January 30, 2020

3169 words 15 mins read

Paper Group ANR 480

Analysis of Ward’s Method. MIRA: A Computational Neuro-Based Cognitive Architecture Applied to Movie Recommender Systems. Defending Against Adversarial Iris Examples Using Wavelet Decomposition. Generalized Resilience and Robust Statistics. Labeler-hot Detection of EEG Epileptic Transients. Contract Statements Knowledge Service for Chatbots. Non-Ga …

Analysis of Ward’s Method


Title	Analysis of Ward’s Method
Authors	Anna Großwendt, Heiko Röglin, Melanie Schmidt
Abstract	We study Ward’s method for the hierarchical $k$-means problem. This popular greedy heuristic is based on the \emph{complete linkage} paradigm: Starting with all data points as singleton clusters, it successively merges two clusters to form a clustering with one cluster less. The pair of clusters is chosen to (locally) minimize the $k$-means cost of the clustering in the next step. Complete linkage algorithms are very popular for hierarchical clustering problems, yet their theoretical properties have been studied relatively little. For the Euclidean $k$-center problem, Ackermann et al. show that the $k$-clustering in the hierarchy computed by complete linkage has a worst-case approximation ratio of $\Theta(\log k)$. If the data lies in $\mathbb{R}^d$ for constant dimension $d$, the guarantee improves to $\mathcal{O}(1)$, but the $\mathcal{O}$-notation hides a linear dependence on $d$. Complete linkage for $k$-median or $k$-means has not been analyzed so far. In this paper, we show that Ward’s method computes a $2$-approximation with respect to the $k$-means objective function if the optimal $k$-clustering is well separated. If additionally the optimal clustering also satisfies a balance condition, then Ward’s method fully recovers the optimum solution. These results hold in arbitrary dimension. We accompany our positive results with a lower bound of $\Omega((3/2)^d)$ for data sets in $\mathbb{R}^d$ that holds if no separation is guaranteed, and with lower bounds when the guaranteed separation is not sufficiently strong. Finally, we show that Ward produces an $\mathcal{O}(1)$-approximative clustering for one-dimensional data sets.
Tasks
Published	2019-07-11
URL	https://arxiv.org/abs/1907.05094v1
PDF	https://arxiv.org/pdf/1907.05094v1.pdf
PWC	https://paperswithcode.com/paper/analysis-of-wards-method
Repo
Framework

MIRA: A Computational Neuro-Based Cognitive Architecture Applied to Movie Recommender Systems


Title	MIRA: A Computational Neuro-Based Cognitive Architecture Applied to Movie Recommender Systems
Authors	Mariana B. Santos, Amanda M. Lima, Lucas A. Silva, Felipe S. Vargas, Guilherme A. Wachs-Lopes, Paulo S. Rodrigues
Abstract	The human mind is still an unknown process of neuroscience in many aspects. Nevertheless, for decades the scientific community has proposed computational models that try to simulate their parts, specific applications, or their behavior in different situations. The most complete model in this line is undoubtedly the LIDA model, proposed by Stan Franklin with the aim of serving as a generic computational architecture for several applications. The present project is inspired by the LIDA model to apply it to the process of movie recommendation, the model called MIRA (Movie Intelligent Recommender Agent) presented percentages of precision similar to a traditional model when submitted to the same assay conditions. Moreover, the proposed model reinforced the precision indexes when submitted to tests with volunteers, proving once again its performance as a cognitive model, when executed with small data volumes. Considering that the proposed model achieved a similar behavior to the traditional models under conditions expected to be similar for natural systems, it can be said that MIRA reinforces the applicability of LIDA as a path to be followed for the study and generation of computational agents inspired by neural behaviors.
Tasks	Recommendation Systems
Published	2019-02-25
URL	http://arxiv.org/abs/1902.09291v2
PDF	http://arxiv.org/pdf/1902.09291v2.pdf
PWC	https://paperswithcode.com/paper/mira-a-computational-neuro-based-cognitive
Repo
Framework

Defending Against Adversarial Iris Examples Using Wavelet Decomposition


Title	Defending Against Adversarial Iris Examples Using Wavelet Decomposition
Authors	Sobhan Soleymani, Ali Dabouei, Jeremy Dawson, Nasser M. Nasrabadi
Abstract	Deep neural networks have presented impressive performance in biometric applications. However, their performance is highly at risk when facing carefully crafted input samples known as adversarial examples. In this paper, we present three defense strategies to detect adversarial iris examples. These defense strategies are based on wavelet domain denoising of the input examples by investigating each wavelet sub-band and removing the sub-bands that are most affected by the adversary. The first proposed defense strategy reconstructs multiple denoised versions of the input example through manipulating the mid- and high-frequency components of the wavelet domain representation of the input example and makes a decision upon the classification result of the majority of the denoised examples. The second and third proposed defense strategies aim to denoise each wavelet domain sub-band and determine the sub-bands that are most likely affected by the adversary using the reconstruction error computed for each sub-band. We test the performance of the proposed defense strategies against several attack scenarios and compare the results with five state of the art defense strategies.
Tasks	Denoising
Published	2019-08-08
URL	https://arxiv.org/abs/1908.03176v1
PDF	https://arxiv.org/pdf/1908.03176v1.pdf
PWC	https://paperswithcode.com/paper/defending-against-adversarial-iris-examples
Repo
Framework

Generalized Resilience and Robust Statistics


Title	Generalized Resilience and Robust Statistics
Authors	Banghua Zhu, Jiantao Jiao, Jacob Steinhardt
Abstract	Robust statistics traditionally focuses on outliers, or perturbations in total variation distance. However, a dataset could be corrupted in many other ways, such as systematic measurement errors and missing covariates. We generalize the robust statistics approach to consider perturbations under any Wasserstein distance, and show that robust estimation is possible whenever a distribution’s population statistics are robust under a certain family of friendly perturbations. This generalizes a property called resilience previously employed in the special case of mean estimation with outliers. We justify the generalized resilience property by showing that it holds under moment or hypercontractive conditions. Even in the total variation case, these subsume conditions in the literature for mean estimation, regression, and covariance estimation; the resulting analysis simplifies and sometimes improves these known results in both population limit and finite-sample rate. Our robust estimators are based on minimum distance (MD) functionals (Donoho and Liu, 1988), which project onto a set of distributions under a discrepancy related to the perturbation. We present two approaches for designing MD estimators with good finite-sample rates: weakening the discrepancy and expanding the set of distributions. We also present connections to Gao et al. (2019)‘s recent analysis of generative adversarial networks for robust estimation.
Tasks
Published	2019-09-19
URL	https://arxiv.org/abs/1909.08755v1
PDF	https://arxiv.org/pdf/1909.08755v1.pdf
PWC	https://paperswithcode.com/paper/generalized-resilience-and-robust-statistics
Repo
Framework

Labeler-hot Detection of EEG Epileptic Transients


Title	Labeler-hot Detection of EEG Epileptic Transients
Authors	Lukasz Czekaj, Wojciech Ziembla, Pawel Jezierski, Pawel Swiniarski, Anna Kolodziejak, Pawel Ogniewski, Pawel Niedbalski, Anna Jezierska, Daniel Wesierski
Abstract	Preventing early progression of epilepsy and so the severity of seizures requires an effective diagnosis. Epileptic transients indicate the ability to develop seizures but humans overlook such brief events in an electroencephalogram (EEG) what compromises patient treatment. Traditionally, training of the EEG event detection algorithms has relied on ground truth labels, obtained from the consensus of the majority of labelers. In this work, we go beyond labeler consensus on EEG data. Our event descriptor integrates EEG signal features with one-hot encoded labeler category that is a key to improved generalization performance. Notably, boosted decision trees take advantage of singly-labeled but more varied training sets. Our quantitative experiments show the proposed labeler-hot epileptic event detector consistently outperforms a consensus-trained detector and maintains confidence bounds of the detection. The results on our infant EEG recordings suggest datasets can gain higher event variety faster and thus better performance by shifting available human effort from consensus-oriented to separate labeling when labels include both, the event and the labeler category.
Tasks	EEG
Published	2019-03-11
URL	https://arxiv.org/abs/1903.04337v3
PDF	https://arxiv.org/pdf/1903.04337v3.pdf
PWC	https://paperswithcode.com/paper/labeler-hot-detection-of-eeg-epileptic
Repo
Framework

Contract Statements Knowledge Service for Chatbots


Title	Contract Statements Knowledge Service for Chatbots
Authors	Boris Ruf, Matteo Sammarco, Marcin Detyniecki
Abstract	Towards conversational agents that are capable of handling more complex questions on contractual conditions, formalizing contract statements in a machine readable way is crucial. However, constructing a formal model which captures the full scope of a contract proves difficult due to the overall complexity its set of rules represent. Instead, this paper presents a top-down approach to the problem. After identifying the most relevant contract statements, we model their underlying rules in a novel knowledge engineering method. A user-friendly tool we developed for this purpose allows to do so easily and at scale. Then, we expose the statements as service so they can get smoothly integrated in any chatbot framework.
Tasks	Chatbot
Published	2019-10-10
URL	https://arxiv.org/abs/1910.04424v1
PDF	https://arxiv.org/pdf/1910.04424v1.pdf
PWC	https://paperswithcode.com/paper/contract-statements-knowledge-service-for
Repo
Framework

Non-Gaussian processes and neural networks at finite widths


Title	Non-Gaussian processes and neural networks at finite widths
Authors	Sho Yaida
Abstract	Gaussian processes are ubiquitous in nature and engineering. A case in point is a class of neural networks in the infinite-width limit, whose priors correspond to Gaussian processes. Here we perturbatively extend this correspondence to finite-width neural networks, yielding non-Gaussian processes as priors. The methodology developed herein allows us to track the flow of preactivation distributions by progressively integrating out random variables from lower to higher layers, reminiscent of renormalization-group flow. We further develop a perturbative procedure to perform Bayesian inference with weakly non-Gaussian priors.
Tasks	Bayesian Inference, Gaussian Processes
Published	2019-09-30
URL	https://arxiv.org/abs/1910.00019v1
PDF	https://arxiv.org/pdf/1910.00019v1.pdf
PWC	https://paperswithcode.com/paper/non-gaussian-processes-and-neural-networks-at
Repo
Framework

Aggregation Signature for Small Object Tracking


Title	Aggregation Signature for Small Object Tracking
Authors	Chunlei Liu, Wenrui Ding, Jinyu Yang, Vittorio Murino, Baochang Zhang, Jungong Han, Guodong Guo
Abstract	Small object tracking becomes an increasingly important task, which however has been largely unexplored in computer vision. The great challenges stem from the facts that: 1) small objects show extreme vague and variable appearances, and 2) they tend to be lost easier as compared to normal-sized ones due to the shaking of lens. In this paper, we propose a novel aggregation signature suitable for small object tracking, especially aiming for the challenge of sudden and large drift. We make three-fold contributions in this work. First, technically, we propose a new descriptor, named aggregation signature, based on saliency, able to represent highly distinctive features for small objects. Second, theoretically, we prove that the proposed signature matches the foreground object more accurately with a high probability. Third, experimentally, the aggregation signature achieves a high performance on multiple datasets, outperforming the state-of-the-art methods by large margins. Moreover, we contribute with two newly collected benchmark datasets, i.e., small90 and small112, for visually small object tracking. The datasets will be available in https://github.com/bczhangbczhang/.
Tasks	Object Tracking
Published	2019-10-24
URL	https://arxiv.org/abs/1910.10859v1
PDF	https://arxiv.org/pdf/1910.10859v1.pdf
PWC	https://paperswithcode.com/paper/aggregation-signature-for-small-object
Repo
Framework

A Joint Named-Entity Recognizer for Heterogeneous Tag-sets Using a Tag Hierarchy


Title	A Joint Named-Entity Recognizer for Heterogeneous Tag-sets Using a Tag Hierarchy
Authors	Genady Beryozkin, Yoel Drori, Oren Gilon, Tzvika Hartman, Idan Szpektor
Abstract	We study a variant of domain adaptation for named-entity recognition where multiple, heterogeneously tagged training sets are available. Furthermore, the test tag-set is not identical to any individual training tag-set. Yet, the relations between all tags are provided in a tag hierarchy, covering the test tags as a combination of training tags. This setting occurs when various datasets are created using different annotation schemes. This is also the case of extending a tag-set with a new tag by annotating only the new tag in a new dataset. We propose to use the given tag hierarchy to jointly learn a neural network that shares its tagging layer among all tag-sets. We compare this model to combining independent models and to a model based on the multitasking approach. Our experiments show the benefit of the tag-hierarchy model, especially when facing non-trivial consolidation of tag-sets.
Tasks	Domain Adaptation, Named Entity Recognition
Published	2019-05-22
URL	https://arxiv.org/abs/1905.09135v2
PDF	https://arxiv.org/pdf/1905.09135v2.pdf
PWC	https://paperswithcode.com/paper/a-joint-named-entity-recognizer-for
Repo
Framework

Live Illumination Decomposition of Videos


Title	Live Illumination Decomposition of Videos
Authors	Abhimitra Meka, Mohammad Shafiei, Michael Zollhoefer, Christian Richardt, Christian Theobalt
Abstract	We propose the first approach for the decomposition of a monocular color video into direct and indirect illumination components in real-time. We retrieve, in separate layers, the contribution made to the scene appearance by the scene reflectance, the light sources and the reflections from various coherent scene regions to one another. Existing techniques that invert global light transport require image capture under multiplexed controlled lighting, or only enable the decomposition of a single image at slow off-line frame rates. In contrast, our approach works for regular videos and produces temporally coherent decomposition layers at real-time frame rates. At the core of our approach are several sparsity priors that enable the estimation of the per-pixel direct and indirect illumination layers based on a small set of jointly estimated base reflectance colors. The resulting variational decomposition problem uses a new formulation based on sparse and dense sets of non-linear equations that we solve efficiently using a novel alternating data-parallel optimization strategy. We evaluate our approach qualitatively and quantitatively, and show improvements over the state of the art in this field, in both quality and runtime. In addition, we demonstrate various real-time appearance editing applications for videos with consistent illumination.
Tasks
Published	2019-08-06
URL	https://arxiv.org/abs/1908.01961v1
PDF	https://arxiv.org/pdf/1908.01961v1.pdf
PWC	https://paperswithcode.com/paper/live-illumination-decomposition-of-videos
Repo
Framework

Learning Arbitrary Quantities of Interest from Expensive Black-Box Functions through Bayesian Sequential Optimal Design


Title	Learning Arbitrary Quantities of Interest from Expensive Black-Box Functions through Bayesian Sequential Optimal Design
Authors	Piyush Pandita, Nimish Awalgaonkar, Ilias Bilionis, Jitesh Panchal
Abstract	Estimating arbitrary quantities of interest (QoIs) that are non-linear operators of complex, expensive-to-evaluate, black-box functions is a challenging problem due to missing domain knowledge and finite budgets. Bayesian optimal design of experiments (BODE) is a family of methods that identify an optimal design of experiments (DOE) under different contexts, using only in a limited number of function evaluations. Under BODE methods, sequential design of experiments (SDOE) accomplishes this task by selecting an optimal sequence of experiments while using data-driven probabilistic surrogate models instead of the expensive black-box function. Probabilistic predictions from the surrogate model are used to define an information acquisition function (IAF) which quantifies the marginal value contributed or the expected information gained by a hypothetical experiment. The next experiment is selected by maximizing the IAF. A generally applicable IAF is the expected information gain (EIG) about a QoI as captured by the expectation of the Kullback-Leibler divergence between the predictive distribution of the QoI after doing a hypothetical experiment and the current predictive distribution about the same QoI. We model the underlying information source as a fully-Bayesian, non-stationary Gaussian process (FBNSGP), and derive an approximation of the information gain of a hypothetical experiment about an arbitrary QoI conditional on the hyper-parameters The EIG about the same QoI is estimated by sample averages to integrate over the posterior of the hyper-parameters and the potential experimental outcomes. We demonstrate the performance of our method in four numerical examples and a practical engineering problem of steel wire manufacturing. The method is compared to two classic SDOE methods: random sampling and uncertainty sampling.
Tasks
Published	2019-12-16
URL	https://arxiv.org/abs/1912.07366v1
PDF	https://arxiv.org/pdf/1912.07366v1.pdf
PWC	https://paperswithcode.com/paper/learning-arbitrary-quantities-of-interest
Repo
Framework

Progressive Learning of Low-Precision Networks


Title	Progressive Learning of Low-Precision Networks
Authors	Zhengguang Zhou, Wengang Zhou, Xutao Lv, Xuan Huang, Xiaoyu Wang, Houqiang Li
Abstract	Recent years have witnessed the great advance of deep learning in a variety of vision tasks. Many state-of-the-art deep neural networks suffer from large size and high complexity, which makes it difficult to deploy in resource-limited platforms such as mobile devices. To this end, low-precision neural networks are widely studied which quantize weights or activations into the low-bit format. Though being efficient, low-precision networks are usually hard to train and encounter severe accuracy degradation. In this paper, we propose a new training strategy through expanding low-precision networks during training and removing the expanded parts for network inference. First, we equip each low-precision convolutional layer with an ancillary full-precision convolutional layer based on a low-precision network structure, which could guide the network to good local minima. Second, a decay method is introduced to reduce the output of the added full-precision convolution gradually, which keeps the resulted topology structure the same to the original low-precision one. Experiments on SVHN, CIFAR and ILSVRC-2012 datasets prove that the proposed method can bring faster convergence and higher accuracy for low-precision neural networks.
Tasks
Published	2019-05-28
URL	https://arxiv.org/abs/1905.11781v1
PDF	https://arxiv.org/pdf/1905.11781v1.pdf
PWC	https://paperswithcode.com/paper/progressive-learning-of-low-precision
Repo
Framework

HAMBox: Delving into Online High-quality Anchors Mining for Detecting Outer Faces


Title	HAMBox: Delving into Online High-quality Anchors Mining for Detecting Outer Faces
Authors	Yang Liu, Xu Tang, Xiang Wu, Junyu Han, Jingtuo Liu, Errui Ding
Abstract	Current face detectors utilize anchors to frame a multi-task learning problem which combines classification and bounding box regression. Effective anchor design and anchor matching strategy enable face detectors to localize faces under large pose and scale variations. However, we observe that more than 80% correctly predicted bounding boxes are regressed from the unmatched anchors (the IoUs between anchors and target faces are lower than a threshold) in the inference phase. It indicates that these unmatched anchors perform excellent regression ability, but the existing methods neglect to learn from them. In this paper, we propose an Online High-quality Anchor Mining Strategy (HAMBox), which explicitly helps outer faces compensate with high-quality anchors. Our proposed HAMBox method could be a general strategy for anchor-based single-stage face detection. Experiments on various datasets, including WIDER FACE, FDDB, AFW and PASCAL Face, demonstrate the superiority of the proposed method. Furthermore, our team win the championship on the Face Detection test track of WIDER Face and Pedestrian Challenge 2019. We will release the codes with PaddlePaddle.
Tasks	Face Detection, Multi-Task Learning
Published	2019-12-19
URL	https://arxiv.org/abs/1912.09231v1
PDF	https://arxiv.org/pdf/1912.09231v1.pdf
PWC	https://paperswithcode.com/paper/hambox-delving-into-online-high-quality
Repo
Framework

Evolutionary Dynamic Multi-objective Optimization Via Regression Transfer Learning


Title	Evolutionary Dynamic Multi-objective Optimization Via Regression Transfer Learning
Authors	Zhenzhong Wang, Min Jiang, Xing Gao, Liang Feng, Weizhen Hu, Kay Chen Tan
Abstract	Dynamic multi-objective optimization problems (DMOPs) remain a challenge to be settled, because of conflicting objective functions change over time. In recent years, transfer learning has been proven to be a kind of effective approach in solving DMOPs. In this paper, a novel transfer learning based dynamic multi-objective optimization algorithm (DMOA) is proposed called regression transfer learning prediction based DMOA (RTLP-DMOA). The algorithm aims to generate an excellent initial population to accelerate the evolutionary process and improve the evolutionary performance in solving DMOPs. When an environmental change is detected, a regression transfer learning prediction model is constructed by reusing the historical population, which can predict objective values. Then, with the assistance of this prediction model, some high-quality solutions with better predicted objective values are selected as the initial population, which can improve the performance of the evolutionary process. We compare the proposed algorithm with three state-of-the-art algorithms on benchmark functions. Experimental results indicate that the proposed algorithm can significantly enhance the performance of static multi-objective optimization algorithms and is competitive in convergence and diversity.
Tasks	Transfer Learning
Published	2019-10-19
URL	https://arxiv.org/abs/1910.08753v2
PDF	https://arxiv.org/pdf/1910.08753v2.pdf
PWC	https://paperswithcode.com/paper/evolutionary-dynamic-multi-objective
Repo
Framework

Definitions and Semantic Simulations Based on Object-Oriented Analysis and Modeling


Title	Definitions and Semantic Simulations Based on Object-Oriented Analysis and Modeling
Authors	Robert B. Allen
Abstract	We have proposed going beyond traditional ontologies to use rich semantics implemented in programming languages for modeling. In this paper, we discuss the application of executable semantic models to two examples, first a structured definition of a waterfall and second the cardiopulmonary system. We examine the components of these models and the way those components interact. Ultimately, such models should provide the basis for direct representation.
Tasks
Published	2019-12-31
URL	https://arxiv.org/abs/1912.13186v1
PDF	https://arxiv.org/pdf/1912.13186v1.pdf
PWC	https://paperswithcode.com/paper/definitions-and-semantic-simulations-based-on
Repo
Framework