January 28, 2020

3321 words 16 mins read

Paper Group ANR 972

The Performance of Machine and Deep Learning Classifiers in Detecting Zero-Day Vulnerabilities. On Space-spectrum Uncertainty Analysis for Coded Aperture Systems. CNN-based Semantic Segmentation using Level Set Loss. Contrast Optimization And Local Adaptation (COALA) for HDR Compression. DAWN: Dual Augmented Memory Network for Unsupervised Video Ob …

The Performance of Machine and Deep Learning Classifiers in Detecting Zero-Day Vulnerabilities


Title	The Performance of Machine and Deep Learning Classifiers in Detecting Zero-Day Vulnerabilities
Authors	Faranak Abri, Sima Siami-Namini, Mahdi Adl Khanghah, Fahimeh Mirza Soltani, Akbar Siami Namin
Abstract	The detection of zero-day attacks and vulnerabilities is a challenging problem. It is of utmost importance for network administrators to identify them with high accuracy. The higher the accuracy is, the more robust the defense mechanism will be. In an ideal scenario (i.e., 100% accuracy) the system can detect zero-day malware without being concerned about mistakenly tagging benign files as malware or enabling disruptive malicious code running as none-malicious ones. This paper investigates different machine learning algorithms to find out how well they can detect zero-day malware. Through the examination of 34 machine/deep learning classifiers, we found that the random forest classifier offered the best accuracy. The paper poses several research questions regarding the performance of machine and deep learning algorithms when detecting zero-day malware with zero rates for false positive and false negative.
Tasks
Published	2019-11-21
URL	https://arxiv.org/abs/1911.09586v1
PDF	https://arxiv.org/pdf/1911.09586v1.pdf
PWC	https://paperswithcode.com/paper/the-performance-of-machine-and-deep-learning
Repo
Framework

On Space-spectrum Uncertainty Analysis for Coded Aperture Systems


Title	On Space-spectrum Uncertainty Analysis for Coded Aperture Systems
Authors	Vishwanath Saragadam, Aswin Sankaranarayanan
Abstract	We introduce and analyze the concept of space-spectrum uncertainty for certain commonly-used designs for spectrally programmable cameras. Our key finding states that, it is impossible to simultaneously capture high-resolution spatial images while programming the spectrum at high resolution. This phenomenon arises due to a Fourier relationship between the aperture used for obtaining spectrum and its corresponding diffraction blur in the (spatial) image. We show that the product of spatial and spectral standard deviations is lower bounded by {\lambda}/4{\pi}{\nu_0} femto square-meters, where {\nu_0} is the density of groves in the diffraction grating and {\lambda} is the wavelength of light. Experiments with a lab prototype for simultaneously measuring spectrum and image validate our findings and its implication for spectral filtering.
Tasks
Published	2019-11-16
URL	https://arxiv.org/abs/1911.06956v1
PDF	https://arxiv.org/pdf/1911.06956v1.pdf
PWC	https://paperswithcode.com/paper/on-space-spectrum-uncertainty-analysis-for
Repo
Framework

CNN-based Semantic Segmentation using Level Set Loss


Title	CNN-based Semantic Segmentation using Level Set Loss
Authors	Youngeun Kim, Seunghyeon Kim, Taekyung Kim, Changick Kim
Abstract	Thesedays, Convolutional Neural Networks are widely used in semantic segmentation. However, since CNN-based segmentation networks produce low-resolution outputs with rich semantic information, it is inevitable that spatial details (e.g., small bjects and fine boundary information) of segmentation results will be lost. To address this problem, motivated by a variational approach to image segmentation (i.e., level set theory), we propose a novel loss function called the level set loss which is designed to refine spatial details of segmentation results. To deal with multiple classes in an image, we first decompose the ground truth into binary images. Note that each binary image consists of background and regions belonging to a class. Then we convert level set functions into class probability maps and calculate the energy for each class. The network is trained to minimize the weighted sum of the level set loss and the cross-entropy loss. The proposed level set loss improves the spatial details of segmentation results in a time and memory efficient way. Furthermore, our experimental results show that the proposed loss function achieves better performance than previous approaches.
Tasks	Semantic Segmentation
Published	2019-10-02
URL	https://arxiv.org/abs/1910.00950v1
PDF	https://arxiv.org/pdf/1910.00950v1.pdf
PWC	https://paperswithcode.com/paper/cnn-based-semantic-segmentation-using-level
Repo
Framework

Contrast Optimization And Local Adaptation (COALA) for HDR Compression


Title	Contrast Optimization And Local Adaptation (COALA) for HDR Compression
Authors	Shay Maymon, Hila Barel
Abstract	This paper develops a novel approach for high dynamic-range compression. It relies on the widely accepted assumption that the human visual system is not very sensitive to absolute luminance reaching the retina, but rather responds to relative luminance ratios. Dynamic-range compression is then formulated as a regularized optimization in which the image dynamic range is reduced while the local contrast of the original scene is preserved. Our method is shown to be capable of drastic dynamic-range compression, while preserving fine details and avoiding common artifacts such as halos, gradient reversals, or loss of local contrast.
Tasks
Published	2019-05-15
URL	https://arxiv.org/abs/1905.06372v1
PDF	https://arxiv.org/pdf/1905.06372v1.pdf
PWC	https://paperswithcode.com/paper/contrast-optimization-and-local-adaptation
Repo
Framework

DAWN: Dual Augmented Memory Network for Unsupervised Video Object Tracking


Title	DAWN: Dual Augmented Memory Network for Unsupervised Video Object Tracking
Authors	Zhenmei Shi, Haoyang Fang, Yu-Wing Tai, Chi-Keung Tang
Abstract	Psychological studies have found that human visual tracking system involves learning, memory, and planning. Despite recent successes, not many works have focused on memory and planning in deep learning based tracking. We are thus interested in memory augmented network, where an external memory remembers the evolving appearance of the target (foreground) object without backpropagation for updating weights. Our Dual Augmented Memory Network (DAWN) is unique in remembering both target and background, and using an improved attention LSTM memory to guide the focus on memorized features. DAWN is effective in unsupervised tracking in handling total occlusion, severe motion blur, abrupt changes in target appearance, multiple object instances, and similar foreground and background features. We present extensive quantitative and qualitative experimental comparison with state-of-the-art methods including top contenders in recent VOT challenges. Notably, despite the straightforward implementation, DAWN is ranked third in both VOT2016 and VOT2017 challenges with excellent success rate among all VOT fast trackers running at fps > 10 in unsupervised tracking in both challenges. We propose DAWN-RPN, where we simply augment our memory and attention LSTM modules to the state-of-the-art SiamRPN, and report immediate performance gain, thus demonstrating DAWN can work well with and directly benefit other models to handle difficult cases as well.
Tasks	Object Tracking, Video Object Tracking, Visual Tracking
Published	2019-08-02
URL	https://arxiv.org/abs/1908.00777v2
PDF	https://arxiv.org/pdf/1908.00777v2.pdf
PWC	https://paperswithcode.com/paper/dawn-dual-augmented-memory-network-for
Repo
Framework

Contextualization of Morphological Inflection


Title	Contextualization of Morphological Inflection
Authors	Ekaterina Vylomova, Ryan Cotterell, Timothy Baldwin, Trevor Cohn, Jason Eisner
Abstract	Critical to natural language generation is the production of correctly inflected text. In this paper, we isolate the task of predicting a fully inflected sentence from its partially lemmatized version. Unlike traditional morphological inflection or surface realization, our task input does not provide ``gold’’ tags that specify what morphological features to realize on each lemmatized word; rather, such features must be inferred from sentential context. We develop a neural hybrid graphical model that explicitly reconstructs morphological features before predicting the inflected forms, and compare this to a system that directly predicts the inflected forms without relying on any morphological annotation. We experiment on several typologically diverse languages from the Universal Dependencies treebanks, showing the utility of incorporating linguistically-motivated latent variables into NLP models. \|
Tasks	Morphological Inflection, Text Generation
Published	2019-05-04
URL	https://arxiv.org/abs/1905.01420v1
PDF	https://arxiv.org/pdf/1905.01420v1.pdf
PWC	https://paperswithcode.com/paper/contextualization-of-morphological-inflection
Repo
Framework

3DFPN-HS$^2$: 3D Feature Pyramid Network Based High Sensitivity and Specificity Pulmonary Nodule Detection


Title	3DFPN-HS$^2$: 3D Feature Pyramid Network Based High Sensitivity and Specificity Pulmonary Nodule Detection
Authors	Jingya Liu, Liangliang Cao, Oguz Akin, Yingli Tian
Abstract	Accurate detection of pulmonary nodules with high sensitivity and specificity is essential for automatic lung cancer diagnosis from CT scans. Although many deep learning-based algorithms make great progress for improving the accuracy of nodule detection, the high false positive rate is still a challenging problem which limited the automatic diagnosis in routine clinical practice. In this paper, we propose a novel pulmonary nodule detection framework based on a 3D Feature Pyramid Network (3DFPN) to improve the sensitivity of nodule detection by employing multi-scale features to increase the resolution of nodules, as well as a parallel top-down path to transit the high-level semantic features to complement low-level general features. Furthermore, a High Sensitivity and Specificity (HS$^2$) network is introduced to eliminate the falsely detected nodule candidates by tracking the appearance changes in continuous CT slices of each nodule candidate. The proposed framework is evaluated on the public Lung Nodule Analysis (LUNA16) challenge dataset. Our method is able to accurately detect lung nodules at high sensitivity and specificity and achieves $90.4%$ sensitivity with 1/8 false positive per scan which outperforms the state-of-the-art results $15.6%$.
Tasks	Lung Cancer Diagnosis
Published	2019-06-08
URL	https://arxiv.org/abs/1906.03467v2
PDF	https://arxiv.org/pdf/1906.03467v2.pdf
PWC	https://paperswithcode.com/paper/3dfpn-hs2-3d-feature-pyramid-network-based
Repo
Framework

Unsupervised learning-based long-term superpixel tracking


Title	Unsupervised learning-based long-term superpixel tracking
Authors	Pierre-Henri Conze, Florian Tilquin, Mathieu Lamard, Fabrice Heitz, Gwenolé Quellec
Abstract	Finding correspondences between structural entities decomposing images is of high interest for computer vision applications. In particular, we analyze how to accurately track superpixels - visual primitives generated by aggregating adjacent pixels sharing similar characteristics - over extended time periods relying on unsupervised learning and temporal integration. A two-step video processing pipeline dedicated to long-term superpixel tracking is proposed. First, unsupervised learning-based superpixel matching provides correspondences between consecutive and distant frames using new context-rich features extended from greyscale to multi-channel and forward-backward consistency contraints. Resulting elementary matches are then combined along multi-step paths running through the whole sequence with various inter-frame distances. This produces a large set of candidate long-term superpixel pairings upon which majority voting is performed. Video object tracking experiments demonstrate the accuracy of our elementary estimator against state-of-the-art methods and proves the ability of multi-step integration to provide accurate long-term superpixel matches compared to usual direct and sequential integration.
Tasks	Object Tracking, Video Object Tracking
Published	2019-02-25
URL	http://arxiv.org/abs/1902.09596v1
PDF	http://arxiv.org/pdf/1902.09596v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-learning-based-long-term
Repo
Framework

Efficient Symmetric Norm Regression via Linear Sketching


Title	Efficient Symmetric Norm Regression via Linear Sketching
Authors	Zhao Song, Ruosong Wang, Lin F. Yang, Hongyang Zhang, Peilin Zhong
Abstract	We provide efficient algorithms for overconstrained linear regression problems with size $n \times d$ when the loss function is a symmetric norm (a norm invariant under sign-flips and coordinate-permutations). An important class of symmetric norms are Orlicz norms, where for a function $G$ and a vector $y \in \mathbb{R}^n$, the corresponding Orlicz norm $\y_G$ is defined as the unique value $\alpha$ such that $\sum_{i=1}^n G(y_i/\alpha) = 1$. When the loss function is an Orlicz norm, our algorithm produces a $(1 + \varepsilon)$-approximate solution for an arbitrarily small constant $\varepsilon > 0$ in input-sparsity time, improving over the previously best-known algorithm which produces a $d \cdot \mathrm{polylog} n$-approximate solution. When the loss function is a general symmetric norm, our algorithm produces a $\sqrt{d} \cdot \mathrm{polylog} n \cdot \mathrm{mmc}(\ell)$-approximate solution in input-sparsity time, where $\mathrm{mmc}(\ell)$ is a quantity related to the symmetric norm under consideration. To the best of our knowledge, this is the first input-sparsity time algorithm with provable guarantees for the general class of symmetric norm regression problem. Our results shed light on resolving the universal sketching problem for linear regression, and the techniques might be of independent interest to numerical linear algebra problems more broadly.
Tasks
Published	2019-10-04
URL	https://arxiv.org/abs/1910.01788v2
PDF	https://arxiv.org/pdf/1910.01788v2.pdf
PWC	https://paperswithcode.com/paper/efficient-symmetric-norm-regression-via
Repo
Framework

Off-Policy Evaluation via Off-Policy Classification


Title	Off-Policy Evaluation via Off-Policy Classification
Authors	Alex Irpan, Kanishka Rao, Konstantinos Bousmalis, Chris Harris, Julian Ibarz, Sergey Levine
Abstract	In this work, we consider the problem of model selection for deep reinforcement learning (RL) in real-world environments. Typically, the performance of deep RL algorithms is evaluated via on-policy interactions with the target environment. However, comparing models in a real-world environment for the purposes of early stopping or hyperparameter tuning is costly and often practically infeasible. This leads us to examine off-policy policy evaluation (OPE) in such settings. We focus on OPE for value-based methods, which are of particular interest in deep RL, with applications like robotics, where off-policy algorithms based on Q-function estimation can often attain better sample complexity than direct policy optimization. Existing OPE metrics either rely on a model of the environment, or the use of importance sampling (IS) to correct for the data being off-policy. However, for high-dimensional observations, such as images, models of the environment can be difficult to fit and value-based methods can make IS hard to use or even ill-conditioned, especially when dealing with continuous action spaces. In this paper, we focus on the specific case of MDPs with continuous action spaces and sparse binary rewards, which is representative of many important real-world applications. We propose an alternative metric that relies on neither models nor IS, by framing OPE as a positive-unlabeled (PU) classification problem with the Q-function as the decision function. We experimentally show that this metric outperforms baselines on a number of tasks. Most importantly, it can reliably predict the relative performance of different policies in a number of generalization scenarios, including the transfer to the real-world of policies trained in simulation for an image-based robotic manipulation task.
Tasks	Model Selection
Published	2019-06-04
URL	https://arxiv.org/abs/1906.01624v3
PDF	https://arxiv.org/pdf/1906.01624v3.pdf
PWC	https://paperswithcode.com/paper/off-policy-evaluation-via-off-policy
Repo
Framework

Feature Engineering for Mid-Price Prediction with Deep Learning


Title	Feature Engineering for Mid-Price Prediction with Deep Learning
Authors	Adamantios Ntakaris, Giorgio Mirone, Juho Kanniainen, Moncef Gabbouj, Alexandros Iosifidis
Abstract	Mid-price movement prediction based on limit order book (LOB) data is a challenging task due to the complexity and dynamics of the LOB. So far, there have been very limited attempts for extracting relevant features based on LOB data. In this paper, we address this problem by designing a new set of handcrafted features and performing an extensive experimental evaluation on both liquid and illiquid stocks. More specifically, we implement a new set of econometrical features that capture statistical properties of the underlying securities for the task of mid-price prediction. Moreover, we develop a new experimental protocol for online learning that treats the task as a multi-objective optimization problem and predicts i) the direction of the next price movement and ii) the number of order book events that occur until the change takes place. In order to predict the mid-price movement, the features are fed into nine different deep learning models based on multi-layer perceptrons (MLP), convolutional neural networks (CNN) and long short-term memory (LSTM) neural networks. The performance of the proposed method is then evaluated on liquid and illiquid stocks, which are based on TotalView-ITCH US and Nordic stocks, respectively. For some stocks, results suggest that the correct choice of a feature set and a model can lead to the successful prediction of how long it takes to have a stock price movement.
Tasks	Feature Engineering
Published	2019-04-10
URL	https://arxiv.org/abs/1904.05384v3
PDF	https://arxiv.org/pdf/1904.05384v3.pdf
PWC	https://paperswithcode.com/paper/feature-engineering-for-mid-price-prediction
Repo
Framework

Bandit Multiclass Linear Classification: Efficient Algorithms for the Separable Case


Title	Bandit Multiclass Linear Classification: Efficient Algorithms for the Separable Case
Authors	Alina Beygelzimer, Dávid Pál, Balázs Szörényi, Devanathan Thiruvenkatachari, Chen-Yu Wei, Chicheng Zhang
Abstract	We study the problem of efficient online multiclass linear classification with bandit feedback, where all examples belong to one of $K$ classes and lie in the $d$-dimensional Euclidean space. Previous works have left open the challenge of designing efficient algorithms with finite mistake bounds when the data is linearly separable by a margin $\gamma$. In this work, we take a first step towards this problem. We consider two notions of linear separability: strong and weak. 1. Under the strong linear separability condition, we design an efficient algorithm that achieves a near-optimal mistake bound of $O\left( K/\gamma^2 \right)$. 2. Under the more challenging weak linear separability condition, we design an efficient algorithm with a mistake bound of $\min (2^{\widetilde{O}(K \log^2 (1/\gamma))}, 2^{\widetilde{O}(\sqrt{1/\gamma} \log K)})$. Our algorithm is based on kernel Perceptron, which is inspired by the work of (Klivans and Servedio, 2008) on improperly learning intersection of halfspaces.
Tasks
Published	2019-02-06
URL	https://arxiv.org/abs/1902.02244v2
PDF	https://arxiv.org/pdf/1902.02244v2.pdf
PWC	https://paperswithcode.com/paper/bandit-multiclass-linear-classification
Repo
Framework

A Human-Grounded Evaluation of SHAP for Alert Processing


Title	A Human-Grounded Evaluation of SHAP for Alert Processing
Authors	Hilde J. P. Weerts, Werner van Ipenburg, Mykola Pechenizkiy
Abstract	In the past years, many new explanation methods have been proposed to achieve interpretability of machine learning predictions. However, the utility of these methods in practical applications has not been researched extensively. In this paper we present the results of a human-grounded evaluation of SHAP, an explanation method that has been well-received in the XAI and related communities. In particular, we study whether this local model-agnostic explanation method can be useful for real human domain experts to assess the correctness of positive predictions, i.e. alerts generated by a classifier. We performed experimentation with three different groups of participants (159 in total), who had basic knowledge of explainable machine learning. We performed a qualitative analysis of recorded reflections of experiment participants performing alert processing with and without SHAP information. The results suggest that the SHAP explanations do impact the decision-making process, although the model’s confidence score remains to be a leading source of evidence. We statistically test whether there is a significant difference in task utility metrics between tasks for which an explanation was available and tasks in which it was not provided. As opposed to common intuitions, we did not find a significant difference in alert processing performance when a SHAP explanation is available compared to when it is not.
Tasks	Decision Making
Published	2019-07-07
URL	https://arxiv.org/abs/1907.03324v1
PDF	https://arxiv.org/pdf/1907.03324v1.pdf
PWC	https://paperswithcode.com/paper/a-human-grounded-evaluation-of-shap-for-alert
Repo
Framework

Towards Model-based Reinforcement Learning for Industry-near Environments


Title	Towards Model-based Reinforcement Learning for Industry-near Environments
Authors	Per-Arne Andersen, Morten Goodwin, Ole-Christoffer Granmo
Abstract	Deep reinforcement learning has over the past few years shown great potential in learning near-optimal control in complex simulated environments with little visible information. Rainbow (Q-Learning) and PPO (Policy Optimisation) have shown outstanding performance in a variety of tasks, including Atari 2600, MuJoCo, and Roboschool test suite. While these algorithms are fundamentally different, both suffer from high variance, low sample efficiency, and hyperparameter sensitivity that in practice, make these algorithms a no-go for critical operations in the industry. On the other hand, model-based reinforcement learning focuses on learning the transition dynamics between states in an environment. If these environment dynamics are adequately learned, a model-based approach is perhaps the most sample efficient method for learning agents to act in an environment optimally. The traits of model-based reinforcement are ideal for real-world environments where sampling is slow and for mission-critical operations. In the warehouse industry, there is an increasing motivation to minimise time and to maximise production. Currently, autonomous agents act suboptimally using handcrafted policies for significant portions of the state-space. In this paper, we present The Dreaming Variational Autoencoder v2 (DVAE-2), a model-based reinforcement learning algorithm that increases sample efficiency, hence enable algorithms with low sample efficiency function better in real-world environments. We introduce Deep Warehouse, a simulated environment for industry-near testing of autonomous agents in grid-based warehouses. Finally, we illustrate that DVAE-2 improves the sample efficiency for the Deep Warehouse compared to model-free methods.
Tasks	Q-Learning
Published	2019-07-27
URL	https://arxiv.org/abs/1907.11971v1
PDF	https://arxiv.org/pdf/1907.11971v1.pdf
PWC	https://paperswithcode.com/paper/towards-model-based-reinforcement-learning
Repo
Framework

FUSE: Multi-Faceted Set Expansion by Coherent Clustering of Skip-grams


Title	FUSE: Multi-Faceted Set Expansion by Coherent Clustering of Skip-grams
Authors	Wanzheng Zhu, Hongyu Gong, Jiaming Shen, Chao Zhang, Jingbo Shang, Suma Bhat, Jiawei Han
Abstract	Set expansion aims to expand a small set of seed entities into a complete set of relevant entities. Most existing approaches assume the input seed set is unambiguous and completely ignore the multi-faceted semantics of seed entities. As a result, given the seed set {“Canon”, “Sony”, “Nikon”}, previous methods return one mixed set of entities that are either Camera Brands or Japanese Companies. In this paper, we study the task of multi-faceted set expansion, which aims to capture all semantic facets in the seed set and return multiple sets of entities, one for each semantic facet. We propose an unsupervised framework, FUSE, which consists of three major components: (1) facet discovery module: identifies all semantic facets of each seed entity by extracting and clustering its skip-grams, and (2) facet fusion module: discovers shared semantic facets of the entire seed set by an optimization formulation, and (3) entity expansion module: expands each semantic facet by utilizing an iterative algorithm robust to skip-gram noise. Extensive experiments demonstrate that our algorithm, FUSE, can accurately identify multiple semantic facets of the seed set and generate quality entities for each facet.
Tasks
Published	2019-10-10
URL	https://arxiv.org/abs/1910.04345v2
PDF	https://arxiv.org/pdf/1910.04345v2.pdf
PWC	https://paperswithcode.com/paper/fuse-multi-faceted-set-expansion-by-coherent
Repo
Framework