July 28, 2019

3061 words 15 mins read

Paper Group ANR 357

Stochastic Neighbor Embedding separates well-separated clusters. Exemplar-Centered Supervised Shallow Parametric Data Embedding. Interpretation of Mammogram and Chest X-Ray Reports Using Deep Neural Networks - Preliminary Results. From Modal to Multimodal Ambiguities: a Classification Approach. 2D-3D Fully Convolutional Neural Networks for Cardiac …

Stochastic Neighbor Embedding separates well-separated clusters


Title	Stochastic Neighbor Embedding separates well-separated clusters
Authors	Uri Shaham, Stefan Steinerberger
Abstract	Stochastic Neighbor Embedding and its variants are widely used dimensionality reduction techniques – despite their popularity, no theoretical results are known. We prove that the optimal SNE embedding of well-separated clusters from high dimensions to any Euclidean space R^d manages to successfully separate the clusters in a quantitative way. The result also applies to a larger family of methods including a variant of t-SNE.
Tasks	Dimensionality Reduction
Published	2017-02-09
URL	http://arxiv.org/abs/1702.02670v2
PDF	http://arxiv.org/pdf/1702.02670v2.pdf
PWC	https://paperswithcode.com/paper/stochastic-neighbor-embedding-separates-well
Repo
Framework

Exemplar-Centered Supervised Shallow Parametric Data Embedding


Title	Exemplar-Centered Supervised Shallow Parametric Data Embedding
Authors	Martin Renqiang Min, Hongyu Guo, Dongjin Song
Abstract	Metric learning methods for dimensionality reduction in combination with k-Nearest Neighbors (kNN) have been extensively deployed in many classification, data embedding, and information retrieval applications. However, most of these approaches involve pairwise training data comparisons, and thus have quadratic computational complexity with respect to the size of training set, preventing them from scaling to fairly big datasets. Moreover, during testing, comparing test data against all the training data points is also expensive in terms of both computational cost and resources required. Furthermore, previous metrics are either too constrained or too expressive to be well learned. To effectively solve these issues, we present an exemplar-centered supervised shallow parametric data embedding model, using a Maximally Collapsing Metric Learning (MCML) objective. Our strategy learns a shallow high-order parametric embedding function and compares training/test data only with learned or precomputed exemplars, resulting in a cost function with linear computational complexity for both training and testing. We also empirically demonstrate, using several benchmark datasets, that for classification in two-dimensional embedding space, our approach not only gains speedup of kNN by hundreds of times, but also outperforms state-of-the-art supervised embedding approaches.
Tasks	Dimensionality Reduction, Information Retrieval, Metric Learning
Published	2017-02-21
URL	http://arxiv.org/abs/1702.06602v2
PDF	http://arxiv.org/pdf/1702.06602v2.pdf
PWC	https://paperswithcode.com/paper/exemplar-centered-supervised-shallow
Repo
Framework

Interpretation of Mammogram and Chest X-Ray Reports Using Deep Neural Networks - Preliminary Results


Title	Interpretation of Mammogram and Chest X-Ray Reports Using Deep Neural Networks - Preliminary Results
Authors	Hojjat Salehinejad, Shahrokh Valaee, Aren Mnatzakanian, Tim Dowdell, Joseph Barfett, Errol Colak
Abstract	Radiology reports are an important means of communication between radiologists and other physicians. These reports express a radiologist’s interpretation of a medical imaging examination and are critical in establishing a diagnosis and formulating a treatment plan. In this paper, we propose a Bi-directional convolutional neural network (Bi-CNN) model for the interpretation and classification of mammograms based on breast density and chest radiographic radiology reports based on the basis of chest pathology. The proposed approach helps to organize databases of radiology reports, retrieve them expeditiously, and evaluate the radiology report that could be used in an auditing system to decrease incorrect diagnoses. Our study revealed that the proposed Bi-CNN outperforms the random forest and the support vector machine methods.
Tasks
Published	2017-08-24
URL	http://arxiv.org/abs/1708.09254v3
PDF	http://arxiv.org/pdf/1708.09254v3.pdf
PWC	https://paperswithcode.com/paper/interpretation-of-mammogram-and-chest-x-ray
Repo
Framework


Title	From Modal to Multimodal Ambiguities: a Classification Approach
Authors	Maria Chiara Caschera, Fernando Ferri, Patrizia Grifoni
Abstract	This paper deals with classifying ambiguities for Multimodal Languages. It evolves the classifications and the methods of the literature on ambiguities for Natural Language and Visual Language, empirically defining an original classification of ambiguities for multimodal interaction using a linguistic perspective. This classification distinguishes between Semantic and Syntactic multimodal ambiguities and their subclasses, which are intercepted using a rule-based method implemented in a software module. The experimental results have achieved an accuracy of the obtained classification compared to the expected one, which are defined by the human judgment, of 94.6% for the semantic ambiguities classes, and 92.1% for the syntactic ambiguities classes.
Tasks
Published	2017-04-04
URL	http://arxiv.org/abs/1704.02841v1
PDF	http://arxiv.org/pdf/1704.02841v1.pdf
PWC	https://paperswithcode.com/paper/from-modal-to-multimodal-ambiguities-a
Repo
Framework

2D-3D Fully Convolutional Neural Networks for Cardiac MR Segmentation


Title	2D-3D Fully Convolutional Neural Networks for Cardiac MR Segmentation
Authors	Jay Patravali, Shubham Jain, Sasank Chilamkurthy
Abstract	In this paper, we develop a 2D and 3D segmentation pipelines for fully automated cardiac MR image segmentation using Deep Convolutional Neural Networks (CNN). Our models are trained end-to-end from scratch using the ACD Challenge 2017 dataset comprising of 100 studies, each containing Cardiac MR images in End Diastole and End Systole phase. We show that both our segmentation models achieve near state-of-the-art performance scores in terms of distance metrics and have convincing accuracy in terms of clinical parameters. A comparative analysis is provided by introducing a novel dice loss function and its combination with cross entropy loss. By exploring different network structures and comprehensive experiments, we discuss several key insights to obtain optimal model performance, which also is central to the theme of this challenge.
Tasks	Semantic Segmentation
Published	2017-07-31
URL	http://arxiv.org/abs/1707.09813v1
PDF	http://arxiv.org/pdf/1707.09813v1.pdf
PWC	https://paperswithcode.com/paper/2d-3d-fully-convolutional-neural-networks-for
Repo
Framework

Perceptual Generative Adversarial Networks for Small Object Detection


Title	Perceptual Generative Adversarial Networks for Small Object Detection
Authors	Jianan Li, Xiaodan Liang, Yunchao Wei, Tingfa Xu, Jiashi Feng, Shuicheng Yan
Abstract	Detecting small objects is notoriously challenging due to their low resolution and noisy representation. Existing object detection pipelines usually detect small objects through learning representations of all the objects at multiple scales. However, the performance gain of such ad hoc architectures is usually limited to pay off the computational cost. In this work, we address the small object detection problem by developing a single architecture that internally lifts representations of small objects to “super-resolved” ones, achieving similar characteristics as large objects and thus more discriminative for detection. For this purpose, we propose a new Perceptual Generative Adversarial Network (Perceptual GAN) model that improves small object detection through narrowing representation difference of small objects from the large ones. Specifically, its generator learns to transfer perceived poor representations of the small objects to super-resolved ones that are similar enough to real large objects to fool a competing discriminator. Meanwhile its discriminator competes with the generator to identify the generated representation and imposes an additional perceptual requirement - generated representations of small objects must be beneficial for detection purpose - on the generator. Extensive evaluations on the challenging Tsinghua-Tencent 100K and the Caltech benchmark well demonstrate the superiority of Perceptual GAN in detecting small objects, including traffic signs and pedestrians, over well-established state-of-the-arts.
Tasks	Object Detection, Small Object Detection
Published	2017-06-16
URL	http://arxiv.org/abs/1706.05274v2
PDF	http://arxiv.org/pdf/1706.05274v2.pdf
PWC	https://paperswithcode.com/paper/perceptual-generative-adversarial-networks
Repo
Framework

Optimization of Tree Ensembles


Title	Optimization of Tree Ensembles
Authors	Velibor V. Mišić
Abstract	Tree ensemble models such as random forests and boosted trees are among the most widely used and practically successful predictive models in applied machine learning and business analytics. Although such models have been used to make predictions based on exogenous, uncontrollable independent variables, they are increasingly being used to make predictions where the independent variables are controllable and are also decision variables. In this paper, we study the problem of tree ensemble optimization: given a tree ensemble that predicts some dependent variable using controllable independent variables, how should we set these variables so as to maximize the predicted value? We formulate the problem as a mixed-integer optimization problem. We theoretically examine the strength of our formulation, provide a hierarchy of approximate formulations with bounds on approximation quality and exploit the structure of the problem to develop two large-scale solution methods, one based on Benders decomposition and one based on iteratively generating tree split constraints. We test our methodology on real data sets, including two case studies in drug design and customized pricing, and show that our methodology can efficiently solve large-scale instances to near or full optimality, and outperforms solutions obtained by heuristic approaches. In our drug design case, we show how our approach can identify compounds that efficiently trade-off predicted performance and novelty with respect to existing, known compounds. In our customized pricing case, we show how our approach can efficiently determine optimal store-level prices under a random forest model that delivers excellent predictive accuracy.
Tasks
Published	2017-05-30
URL	https://arxiv.org/abs/1705.10883v2
PDF	https://arxiv.org/pdf/1705.10883v2.pdf
PWC	https://paperswithcode.com/paper/optimization-of-tree-ensembles
Repo
Framework

Machine Learning for the Geosciences: Challenges and Opportunities


Title	Machine Learning for the Geosciences: Challenges and Opportunities
Authors	Anuj Karpatne, Imme Ebert-Uphoff, Sai Ravela, Hassan Ali Babaie, Vipin Kumar
Abstract	Geosciences is a field of great societal relevance that requires solutions to several urgent problems facing our humanity and the planet. As geosciences enters the era of big data, machine learning (ML) – that has been widely successful in commercial domains – offers immense potential to contribute to problems in geosciences. However, problems in geosciences have several unique challenges that are seldom found in traditional applications, requiring novel problem formulations and methodologies in machine learning. This article introduces researchers in the machine learning (ML) community to these challenges offered by geoscience problems and the opportunities that exist for advancing both machine learning and geosciences. We first highlight typical sources of geoscience data and describe their properties that make it challenging to use traditional machine learning techniques. We then describe some of the common categories of geoscience problems where machine learning can play a role, and discuss some of the existing efforts and promising directions for methodological development in machine learning. We conclude by discussing some of the emerging research themes in machine learning that are applicable across all problems in the geosciences, and the importance of a deep collaboration between machine learning and geosciences for synergistic advancements in both disciplines.
Tasks
Published	2017-11-13
URL	http://arxiv.org/abs/1711.04708v1
PDF	http://arxiv.org/pdf/1711.04708v1.pdf
PWC	https://paperswithcode.com/paper/machine-learning-for-the-geosciences
Repo
Framework

Named Entity Recognition with stack residual LSTM and trainable bias decoding


Title	Named Entity Recognition with stack residual LSTM and trainable bias decoding
Authors	Quan Tran, Andrew MacKinlay, Antonio Jimeno Yepes
Abstract	Recurrent Neural Network models are the state-of-the-art for Named Entity Recognition (NER). We present two innovations to improve the performance of these models. The first innovation is the introduction of residual connections between the Stacked Recurrent Neural Network model to address the degradation problem of deep neural networks. The second innovation is a bias decoding mechanism that allows the trained system to adapt to non-differentiable and externally computed objectives, such as the entity-based F-measure. Our work improves the state-of-the-art results for both Spanish and English languages on the standard train/development/test split of the CoNLL 2003 Shared Task NER dataset.
Tasks	Named Entity Recognition
Published	2017-06-23
URL	http://arxiv.org/abs/1706.07598v2
PDF	http://arxiv.org/pdf/1706.07598v2.pdf
PWC	https://paperswithcode.com/paper/named-entity-recognition-with-stack-residual
Repo
Framework

ISLAND: In-Silico Prediction of Proteins Binding Affinity Using Sequence Descriptors


Title	ISLAND: In-Silico Prediction of Proteins Binding Affinity Using Sequence Descriptors
Authors	Wajid Arshad Abbasi, Fahad Ul Hassan, Adiba Yaseen, Fayyaz Ul Amir Afsar Minhas
Abstract	Determination of binding affinity of proteins in the formation of protein complexes requires sophisticated, expensive and time-consuming experimentation which can be replaced with computational methods. Most computational prediction techniques require protein structures which limit their applicability to protein complexes with known structures. In this work, we explore sequence based protein binding affinity prediction using machine learning. Our paper highlights the fact that the generalization performance of even the state of the art sequence-only predictor of binding affinity is far from satisfactory and that the development of effective and practical methods in this domain is still an open problem. We also propose a novel sequence-only predictor of binding affinity called ISLAND which gives better accuracy than existing methods over the same validation set as well as on external independent test dataset. A cloud-based webserver implementation of ISLAND and its Python code are available at the URL: http://faculty.pieas.edu.pk/fayyaz/software.html#island.
Tasks
Published	2017-11-22
URL	http://arxiv.org/abs/1711.10540v2
PDF	http://arxiv.org/pdf/1711.10540v2.pdf
PWC	https://paperswithcode.com/paper/island-in-silico-prediction-of-proteins
Repo
Framework

Graph-Cut RANSAC


Title	Graph-Cut RANSAC
Authors	Daniel Barath, Jiri Matas
Abstract	A novel method for robust estimation, called Graph-Cut RANSAC, GC-RANSAC in short, is introduced. To separate inliers and outliers, it runs the graph-cut algorithm in the local optimization (LO) step which is applied when a so-far-the-best model is found. The proposed LO step is conceptually simple, easy to implement, globally optimal and efficient. GC-RANSAC is shown experimentally, both on synthesized tests and real image pairs, to be more geometrically accurate than state-of-the-art methods on a range of problems, e.g. line fitting, homography, affine transformation, fundamental and essential matrix estimation. It runs in real-time for many problems at a speed approximately equal to that of the less accurate alternatives (in milliseconds on standard CPU).
Tasks
Published	2017-06-03
URL	http://arxiv.org/abs/1706.00984v2
PDF	http://arxiv.org/pdf/1706.00984v2.pdf
PWC	https://paperswithcode.com/paper/graph-cut-ransac
Repo
Framework

Direct Monocular Odometry Using Points and Lines


Title	Direct Monocular Odometry Using Points and Lines
Authors	Shichao Yang, Sebastian Scherer
Abstract	Most visual odometry algorithm for a monocular camera focuses on points, either by feature matching, or direct alignment of pixel intensity, while ignoring a common but important geometry entity: edges. In this paper, we propose an odometry algorithm that combines points and edges to benefit from the advantages of both direct and feature based methods. It works better in texture-less environments and is also more robust to lighting changes and fast motion by increasing the convergence basin. We maintain a depth map for the keyframe then in the tracking part, the camera pose is recovered by minimizing both the photometric error and geometric error to the matched edge in a probabilistic framework. In the mapping part, edge is used to speed up and increase stereo matching accuracy. On various public datasets, our algorithm achieves better or comparable performance than state-of-the-art monocular odometry methods. In some challenging texture-less environments, our algorithm reduces the state estimation error over 50%.
Tasks	Stereo Matching, Stereo Matching Hand, Visual Odometry
Published	2017-03-19
URL	http://arxiv.org/abs/1703.06380v1
PDF	http://arxiv.org/pdf/1703.06380v1.pdf
PWC	https://paperswithcode.com/paper/direct-monocular-odometry-using-points-and
Repo
Framework

Push and Pull Search for Solving Constrained Multi-objective Optimization Problems


Title	Push and Pull Search for Solving Constrained Multi-objective Optimization Problems
Authors	Zhun Fan, Wenji Li, Xinye Cai, Hui Li, Caimin Wei, Qingfu Zhang, Kalyanmoy Deb, Erik D. Goodman
Abstract	This paper proposes a push and pull search (PPS) framework for solving constrained multi-objective optimization problems (CMOPs). To be more specific, the proposed PPS divides the search process into two different stages, including the push and pull search stages. In the push stage, a multi-objective evolutionary algorithm (MOEA) is adopted to explore the search space without considering any constraints, which can help to get across infeasible regions very fast and approach the unconstrained Pareto front. Furthermore, the landscape of CMOPs with constraints can be probed and estimated in the push stage, which can be utilized to conduct the parameters setting for constraint-handling approaches applied in the pull stage. Then, a constrained multi-objective evolutionary algorithm (CMOEA) equipped with an improved epsilon constraint-handling is applied to pull the infeasible individuals achieved in the push stage to the feasible and non-dominated regions. Compared with other CMOEAs, the proposed PPS method can more efficiently get across infeasible regions and converge to the feasible and non-dominated regions by applying push and pull search strategies at different stages. To evaluate the performance regarding convergence and diversity, a set of benchmark CMOPs is used to test the proposed PPS and compare with other five CMOEAs, including MOEA/D-CDP, MOEA/D-SR, C-MOEA/D, MOEA/D-Epsilon and MOEA/D-IEpsilon. The comprehensive experimental results demonstrate that the proposed PPS achieves significantly better or competitive performance than the other five CMOEAs on most of the benchmark set.
Tasks
Published	2017-09-15
URL	http://arxiv.org/abs/1709.05915v1
PDF	http://arxiv.org/pdf/1709.05915v1.pdf
PWC	https://paperswithcode.com/paper/push-and-pull-search-for-solving-constrained
Repo
Framework

Lifelong Learning in Costly Feature Spaces


Title	Lifelong Learning in Costly Feature Spaces
Authors	Maria-Florina Balcan, Avrim Blum, Vaishnavh Nagarajan
Abstract	An important long-term goal in machine learning systems is to build learning agents that, like humans, can learn many tasks over their lifetime, and moreover use information from these tasks to improve their ability to do so efficiently. In this work, our goal is to provide new theoretical insights into the potential of this paradigm. In particular, we propose a lifelong learning framework that adheres to a novel notion of resource efficiency that is critical in many real-world domains where feature evaluations are costly. That is, our learner aims to reuse information from previously learned related tasks to learn future tasks in a feature-efficient manner. Furthermore, we consider novel combinatorial ways in which learning tasks can relate. Specifically, we design lifelong learning algorithms for two structurally different and widely used families of target functions: decision trees/lists and monomials/polynomials. We also provide strong feature-efficiency guarantees for these algorithms; in fact, we show that in order to learn future targets, we need only slightly more feature evaluations per training example than what is needed to predict on an arbitrary example using those targets. We also provide algorithms with guarantees in an agnostic model where not all the targets are related to each other. Finally, we also provide lower bounds on the performance of a lifelong learner in these models, which are in fact tight under some conditions.
Tasks
Published	2017-06-30
URL	http://arxiv.org/abs/1706.10271v1
PDF	http://arxiv.org/pdf/1706.10271v1.pdf
PWC	https://paperswithcode.com/paper/lifelong-learning-in-costly-feature-spaces
Repo
Framework

Exploiting random projections and sparsity with random forests and gradient boosting methods – Application to multi-label and multi-output learning, random forest model compression and leveraging input sparsity


Title	Exploiting random projections and sparsity with random forests and gradient boosting methods – Application to multi-label and multi-output learning, random forest model compression and leveraging input sparsity
Authors	Arnaud Joly
Abstract	Within machine learning, the supervised learning field aims at modeling the input-output relationship of a system, from past observations of its behavior. Decision trees characterize the input-output relationship through a series of nested $if-then-else$ questions, the testing nodes, leading to a set of predictions, the leaf nodes. Several of such trees are often combined together for state-of-the-art performance: random forest ensembles average the predictions of randomized decision trees trained independently in parallel, while tree boosting ensembles train decision trees sequentially to refine the predictions made by the previous ones. The emergence of new applications requires scalable supervised learning algorithms in terms of computational power and memory space with respect to the number of inputs, outputs, and observations without sacrificing accuracy. In this thesis, we identify three main areas where decision tree methods could be improved for which we provide and evaluate original algorithmic solutions: (i) learning over high dimensional output spaces, (ii) learning with large sample datasets and stringent memory constraints at prediction time and (iii) learning over high dimensional sparse input spaces.
Tasks	Model Compression
Published	2017-04-26
URL	http://arxiv.org/abs/1704.08067v1
PDF	http://arxiv.org/pdf/1704.08067v1.pdf
PWC	https://paperswithcode.com/paper/exploiting-random-projections-and-sparsity
Repo
Framework