July 29, 2019

3024 words 15 mins read

Paper Group ANR 67

Training Quantized Nets: A Deeper Understanding. Exploiting Color Name Space for Salient Object Detection. A Guided Spatial Transformer Network for Histology Cell Differentiation. A Study on the Extraction and Analysis of a Large Set of Eye Movement Features during Reading. Regulating Highly Automated Robot Ecologies: Insights from Three User Studi …

Training Quantized Nets: A Deeper Understanding


Title	Training Quantized Nets: A Deeper Understanding
Authors	Hao Li, Soham De, Zheng Xu, Christoph Studer, Hanan Samet, Tom Goldstein
Abstract	Currently, deep neural networks are deployed on low-power portable devices by first training a full-precision model using powerful hardware, and then deriving a corresponding low-precision model for efficient inference on such systems. However, training models directly with coarsely quantized weights is a key step towards learning on embedded platforms that have limited computing resources, memory capacity, and power consumption. Numerous recent publications have studied methods for training quantized networks, but these studies have mostly been empirical. In this work, we investigate training methods for quantized neural networks from a theoretical viewpoint. We first explore accuracy guarantees for training methods under convexity assumptions. We then look at the behavior of these algorithms for non-convex problems, and show that training algorithms that exploit high-precision representations have an important greedy search phase that purely quantized training methods lack, which explains the difficulty of training using low-precision arithmetic.
Tasks
Published	2017-06-07
URL	http://arxiv.org/abs/1706.02379v3
PDF	http://arxiv.org/pdf/1706.02379v3.pdf
PWC	https://paperswithcode.com/paper/training-quantized-nets-a-deeper
Repo
Framework

Exploiting Color Name Space for Salient Object Detection


Title	Exploiting Color Name Space for Salient Object Detection
Authors	Jing Lou, Huan Wang, Longtao Chen, Fenglei Xu, Qingyuan Xia, Wei Zhu, Mingwu Ren
Abstract	In this paper, we will investigate the contribution of color names for the task of salient object detection. An input image is first converted to color name space, which is consisted of 11 probabilistic channels. By exploiting a surroundedness cue, we obtain a saliency map through a linear combination of a set of sequential attention maps. To overcome the limitation of only using the surroundedness cue, two global cues with respect to color names are invoked to guide the computation of a weighted saliency map. Finally, we integrate the above two saliency maps into a unified framework to generate the final result. In addition, an improved post-processing procedure is introduced to effectively suppress image backgrounds while uniformly highlight salient objects. Experimental results show that the proposed model produces more accurate saliency maps and performs well against twenty-one saliency models in terms of three evaluation metrics on three public data sets.
Tasks	Object Detection, Salient Object Detection
Published	2017-03-27
URL	https://arxiv.org/abs/1703.08912v2
PDF	https://arxiv.org/pdf/1703.08912v2.pdf
PWC	https://paperswithcode.com/paper/exploiting-color-name-space-for-salient
Repo
Framework

A Guided Spatial Transformer Network for Histology Cell Differentiation


Title	A Guided Spatial Transformer Network for Histology Cell Differentiation
Authors	Marc Aubreville, Maximilian Krappmann, Christof Bertram, Robert Klopfleisch, Andreas Maier
Abstract	Identification and counting of cells and mitotic figures is a standard task in diagnostic histopathology. Due to the large overall cell count on histological slides and the potential sparse prevalence of some relevant cell types or mitotic figures, retrieving annotation data for sufficient statistics is a tedious task and prone to a significant error in assessment. Automatic classification and segmentation is a classic task in digital pathology, yet it is not solved to a sufficient degree. We present a novel approach for cell and mitotic figure classification, based on a deep convolutional network with an incorporated Spatial Transformer Network. The network was trained on a novel data set with ten thousand mitotic figures, about ten times more than previous data sets. The algorithm is able to derive the cell class (mitotic tumor cells, non-mitotic tumor cells and granulocytes) and their position within an image. The mean accuracy of the algorithm in a five-fold cross-validation is 91.45%. In our view, the approach is a promising step into the direction of a more objective and accurate, semi-automatized mitosis counting supporting the pathologist.
Tasks
Published	2017-07-26
URL	http://arxiv.org/abs/1707.08525v1
PDF	http://arxiv.org/pdf/1707.08525v1.pdf
PWC	https://paperswithcode.com/paper/a-guided-spatial-transformer-network-for
Repo
Framework

A Study on the Extraction and Analysis of a Large Set of Eye Movement Features during Reading


Title	A Study on the Extraction and Analysis of a Large Set of Eye Movement Features during Reading
Authors	Ioannis Rigas, Lee Friedman, Oleg Komogortsev
Abstract	This work presents a study on the extraction and analysis of a set of 101 categories of eye movement features from three types of eye movement events: fixations, saccades, and post-saccadic oscillations. The eye movements were recorded during a reading task. For the categories of features with multiple instances in a recording we extract corresponding feature subtypes by calculating descriptive statistics on the distributions of these instances. A unified framework of detailed descriptions and mathematical formulas are provided for the extraction of the feature set. The analysis of feature values is performed using a large database of eye movement recordings from a normative population of 298 subjects. We demonstrate the central tendency and overall variability of feature values over the experimental population, and more importantly, we quantify the test-retest reliability (repeatability) of each separate feature. The described methods and analysis can provide valuable tools in fields exploring the eye movements, such as in behavioral studies, attention and cognition research, medical research, biometric recognition, and human-computer interaction.
Tasks
Published	2017-03-27
URL	http://arxiv.org/abs/1703.09167v1
PDF	http://arxiv.org/pdf/1703.09167v1.pdf
PWC	https://paperswithcode.com/paper/a-study-on-the-extraction-and-analysis-of-a
Repo
Framework

Regulating Highly Automated Robot Ecologies: Insights from Three User Studies


Title	Regulating Highly Automated Robot Ecologies: Insights from Three User Studies
Authors	Wen Shen, Alanoud Al Khemeiri, Abdulla Almehrezi, Wael Al Enezi, Iyad Rahwan, Jacob W. Crandall
Abstract	Highly automated robot ecologies (HARE), or societies of independent autonomous robots or agents, are rapidly becoming an important part of much of the world’s critical infrastructure. As with human societies, regulation, wherein a governing body designs rules and processes for the society, plays an important role in ensuring that HARE meet societal objectives. However, to date, a careful study of interactions between a regulator and HARE is lacking. In this paper, we report on three user studies which give insights into how to design systems that allow people, acting as the regulatory authority, to effectively interact with HARE. As in the study of political systems in which governments regulate human societies, our studies analyze how interactions between HARE and regulators are impacted by regulatory power and individual (robot or agent) autonomy. Our results show that regulator power, decision support, and adaptive autonomy can each diminish the social welfare of HARE, and hint at how these seemingly desirable mechanisms can be designed so that they become part of successful HARE.
Tasks
Published	2017-08-07
URL	http://arxiv.org/abs/1708.02167v1
PDF	http://arxiv.org/pdf/1708.02167v1.pdf
PWC	https://paperswithcode.com/paper/regulating-highly-automated-robot-ecologies
Repo
Framework

Deterministic and Probabilistic Conditions for Finite Completability of Low-rank Multi-View Data


Title	Deterministic and Probabilistic Conditions for Finite Completability of Low-rank Multi-View Data
Authors	Morteza Ashraphijuo, Xiaodong Wang, Vaneet Aggarwal
Abstract	We consider the multi-view data completion problem, i.e., to complete a matrix $\mathbf{U}=[\mathbf{U}_1\mathbf{U}_2]$ where the ranks of $\mathbf{U},\mathbf{U}_1$, and $\mathbf{U}_2$ are given. In particular, we investigate the fundamental conditions on the sampling pattern, i.e., locations of the sampled entries for finite completability of such a multi-view data given the corresponding rank constraints. In contrast with the existing analysis on Grassmannian manifold for a single-view matrix, i.e., conventional matrix completion, we propose a geometric analysis on the manifold structure for multi-view data to incorporate more than one rank constraint. We provide a deterministic necessary and sufficient condition on the sampling pattern for finite completability. We also give a probabilistic condition in terms of the number of samples per column that guarantees finite completability with high probability. Finally, using the developed tools, we derive the deterministic and probabilistic guarantees for unique completability.
Tasks	Matrix Completion
Published	2017-01-03
URL	http://arxiv.org/abs/1701.00737v2
PDF	http://arxiv.org/pdf/1701.00737v2.pdf
PWC	https://paperswithcode.com/paper/deterministic-and-probabilistic-conditions
Repo
Framework

Label Stability in Multiple Instance Learning


Title	Label Stability in Multiple Instance Learning
Authors	Veronika Cheplygina, Lauge Sørensen, David M. J. Tax, Marleen de Bruijne, Marco Loog
Abstract	We address the problem of \emph{instance label stability} in multiple instance learning (MIL) classifiers. These classifiers are trained only on globally annotated images (bags), but often can provide fine-grained annotations for image pixels or patches (instances). This is interesting for computer aided diagnosis (CAD) and other medical image analysis tasks for which only a coarse labeling is provided. Unfortunately, the instance labels may be unstable. This means that a slight change in training data could potentially lead to abnormalities being detected in different parts of the image, which is undesirable from a CAD point of view. Despite MIL gaining popularity in the CAD literature, this issue has not yet been addressed. We investigate the stability of instance labels provided by several MIL classifiers on 5 different datasets, of which 3 are medical image datasets (breast histopathology, diabetic retinopathy and computed tomography lung images). We propose an unsupervised measure to evaluate instance stability, and demonstrate that a performance-stability trade-off can be made when comparing MIL classifiers.
Tasks	Multiple Instance Learning
Published	2017-03-15
URL	http://arxiv.org/abs/1703.04986v1
PDF	http://arxiv.org/pdf/1703.04986v1.pdf
PWC	https://paperswithcode.com/paper/label-stability-in-multiple-instance-learning
Repo
Framework

Learning Rare Word Representations using Semantic Bridging


Title	Learning Rare Word Representations using Semantic Bridging
Authors	Victor Prokhorov, Mohammad Taher Pilehvar, Dimitri Kartsaklis, Pietro Lió, Nigel Collier
Abstract	We propose a methodology that adapts graph embedding techniques (DeepWalk (Perozzi et al., 2014) and node2vec (Grover and Leskovec, 2016)) as well as cross-lingual vector space mapping approaches (Least Squares and Canonical Correlation Analysis) in order to merge the corpus and ontological sources of lexical knowledge. We also perform comparative analysis of the used algorithms in order to identify the best combination for the proposed system. We then apply this to the task of enhancing the coverage of an existing word embedding’s vocabulary with rare and unseen words. We show that our technique can provide considerable extra coverage (over 99%), leading to consistent performance gain (around 10% absolute gain is achieved with w2v-gn-500K cf.\S 3.3) on the Rare Word Similarity dataset.
Tasks	Graph Embedding
Published	2017-07-24
URL	http://arxiv.org/abs/1707.07554v1
PDF	http://arxiv.org/pdf/1707.07554v1.pdf
PWC	https://paperswithcode.com/paper/learning-rare-word-representations-using
Repo
Framework

Learning Graph Topological Features via GAN


Title	Learning Graph Topological Features via GAN
Authors	Weiyi Liu, Hal Cooper, Min Hwan Oh, Sailung Yeung, Pin-Yu Chen, Toyotaro Suzumura, Lingli Chen
Abstract	Inspired by the generation power of generative adversarial networks (GANs) in image domains, we introduce a novel hierarchical architecture for learning characteristic topological features from a single arbitrary input graph via GANs. The hierarchical architecture consisting of multiple GANs preserves both local and global topological features and automatically partitions the input graph into representative stages for feature learning. The stages facilitate reconstruction and can be used as indicators of the importance of the associated topological structures. Experiments show that our method produces subgraphs retaining a wide range of topological features, even in early reconstruction stages (unlike a single GAN, which cannot easily identify such features, let alone reconstruct the original graph). This paper is firstline research on combining the use of GANs and graph topological analysis.
Tasks
Published	2017-09-11
URL	https://arxiv.org/abs/1709.03545v5
PDF	https://arxiv.org/pdf/1709.03545v5.pdf
PWC	https://paperswithcode.com/paper/learning-graph-topological-features-via-gan
Repo
Framework

A Time-Vertex Signal Processing Framework


Title	A Time-Vertex Signal Processing Framework
Authors	Francesco Grassi, Andreas Loukas, Nathanaël Perraudin, Benjamin Ricaud
Abstract	An emerging way to deal with high-dimensional non-euclidean data is to assume that the underlying structure can be captured by a graph. Recently, ideas have begun to emerge related to the analysis of time-varying graph signals. This work aims to elevate the notion of joint harmonic analysis to a full-fledged framework denoted as Time-Vertex Signal Processing, that links together the time-domain signal processing techniques with the new tools of graph signal processing. This entails three main contributions: (a) We provide a formal motivation for harmonic time-vertex analysis as an analysis tool for the state evolution of simple Partial Differential Equations on graphs. (b) We improve the accuracy of joint filtering operators by up-to two orders of magnitude. (c) Using our joint filters, we construct time-vertex dictionaries analyzing the different scales and the local time-frequency content of a signal. The utility of our tools is illustrated in numerous applications and datasets, such as dynamic mesh denoising and classification, still-video inpainting, and source localization in seismic events. Our results suggest that joint analysis of time-vertex signals can bring benefits to regression and learning.
Tasks	Denoising, Video Inpainting
Published	2017-05-05
URL	http://arxiv.org/abs/1705.02307v1
PDF	http://arxiv.org/pdf/1705.02307v1.pdf
PWC	https://paperswithcode.com/paper/a-time-vertex-signal-processing-framework
Repo
Framework

N-gram and Neural Language Models for Discriminating Similar Languages


Title	N-gram and Neural Language Models for Discriminating Similar Languages
Authors	Andre Cianflone, Leila Kosseim
Abstract	This paper describes our submission (named clac) to the 2016 Discriminating Similar Languages (DSL) shared task. We participated in the closed Sub-task 1 (Set A) with two separate machine learning techniques. The first approach is a character based Convolution Neural Network with a bidirectional long short term memory (BiLSTM) layer (CLSTM), which achieved an accuracy of 78.45% with minimal tuning. The second approach is a character-based n-gram model. This last approach achieved an accuracy of 88.45% which is close to the accuracy of 89.38% achieved by the best submission, and allowed us to rank #7 overall.
Tasks
Published	2017-08-11
URL	http://arxiv.org/abs/1708.03421v1
PDF	http://arxiv.org/pdf/1708.03421v1.pdf
PWC	https://paperswithcode.com/paper/n-gram-and-neural-language-models-for
Repo
Framework

A deep generative model for single-cell RNA sequencing with application to detecting differentially expressed genes


Title	A deep generative model for single-cell RNA sequencing with application to detecting differentially expressed genes
Authors	Romain Lopez, Jeffrey Regier, Michael Cole, Michael Jordan, Nir Yosef
Abstract	We propose a probabilistic model for interpreting gene expression levels that are observed through single-cell RNA sequencing. In the model, each cell has a low-dimensional latent representation. Additional latent variables account for technical effects that may erroneously set some observations of gene expression levels to zero. Conditional distributions are specified by neural networks, giving the proposed model enough flexibility to fit the data well. We use variational inference and stochastic optimization to approximate the posterior distribution. The inference procedure scales to over one million cells, whereas competing algorithms do not. Even for smaller datasets, for several tasks, the proposed procedure outperforms state-of-the-art methods like ZIFA and ZINB-WaVE. We also extend our framework to take into account batch effects and other confounding factors and propose a natural Bayesian hypothesis framework for differential expression that outperforms tradition DESeq2.
Tasks	Stochastic Optimization
Published	2017-10-13
URL	http://arxiv.org/abs/1710.05086v2
PDF	http://arxiv.org/pdf/1710.05086v2.pdf
PWC	https://paperswithcode.com/paper/a-deep-generative-model-for-single-cell-rna
Repo
Framework

Optimal Identity Testing with High Probability


Title	Optimal Identity Testing with High Probability
Authors	Ilias Diakonikolas, Themis Gouleakis, John Peebles, Eric Price
Abstract	We study the problem of testing identity against a given distribution with a focus on the high confidence regime. More precisely, given samples from an unknown distribution $p$ over $n$ elements, an explicitly given distribution $q$, and parameters $0< \epsilon, \delta < 1$, we wish to distinguish, {\em with probability at least $1-\delta$}, whether the distributions are identical versus $\varepsilon$-far in total variation distance. Most prior work focused on the case that $\delta = \Omega(1)$, for which the sample complexity of identity testing is known to be $\Theta(\sqrt{n}/\epsilon^2)$. Given such an algorithm, one can achieve arbitrarily small values of $\delta$ via black-box amplification, which multiplies the required number of samples by $\Theta(\log(1/\delta))$. We show that black-box amplification is suboptimal for any $\delta = o(1)$, and give a new identity tester that achieves the optimal sample complexity. Our new upper and lower bounds show that the optimal sample complexity of identity testing is [ \Theta\left( \frac{1}{\epsilon^2}\left(\sqrt{n \log(1/\delta)} + \log(1/\delta) \right)\right) ] for any $n, \varepsilon$, and $\delta$. For the special case of uniformity testing, where the given distribution is the uniform distribution $U_n$ over the domain, our new tester is surprisingly simple: to test whether $p = U_n$ versus $d_{\mathrm TV}(p, U_n) \geq \varepsilon$, we simply threshold $d_{\mathrm TV}(\widehat{p}, U_n)$, where $\widehat{p}$ is the empirical probability distribution. The fact that this simple “plug-in” estimator is sample-optimal is surprising, even in the constant $\delta$ case. Indeed, it was believed that such a tester would not attain sublinear sample complexity even for constant values of $\varepsilon$ and $\delta$.
Tasks
Published	2017-08-09
URL	http://arxiv.org/abs/1708.02728v2
PDF	http://arxiv.org/pdf/1708.02728v2.pdf
PWC	https://paperswithcode.com/paper/optimal-identity-testing-with-high
Repo
Framework

Discriminant chronicles mining: Application to care pathways analytics


Title	Discriminant chronicles mining: Application to care pathways analytics
Authors	Yann Dauxais, Thomas Guyet, David Gross-Amblard, André Happe
Abstract	Pharmaco-epidemiology (PE) is the study of uses and effects of drugs in well defined populations. As medico-administrative databases cover a large part of the population, they have become very interesting to carry PE studies. Such databases provide longitudinal care pathways in real condition containing timestamped care events, especially drug deliveries. Temporal pattern mining becomes a strategic choice to gain valuable insights about drug uses. In this paper we propose DCM, a new discriminant temporal pattern mining algorithm. It extracts chronicle patterns that occur more in a studied population than in a control population. We present results on the identification of possible associations between hospitalizations for seizure and anti-epileptic drug switches in care pathway of epileptic patients.
Tasks	Epidemiology
Published	2017-09-11
URL	http://arxiv.org/abs/1709.03309v1
PDF	http://arxiv.org/pdf/1709.03309v1.pdf
PWC	https://paperswithcode.com/paper/discriminant-chronicles-mining-application-to
Repo
Framework

Self-Supervised Siamese Learning on Stereo Image Pairs for Depth Estimation in Robotic Surgery


Title	Self-Supervised Siamese Learning on Stereo Image Pairs for Depth Estimation in Robotic Surgery
Authors	Menglong Ye, Edward Johns, Ankur Handa, Lin Zhang, Philip Pratt, Guang-Zhong Yang
Abstract	Robotic surgery has become a powerful tool for performing minimally invasive procedures, providing advantages in dexterity, precision, and 3D vision, over traditional surgery. One popular robotic system is the da Vinci surgical platform, which allows preoperative information to be incorporated into live procedures using Augmented Reality (AR). Scene depth estimation is a prerequisite for AR, as accurate registration requires 3D correspondences between preoperative and intraoperative organ models. In the past decade, there has been much progress on depth estimation for surgical scenes, such as using monocular or binocular laparoscopes [1,2]. More recently, advances in deep learning have enabled depth estimation via Convolutional Neural Networks (CNNs) [3], but training requires a large image dataset with ground truth depths. Inspired by [4], we propose a deep learning framework for surgical scene depth estimation using self-supervision for scalable data acquisition. Our framework consists of an autoencoder for depth prediction, and a differentiable spatial transformer for training the autoencoder on stereo image pairs without ground truth depths. Validation was conducted on stereo videos collected in robotic partial nephrectomy.
Tasks	Depth Estimation
Published	2017-05-17
URL	http://arxiv.org/abs/1705.08260v1
PDF	http://arxiv.org/pdf/1705.08260v1.pdf
PWC	https://paperswithcode.com/paper/self-supervised-siamese-learning-on-stereo
Repo
Framework