July 29, 2019

2929 words 14 mins read

Paper Group ANR 41

Clustering Small Samples with Quality Guarantees: Adaptivity with One2all pps. Contemporary machine learning: a guide for practitioners in the physical sciences. Context-Aware Semantic Inpainting. A Digital Fuzzy Edge Detector for Color Images. UI-Net: Interactive Artificial Neural Networks for Iterative Image Segmentation Based on a User Model. Pa …

Clustering Small Samples with Quality Guarantees: Adaptivity with One2all pps


Title	Clustering Small Samples with Quality Guarantees: Adaptivity with One2all pps
Authors	Edith Cohen, Shiri Chechik, Haim Kaplan
Abstract	Clustering of data points is a fundamental tool in data analysis. We consider points $X$ in a relaxed metric space, where the triangle inequality holds within a constant factor. The {\em cost} of clustering $X$ by $Q$ is $V(Q)=\sum_{x\in X} d_{xQ}$. Two basic tasks, parametrized by $k \geq 1$, are {\em cost estimation}, which returns (approximate) $V(Q)$ for queries $Q$ such that $Q=k$ and {\em clustering}, which returns an (approximate) minimizer of $V(Q)$ of size $Q=k$. With very large data sets $X$, we seek efficient constructions of small samples that act as surrogates to the full data for performing these tasks. Existing constructions that provide quality guarantees are either worst-case, and unable to benefit from structure of real data sets, or make explicit strong assumptions on the structure. We show here how to avoid both these pitfalls using adaptive designs. At the core of our design is the {\em one2all} construction of multi-objective probability-proportional-to-size (pps) samples: Given a set $M$ of centroids and $\alpha \geq 1$, one2all efficiently assigns probabilities to points so that the clustering cost of {\em each} $Q$ with cost $V(Q) \geq V(M)/\alpha$ can be estimated well from a sample of size $O(\alpha M\epsilon^{-2})$. For cost queries, we can obtain worst-case sample size $O(k\epsilon^{-2})$ by applying one2all to a bicriteria approximation $M$, but we adaptively balance $M$ and $\alpha$ to further reduce sample size. For clustering, we design an adaptive wrapper that applies a base clustering algorithm to a sample $S$. Our wrapper uses the smallest sample that provides statistical guarantees that the quality of the clustering on the sample carries over to the full data set. We demonstrate experimentally the huge gains of using our adaptive instead of worst-case methods.
Tasks
Published	2017-06-12
URL	http://arxiv.org/abs/1706.03607v2
PDF	http://arxiv.org/pdf/1706.03607v2.pdf
PWC	https://paperswithcode.com/paper/clustering-small-samples-with-quality
Repo
Framework

Contemporary machine learning: a guide for practitioners in the physical sciences


Title	Contemporary machine learning: a guide for practitioners in the physical sciences
Authors	Brian K. Spears
Abstract	Machine learning is finding increasingly broad application in the physical sciences. This most often involves building a model relationship between a dependent, measurable output and an associated set of controllable, but complicated, independent inputs. We present a tutorial on current techniques in machine learning – a jumping-off point for interested researchers to advance their work. We focus on deep neural networks with an emphasis on demystifying deep learning. We begin with background ideas in machine learning and some example applications from current research in plasma physics. We discuss supervised learning techniques for modeling complicated functions, beginning with familiar regression schemes, then advancing to more sophisticated deep learning methods. We also address unsupervised learning and techniques for reducing the dimensionality of input spaces. Along the way, we describe methods for practitioners to help ensure that their models generalize from their training data to as-yet-unseen test data. We describe classes of tasks – predicting scalars, handling images, fitting time-series – and prepare the reader to choose an appropriate technique. We finally point out some limitations to modern machine learning and speculate on some ways that practitioners from the physical sciences may be particularly suited to help.
Tasks	Time Series
Published	2017-12-20
URL	http://arxiv.org/abs/1712.08523v1
PDF	http://arxiv.org/pdf/1712.08523v1.pdf
PWC	https://paperswithcode.com/paper/contemporary-machine-learning-a-guide-for
Repo
Framework

Context-Aware Semantic Inpainting


Title	Context-Aware Semantic Inpainting
Authors	Haofeng Li, Guanbin Li, Liang Lin, Yizhou Yu
Abstract	Recently image inpainting has witnessed rapid progress due to generative adversarial networks (GAN) that are able to synthesize realistic contents. However, most existing GAN-based methods for semantic inpainting apply an auto-encoder architecture with a fully connected layer, which cannot accurately maintain spatial information. In addition, the discriminator in existing GANs struggle to understand high-level semantics within the image context and yield semantically consistent content. Existing evaluation criteria are biased towards blurry results and cannot well characterize edge preservation and visual authenticity in the inpainting results. In this paper, we propose an improved generative adversarial network to overcome the aforementioned limitations. Our proposed GAN-based framework consists of a fully convolutional design for the generator which helps to better preserve spatial structures and a joint loss function with a revised perceptual loss to capture high-level semantics in the context. Furthermore, we also introduce two novel measures to better assess the quality of image inpainting results. Experimental results demonstrate that our method outperforms the state of the art under a wide range of criteria.
Tasks	Image Inpainting
Published	2017-12-21
URL	http://arxiv.org/abs/1712.07778v1
PDF	http://arxiv.org/pdf/1712.07778v1.pdf
PWC	https://paperswithcode.com/paper/context-aware-semantic-inpainting
Repo
Framework

A Digital Fuzzy Edge Detector for Color Images


Title	A Digital Fuzzy Edge Detector for Color Images
Authors	Yuan-Hang Zhang, Xie Li, Jing-Yun Xiao
Abstract	Edge detection is a classic problem in the field of image processing, which lays foundations for other tasks such as image segmentation. Conventionally, this operation is performed using gradient operators such as the Roberts or Sobel operator, which can discover local changes in intensity levels. These operators, however, perform poorly on low contrast images. In this paper, we propose an edge detector architecture for color images based on fuzzy theory and the Sobel operator. First, the R, G and B channels are extracted from an image and enhanced using fuzzy methods, in order to suppress noise and improve the contrast between the background and the objects. The Sobel operator is then applied to each of the channels, which are finally combined into an edge map of the origin image. Experimental results obtained through an FPGA-based implementation have proved the proposed method effective.
Tasks	Edge Detection, Semantic Segmentation
Published	2017-01-12
URL	http://arxiv.org/abs/1701.03364v2
PDF	http://arxiv.org/pdf/1701.03364v2.pdf
PWC	https://paperswithcode.com/paper/a-digital-fuzzy-edge-detector-for-color
Repo
Framework

UI-Net: Interactive Artificial Neural Networks for Iterative Image Segmentation Based on a User Model


Title	UI-Net: Interactive Artificial Neural Networks for Iterative Image Segmentation Based on a User Model
Authors	Mario Amrehn, Sven Gaube, Mathias Unberath, Frank Schebesch, Tim Horz, Maddalena Strumia, Stefan Steidl, Markus Kowarschik, Andreas Maier
Abstract	For complex segmentation tasks, fully automatic systems are inherently limited in their achievable accuracy for extracting relevant objects. Especially in cases where only few data sets need to be processed for a highly accurate result, semi-automatic segmentation techniques exhibit a clear benefit for the user. One area of application is medical image processing during an intervention for a single patient. We propose a learning-based cooperative segmentation approach which includes the computing entity as well as the user into the task. Our system builds upon a state-of-the-art fully convolutional artificial neural network (FCN) as well as an active user model for training. During the segmentation process, a user of the trained system can iteratively add additional hints in form of pictorial scribbles as seed points into the FCN system to achieve an interactive and precise segmentation result. The segmentation quality of interactive FCNs is evaluated. Iterative FCN approaches can yield superior results compared to networks without the user input channel component, due to a consistent improvement in segmentation quality after each interaction.
Tasks	Semantic Segmentation
Published	2017-09-11
URL	http://arxiv.org/abs/1709.03450v1
PDF	http://arxiv.org/pdf/1709.03450v1.pdf
PWC	https://paperswithcode.com/paper/ui-net-interactive-artificial-neural-networks
Repo
Framework

Paraphrase Generation with Deep Reinforcement Learning


Title	Paraphrase Generation with Deep Reinforcement Learning
Authors	Zichao Li, Xin Jiang, Lifeng Shang, Hang Li
Abstract	Automatic generation of paraphrases from a given sentence is an important yet challenging task in natural language processing (NLP), and plays a key role in a number of applications such as question answering, search, and dialogue. In this paper, we present a deep reinforcement learning approach to paraphrase generation. Specifically, we propose a new framework for the task, which consists of a \textit{generator} and an \textit{evaluator}, both of which are learned from data. The generator, built as a sequence-to-sequence learning model, can produce paraphrases given a sentence. The evaluator, constructed as a deep matching model, can judge whether two sentences are paraphrases of each other. The generator is first trained by deep learning and then further fine-tuned by reinforcement learning in which the reward is given by the evaluator. For the learning of the evaluator, we propose two methods based on supervised learning and inverse reinforcement learning respectively, depending on the type of available training data. Empirical study shows that the learned evaluator can guide the generator to produce more accurate paraphrases. Experimental results demonstrate the proposed models (the generators) outperform the state-of-the-art methods in paraphrase generation in both automatic evaluation and human evaluation.
Tasks	Paraphrase Generation, Question Answering
Published	2017-11-01
URL	http://arxiv.org/abs/1711.00279v3
PDF	http://arxiv.org/pdf/1711.00279v3.pdf
PWC	https://paperswithcode.com/paper/paraphrase-generation-with-deep-reinforcement
Repo
Framework

A Nuclear-norm Model for Multi-Frame Super-Resolution Reconstruction from Video Clips


Title	A Nuclear-norm Model for Multi-Frame Super-Resolution Reconstruction from Video Clips
Authors	Rui Zhao, Raymond H. Chan
Abstract	We propose a variational approach to obtain super-resolution images from multiple low-resolution frames extracted from video clips. First the displacement between the low-resolution frames and the reference frame are computed by an optical flow algorithm. Then a low-rank model is used to construct the reference frame in high-resolution by incorporating the information of the low-resolution frames. The model has two terms: a 2-norm data fidelity term and a nuclear-norm regularization term. Alternating direction method of multipliers is used to solve the model. Comparison of our methods with other models on synthetic and real video clips show that our resulting images are more accurate with less artifacts. It also provides much finer and discernable details.
Tasks	Multi-Frame Super-Resolution, Optical Flow Estimation, Super-Resolution
Published	2017-04-17
URL	http://arxiv.org/abs/1704.06196v1
PDF	http://arxiv.org/pdf/1704.06196v1.pdf
PWC	https://paperswithcode.com/paper/a-nuclear-norm-model-for-multi-frame-super
Repo
Framework

Propagating Uncertainty in Multi-Stage Bayesian Convolutional Neural Networks with Application to Pulmonary Nodule Detection


Title	Propagating Uncertainty in Multi-Stage Bayesian Convolutional Neural Networks with Application to Pulmonary Nodule Detection
Authors	Onur Ozdemir, Benjamin Woodward, Andrew A. Berlin
Abstract	Motivated by the problem of computer-aided detection (CAD) of pulmonary nodules, we introduce methods to propagate and fuse uncertainty information in a multi-stage Bayesian convolutional neural network (CNN) architecture. The question we seek to answer is “can we take advantage of the model uncertainty provided by one deep learning model to improve the performance of the subsequent deep learning models and ultimately of the overall performance in a multi-stage Bayesian deep learning architecture?". Our experiments show that propagating uncertainty through the pipeline enables us to improve the overall performance in terms of both final prediction accuracy and model confidence.
Tasks
Published	2017-12-01
URL	http://arxiv.org/abs/1712.00497v1
PDF	http://arxiv.org/pdf/1712.00497v1.pdf
PWC	https://paperswithcode.com/paper/propagating-uncertainty-in-multi-stage
Repo
Framework

On the Gap Between Strict-Saddles and True Convexity: An Omega(log d) Lower Bound for Eigenvector Approximation


Title	On the Gap Between Strict-Saddles and True Convexity: An Omega(log d) Lower Bound for Eigenvector Approximation
Authors	Max Simchowitz, Ahmed El Alaoui, Benjamin Recht
Abstract	We prove a \emph{query complexity} lower bound on rank-one principal component analysis (PCA). We consider an oracle model where, given a symmetric matrix $M \in \mathbb{R}^{d \times d}$, an algorithm is allowed to make $T$ \emph{exact} queries of the form $w^{(i)} = Mv^{(i)}$ for $i \in {1,\dots,T}$, where $v^{(i)}$ is drawn from a distribution which depends arbitrarily on the past queries and measurements ${v^{(j)},w^{(j)}}_{1 \le j \le i-1}$. We show that for a small constant $\epsilon$, any adaptive, randomized algorithm which can find a unit vector $\widehat{v}$ for which $\widehat{v}^{\top}M\widehat{v} \ge (1-\epsilon)\M$, with even small probability, must make $T = \Omega(\log d)$ queries. In addition to settling a widely-held folk conjecture, this bound demonstrates a fundamental gap between convex optimization and “strict-saddle” non-convex optimization of which PCA is a canonical example: in the former, first-order methods can have dimension-free iteration complexity, whereas in PCA, the iteration complexity of gradient-based methods must necessarily grow with the dimension. Our argument proceeds via a reduction to estimating the rank-one spike in a deformed Wigner model. We establish lower bounds for this model by developing a “truncated” analogue of the $\chi^2$ Bayes-risk lower bound of Chen et al.
Tasks
Published	2017-04-14
URL	http://arxiv.org/abs/1704.04548v1
PDF	http://arxiv.org/pdf/1704.04548v1.pdf
PWC	https://paperswithcode.com/paper/on-the-gap-between-strict-saddles-and-true
Repo
Framework

XOR-Sampling for Network Design with Correlated Stochastic Events


Title	XOR-Sampling for Network Design with Correlated Stochastic Events
Authors	Xiaojian Wu, Yexiang Xue, Bart Selman, Carla P. Gomes
Abstract	Many network optimization problems can be formulated as stochastic network design problems in which edges are present or absent stochastically. Furthermore, protective actions can guarantee that edges will remain present. We consider the problem of finding the optimal protection strategy under a budget limit in order to maximize some connectivity measurements of the network. Previous approaches rely on the assumption that edges are independent. In this paper, we consider a more realistic setting where multiple edges are not independent due to natural disasters or regional events that make the states of multiple edges stochastically correlated. We use Markov Random Fields to model the correlation and define a new stochastic network design framework. We provide a novel algorithm based on Sample Average Approximation (SAA) coupled with a Gibbs or XOR sampler. The experimental results on real road network data show that the policies produced by SAA with the XOR sampler have higher quality and lower variance compared to SAA with Gibbs sampler.
Tasks
Published	2017-05-23
URL	http://arxiv.org/abs/1705.08218v2
PDF	http://arxiv.org/pdf/1705.08218v2.pdf
PWC	https://paperswithcode.com/paper/xor-sampling-for-network-design-with
Repo
Framework

Understanding Task Design Trade-offs in Crowdsourced Paraphrase Collection


Title	Understanding Task Design Trade-offs in Crowdsourced Paraphrase Collection
Authors	Youxuan Jiang, Jonathan K. Kummerfeld, Walter S. Lasecki
Abstract	Linguistically diverse datasets are critical for training and evaluating robust machine learning systems, but data collection is a costly process that often requires experts. Crowdsourcing the process of paraphrase generation is an effective means of expanding natural language datasets, but there has been limited analysis of the trade-offs that arise when designing tasks. In this paper, we present the first systematic study of the key factors in crowdsourcing paraphrase collection. We consider variations in instructions, incentives, data domains, and workflows. We manually analyzed paraphrases for correctness, grammaticality, and linguistic diversity. Our observations provide new insight into the trade-offs between accuracy and diversity in crowd responses that arise as a result of task design, providing guidance for future paraphrase generation procedures.
Tasks	Paraphrase Generation
Published	2017-04-19
URL	http://arxiv.org/abs/1704.05753v2
PDF	http://arxiv.org/pdf/1704.05753v2.pdf
PWC	https://paperswithcode.com/paper/understanding-task-design-trade-offs-in
Repo
Framework

Practical Machine Learning for Cloud Intrusion Detection: Challenges and the Way Forward


Title	Practical Machine Learning for Cloud Intrusion Detection: Challenges and the Way Forward
Authors	Ram Shankar Siva Kumar, Andrew Wicker, Matt Swann
Abstract	Operationalizing machine learning based security detections is extremely challenging, especially in a continuously evolving cloud environment. Conventional anomaly detection does not produce satisfactory results for analysts that are investigating security incidents in the cloud. Model evaluation alone presents its own set of problems due to a lack of benchmark datasets. When deploying these detections, we must deal with model compliance, localization, and data silo issues, among many others. We pose the problem of “attack disruption” as a way forward in the security data science space. In this paper, we describe the framework, challenges, and open questions surrounding the successful operationalization of machine learning based security detections in a cloud environment and provide some insights on how we have addressed them.
Tasks	Anomaly Detection, Intrusion Detection
Published	2017-09-20
URL	http://arxiv.org/abs/1709.07095v1
PDF	http://arxiv.org/pdf/1709.07095v1.pdf
PWC	https://paperswithcode.com/paper/practical-machine-learning-for-cloud
Repo
Framework

Distributional Modeling on a Diet: One-shot Word Learning from Text Only


Title	Distributional Modeling on a Diet: One-shot Word Learning from Text Only
Authors	Su Wang, Stephen Roller, Katrin Erk
Abstract	We test whether distributional models can do one-shot learning of definitional properties from text only. Using Bayesian models, we find that first learning overarching structure in the known data, regularities in textual contexts and in properties, helps one-shot learning, and that individual context items can be highly informative. Our experiments show that our model can learn properties from a single exposure when given an informative utterance.
Tasks	One-Shot Learning
Published	2017-04-14
URL	http://arxiv.org/abs/1704.04550v4
PDF	http://arxiv.org/pdf/1704.04550v4.pdf
PWC	https://paperswithcode.com/paper/distributional-modeling-on-a-diet-one-shot
Repo
Framework

Model-Robust Counterfactual Prediction Method


Title	Model-Robust Counterfactual Prediction Method
Authors	Dave Zachariah, Petre Stoica
Abstract	We develop a novel method for counterfactual analysis based on observational data using prediction intervals for units under different exposures. Unlike methods that target heterogeneous or conditional average treatment effects of an exposure, the proposed approach aims to take into account the irreducible dispersions of counterfactual outcomes so as to quantify the relative impact of different exposures. The prediction intervals are constructed in a distribution-free and model-robust manner based on the conformal prediction approach. The computational obstacles to this approach are circumvented by leveraging properties of a tuning-free method that learns sparse additive predictor models for counterfactual outcomes. The method is illustrated using both real and synthetic data.
Tasks
Published	2017-05-19
URL	http://arxiv.org/abs/1705.07019v5
PDF	http://arxiv.org/pdf/1705.07019v5.pdf
PWC	https://paperswithcode.com/paper/model-robust-counterfactual-prediction-method
Repo
Framework

Temporal Convolution Based Action Proposal: Submission to ActivityNet 2017


Title	Temporal Convolution Based Action Proposal: Submission to ActivityNet 2017
Authors	Tianwei Lin, Xu Zhao, Zheng Shou
Abstract	In this notebook paper, we describe our approach in the submission to the temporal action proposal (task 3) and temporal action localization (task 4) of ActivityNet Challenge hosted at CVPR 2017. Since the accuracy in action classification task is already very high (nearly 90% in ActivityNet dataset), we believe that the main bottleneck for temporal action localization is the quality of action proposals. Therefore, we mainly focus on the temporal action proposal task and propose a new proposal model based on temporal convolutional network. Our approach achieves the state-of-the-art performances on both temporal action proposal task and temporal action localization task.
Tasks	Action Classification, Action Localization, Temporal Action Localization
Published	2017-07-21
URL	http://arxiv.org/abs/1707.06750v3
PDF	http://arxiv.org/pdf/1707.06750v3.pdf
PWC	https://paperswithcode.com/paper/temporal-convolution-based-action-proposal
Repo
Framework