image. For a given pulse sequence, we use its forward model to generate plausible, synthetic training examples that appear as if they were acquired in a scanner with that pulse sequence. Sampling over a wide variety of pulse sequences results in a wide variety of augmented training examples that help build an image contrast invariant model. Our method trains a single CNN that can segment input MRI images with acquisition parameters as disparate as $T_1$-weighted and $T_2$-weighted contrasts with only $T_1$-weighted training data. The segmentations generated are highly accurate with state-of-the-art results~(overall Dice overlap$=0.94$), with a fast run time~($\approx$ 45 seconds), and consistent across a wide range of acquisition protocols.
Tasks	Brain Segmentation
Published	2019-01-17
URL	http://arxiv.org/abs/1901.05992v3
PDF	http://arxiv.org/pdf/1901.05992v3.pdf
PWC	https://paperswithcode.com/paper/psacnn-pulse-sequence-adaptive-fast-whole
Repo
Framework

Combining Learned Representations for Combinatorial Optimization


Title	Combining Learned Representations for Combinatorial Optimization
Authors	Saavan Patel, Sayeef Salahuddin
Abstract	We propose a new approach to combine Restricted Boltzmann Machines (RBMs) that can be used to solve combinatorial optimization problems. This allows synthesis of larger models from smaller RBMs that have been pretrained, thus effectively bypassing the problem of learning in large RBMs, and creating a system able to model a large, complex multi-modal space. We validate this approach by using learned representations to create ``invertible boolean logic’', where we can use Markov chain Monte Carlo (MCMC) approaches to find the solution to large scale boolean satisfiability problems and show viability towards other combinatorial optimization problems. Using this method, we are able to solve 64 bit addition based problems, as well as factorize 16 bit numbers. We find that these combined representations can provide a more accurate result for the same sample size as compared to a fully trained model. \|
Tasks	Combinatorial Optimization
Published	2019-09-09
URL	https://arxiv.org/abs/1909.03978v1
PDF	https://arxiv.org/pdf/1909.03978v1.pdf
PWC	https://paperswithcode.com/paper/combining-learned-representations-for-1
Repo
Framework

Semantic and Visual Similarities for Efficient Knowledge Transfer in CNN Training


Title	Semantic and Visual Similarities for Efficient Knowledge Transfer in CNN Training
Authors	Lucas Pascal, Xavier Bost, Benoît Huet
Abstract	In recent years, representation learning approaches have disrupted many multimedia computing tasks. Among those approaches, deep convolutional neural networks (CNNs) have notably reached human level expertise on some constrained image classification tasks. Nonetheless, training CNNs from scratch for new task or simply new data turns out to be complex and time-consuming. Recently, transfer learning has emerged as an effective methodology for adapting pre-trained CNNs to new data and classes, by only retraining the last classification layer. This paper focuses on improving this process, in order to better transfer knowledge between CNN architectures for faster trainings in the case of fine tuning for image classification. This is achieved by combining and transfering supplementary weights, based on similarity considerations between source and target classes. The study includes a comparison between semantic and content-based similarities, and highlights increased initial performances and training speed, along with superior long term performances when limited training samples are available.
Tasks	Image Classification, Representation Learning, Transfer Learning
Published	2019-09-13
URL	https://arxiv.org/abs/1909.12916v1
PDF	https://arxiv.org/pdf/1909.12916v1.pdf
PWC	https://paperswithcode.com/paper/semantic-and-visual-similarities-for
Repo
Framework

Semiparametric correction for endogenous truncation bias with Vox Populi based participation decision


Title	Semiparametric correction for endogenous truncation bias with Vox Populi based participation decision
Authors	Nir Billfeld, Moshe Kim
Abstract	We synthesize the knowledge present in various scientific disciplines for the development of semiparametric endogenous truncation-proof algorithm, correcting for truncation bias due to endogenous self-selection. This synthesis enriches the algorithm’s accuracy, efficiency and applicability. Improving upon the covariate shift assumption, data are intrinsically affected and largely generated by their own behavior (cognition). Refining the concept of Vox Populi (Wisdom of Crowd) allows data points to sort themselves out depending on their estimated latent reference group opinion space. Monte Carlo simulations, based on 2,000,000 different distribution functions, practically generating 100 million realizations, attest to a very high accuracy of our model.
Tasks
Published	2019-02-17
URL	http://arxiv.org/abs/1902.06286v1
PDF	http://arxiv.org/pdf/1902.06286v1.pdf
PWC	https://paperswithcode.com/paper/semiparametric-correction-for-endogenous
Repo
Framework

Curriculum Self-Paced Learning for Cross-Domain Object Detection


Title	Curriculum Self-Paced Learning for Cross-Domain Object Detection
Authors	Petru Soviany, Radu Tudor Ionescu, Paolo Rota, Nicu Sebe
Abstract	Training (source) domain bias affects state-of-the-art object detectors, such as Faster R-CNN, when applied to new (target) domains. To alleviate this problem, researchers proposed various domain adaptation methods to improve object detection results in the cross-domain setting, e.g. by translating images with ground-truth labels from the source domain to the target domain using Cycle-GAN or by applying self-paced learning. On top of combining Cycle-GAN transformations and self-paced learning, in this paper, we propose a novel self-paced algorithm that learns from easy to hard. To estimate the difficulty of each image, we use the number of detected objects divided by their average size. Our method is simple and effective, without any overhead during inference. It uses only pseudo-labels for samples taken from the target domain, i.e. the domain adaptation is unsupervised. We conduct experiments on two cross-domain benchmarks, showing better results than the state of the art. We also perform an ablation study demonstrating the utility of each component in our framework.
Tasks	Domain Adaptation, Object Detection
Published	2019-11-15
URL	https://arxiv.org/abs/1911.06849v1
PDF	https://arxiv.org/pdf/1911.06849v1.pdf
PWC	https://paperswithcode.com/paper/curriculum-self-paced-learning-for-cross
Repo
Framework

On the Convergence of Extended Variational Inference for Non-Gaussian Statistical Models


Title	On the Convergence of Extended Variational Inference for Non-Gaussian Statistical Models
Authors	Zhanyu Ma, Jalil Taghia, Jun Guo
Abstract	Variational inference (VI) is a widely used framework in Bayesian estimation. For most of the non-Gaussian statistical models, it is infeasible to find an analytically tractable solution to estimate the posterior distributions of the parameters. Recently, an improved framework, namely the extended variational inference (EVI), has been introduced and applied to derive analytically tractable solution by employing lower-bound approximation to the variational objective function. Two conditions required for EVI implementation, namely the weak condition and the strong condition, are discussed and compared in this paper. In practical implementation, the convergence of the EVI depends on the selection of the lower-bound approximation, no matter with the weak condition or the strong condition. In general, two approximation strategies, the single lower-bound (SLB) approximation and the multiple lower-bounds (MLB) approximation, can be applied to carry out the lower-bound approximation. To clarify the differences between the SLB and the MLB, we will also discuss the convergence properties of the aforementioned two approximations. Extensive comparisons are made based on some existing EVI-based non-Gaussian statistical models. Theoretical analysis are conducted to demonstrate the differences between the weak and the strong conditions. Qualitative and quantitative experimental results are presented to show the advantages of the SLB approximation.
Tasks
Published	2019-02-13
URL	https://arxiv.org/abs/1902.05068v2
PDF	https://arxiv.org/pdf/1902.05068v2.pdf
PWC	https://paperswithcode.com/paper/on-the-convergence-of-extended-variational
Repo
Framework