Paper Group ANR 453
Linear Differential Constraints for Photo-polarimetric Height Estimation. On the Use of Machine Translation-Based Approaches for Vietnamese Diacritic Restoration. Exploring the Use of Shatter for AllSAT Through Ramsey-Type Problems. Multi-level computational methods for interdisciplinary research in the HathiTrust Digital Library. Approximate Kerne …
Linear Differential Constraints for Photo-polarimetric Height Estimation
| Title | Linear Differential Constraints for Photo-polarimetric Height Estimation |
| Authors | Silvia Tozza, William A. P. Smith, Dizhong Zhu, Ravi Ramamoorthi, Edwin R. Hancock |
| Abstract | In this paper we present a differential approach to photo-polarimetric shape estimation. We propose several alternative differential constraints based on polarisation and photometric shading information and show how to express them in a unified partial differential system. Our method uses the image ratios technique to combine shading and polarisation information in order to directly reconstruct surface height, without first computing surface normal vectors. Moreover, we are able to remove the non-linearities so that the problem reduces to solving a linear differential problem. We also introduce a new method for estimating a polarisation image from multichannel data and, finally, we show it is possible to estimate the illumination directions in a two source setup, extending the method into an uncalibrated scenario. From a numerical point of view, we use a least-squares formulation of the discrete version of the problem. To the best of our knowledge, this is the first work to consider a unified differential approach to solve photo-polarimetric shape estimation directly for height. Numerical results on synthetic and real-world data confirm the effectiveness of our proposed method. |
| Tasks | |
| Published | 2017-08-25 |
| URL | http://arxiv.org/abs/1708.07718v1 |
| http://arxiv.org/pdf/1708.07718v1.pdf | |
| PWC | https://paperswithcode.com/paper/linear-differential-constraints-for-photo |
| Repo | |
| Framework | |
On the Use of Machine Translation-Based Approaches for Vietnamese Diacritic Restoration
| Title | On the Use of Machine Translation-Based Approaches for Vietnamese Diacritic Restoration |
| Authors | Thai-Hoang Pham, Xuan-Khoai Pham, Phuong Le-Hong |
| Abstract | This paper presents an empirical study of two machine translation-based approaches for Vietnamese diacritic restoration problem, including phrase-based and neural-based machine translation models. This is the first work that applies neural-based machine translation method to this problem and gives a thorough comparison to the phrase-based machine translation method which is the current state-of-the-art method for this problem. On a large dataset, the phrase-based approach has an accuracy of 97.32% while that of the neural-based approach is 96.15%. While the neural-based method has a slightly lower accuracy, it is about twice faster than the phrase-based method in terms of inference speed. Moreover, neural-based machine translation method has much room for future improvement such as incorporating pre-trained word embeddings and collecting more training data. |
| Tasks | Machine Translation, Word Embeddings |
| Published | 2017-09-20 |
| URL | http://arxiv.org/abs/1709.07104v2 |
| http://arxiv.org/pdf/1709.07104v2.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-use-of-machine-translation-based |
| Repo | |
| Framework | |
Exploring the Use of Shatter for AllSAT Through Ramsey-Type Problems
| Title | Exploring the Use of Shatter for AllSAT Through Ramsey-Type Problems |
| Authors | David E. Narváez |
| Abstract | In the context of SAT solvers, Shatter is a popular tool for symmetry breaking on CNF formulas. Nevertheless, little has been said about its use in the context of AllSAT problems: problems where we are interested in listing all the models of a Boolean formula. AllSAT has gained much popularity in recent years due to its many applications in domains like model checking, data mining, etc. One example of a particularly transparent application of AllSAT to other fields of computer science is computational Ramsey theory. In this paper we study the effect of incorporating Shatter to the workflow of using Boolean formulas to generate all possible edge colorings of a graph avoiding prescribed monochromatic subgraphs. Generating complete sets of colorings is an important building block in computational Ramsey theory. We identify two drawbacks in the na"ive use of Shatter to break the symmetries of Boolean formulas encoding Ramsey-type problems for graphs: a “blow-up” in the number of models and the generation of incomplete sets of colorings. The issues presented in this work are not intended to discourage the use of Shatter as a preprocessing tool for AllSAT problems in combinatorial computing but to help researchers properly use this tool by avoiding these potential pitfalls. To this end, we provide strategies and additional tools to cope with the negative effects of using Shatter for AllSAT. While the specific application addressed in this paper is that of Ramsey-type problems, the analysis we carry out applies to many other areas in which highly-symmetrical Boolean formulas arise and we wish to find all of their models. |
| Tasks | |
| Published | 2017-11-17 |
| URL | http://arxiv.org/abs/1711.06362v1 |
| http://arxiv.org/pdf/1711.06362v1.pdf | |
| PWC | https://paperswithcode.com/paper/exploring-the-use-of-shatter-for-allsat |
| Repo | |
| Framework | |
Multi-level computational methods for interdisciplinary research in the HathiTrust Digital Library
| Title | Multi-level computational methods for interdisciplinary research in the HathiTrust Digital Library |
| Authors | Jaimie Murdock, Colin Allen, Katy Börner, Robert Light, Simon McAlister, Andrew Ravenscroft, Robert Rose, Doori Rose, Jun Otsuka, David Bourget, John Lawrence, Chris Reed |
| Abstract | We show how faceted search using a combination of traditional classification systems and mixed-membership topic models can go beyond keyword search to inform resource discovery, hypothesis formulation, and argument extraction for interdisciplinary research. Our test domain is the history and philosophy of scientific work on animal mind and cognition. The methods can be generalized to other research areas and ultimately support a system for semi-automatic identification of argument structures. We provide a case study for the application of the methods to the problem of identifying and extracting arguments about anthropomorphism during a critical period in the development of comparative psychology. We show how a combination of classification systems and mixed-membership models trained over large digital libraries can inform resource discovery in this domain. Through a novel approach of “drill-down” topic modeling—simultaneously reducing both the size of the corpus and the unit of analysis—we are able to reduce a large collection of fulltext volumes to a much smaller set of pages within six focal volumes containing arguments of interest to historians and philosophers of comparative psychology. The volumes identified in this way did not appear among the first ten results of the keyword search in the HathiTrust digital library and the pages bear the kind of “close reading” needed to generate original interpretations that is the heart of scholarly work in the humanities. Zooming back out, we provide a way to place the books onto a map of science originally constructed from very different data and for different purposes. The multilevel approach advances understanding of the intellectual and societal contexts in which writings are interpreted. |
| Tasks | Topic Models |
| Published | 2017-02-03 |
| URL | http://arxiv.org/abs/1702.01090v2 |
| http://arxiv.org/pdf/1702.01090v2.pdf | |
| PWC | https://paperswithcode.com/paper/multi-level-computational-methods-for |
| Repo | |
| Framework | |
Approximate Kernel PCA Using Random Features: Computational vs. Statistical Trade-off
| Title | Approximate Kernel PCA Using Random Features: Computational vs. Statistical Trade-off |
| Authors | Bharath Sriperumbudur, Nicholas Sterge |
| Abstract | Kernel methods are powerful learning methodologies that provide a simple way to construct nonlinear algorithms from linear ones. Despite their popularity, they suffer from poor scalability in big data scenarios. Various approximation methods, including random feature approximation have been proposed to alleviate the problem. However, the statistical consistency of most of these approximate kernel methods is not well understood except for kernel ridge regression wherein it has been shown that the random feature approximation is not only computationally efficient but also statistically consistent with a minimax optimal rate of convergence. In this paper, we investigate the efficacy of random feature approximation in the context of kernel principal component analysis (KPCA) by studying the trade-off between computational and statistical behaviors of approximate KPCA. We show that the approximate KPCA is both computationally and statistically efficient compared to KPCA in terms of the error associated with reconstructing a kernel function based on its projection onto the corresponding eigenspaces. Depending on the eigenvalue decay behavior of the covariance operator, we show that only $n^{2/3}$ features (polynomial decay) or $\sqrt{n}$ features (exponential decay) are needed to match the statistical performance of KPCA. We also investigate their statistical behaviors in terms of the convergence of corresponding eigenspaces wherein we show that only $\sqrt{n}$ features are required to match the performance of KPCA and if fewer than $\sqrt{n}$ features are used, then approximate KPCA has a worse statistical behavior than that of KPCA. |
| Tasks | |
| Published | 2017-06-20 |
| URL | http://arxiv.org/abs/1706.06296v2 |
| http://arxiv.org/pdf/1706.06296v2.pdf | |
| PWC | https://paperswithcode.com/paper/approximate-kernel-pca-using-random-features |
| Repo | |
| Framework | |
Optimizing and Visualizing Deep Learning for Benign/Malignant Classification in Breast Tumors
| Title | Optimizing and Visualizing Deep Learning for Benign/Malignant Classification in Breast Tumors |
| Authors | Darvin Yi, Rebecca Lynn Sawyer, David Cohn III, Jared Dunnmon, Carson Lam, Xuerong Xiao, Daniel Rubin |
| Abstract | Breast cancer has the highest incidence and second highest mortality rate for women in the US. Our study aims to utilize deep learning for benign/malignant classification of mammogram tumors using a subset of cases from the Digital Database of Screening Mammography (DDSM). Though it was a small dataset from the view of Deep Learning (about 1000 patients), we show that currently state of the art architectures of deep learning can find a robust signal, even when trained from scratch. Using convolutional neural networks (CNNs), we are able to achieve an accuracy of 85% and an ROC AUC of 0.91, while leading hand-crafted feature based methods are only able to achieve an accuracy of 71%. We investigate an amalgamation of architectures to show that our best result is reached with an ensemble of the lightweight GoogLe Nets tasked with interpreting both the coronal caudal view and the mediolateral oblique view, simply averaging the probability scores of both views to make the final prediction. In addition, we have created a novel method to visualize what features the neural network detects for the benign/malignant classification, and have correlated those features with well known radiological features, such as spiculation. Our algorithm significantly improves existing classification methods for mammography lesions and identifies features that correlate with established clinical markers. |
| Tasks | |
| Published | 2017-05-17 |
| URL | http://arxiv.org/abs/1705.06362v1 |
| http://arxiv.org/pdf/1705.06362v1.pdf | |
| PWC | https://paperswithcode.com/paper/optimizing-and-visualizing-deep-learning-for |
| Repo | |
| Framework | |
Stochastic Composite Least-Squares Regression with convergence rate O(1/n)
| Title | Stochastic Composite Least-Squares Regression with convergence rate O(1/n) |
| Authors | Nicolas Flammarion, Francis Bach |
| Abstract | We consider the minimization of composite objective functions composed of the expectation of quadratic functions and an arbitrary convex function. We study the stochastic dual averaging algorithm with a constant step-size, showing that it leads to a convergence rate of O(1/n) without strong convexity assumptions. This thus extends earlier results on least-squares regression with the Euclidean geometry to (a) all convex regularizers and constraints, and (b) all geome-tries represented by a Bregman divergence. This is achieved by a new proof technique that relates stochastic and deterministic recursions. |
| Tasks | |
| Published | 2017-02-21 |
| URL | http://arxiv.org/abs/1702.06429v1 |
| http://arxiv.org/pdf/1702.06429v1.pdf | |
| PWC | https://paperswithcode.com/paper/stochastic-composite-least-squares-regression |
| Repo | |
| Framework | |
Changing Views on Curves and Surfaces
| Title | Changing Views on Curves and Surfaces |
| Authors | Kathlén Kohn, Bernd Sturmfels, Matthew Trager |
| Abstract | Visual events in computer vision are studied from the perspective of algebraic geometry. Given a sufficiently general curve or surface in 3-space, we consider the image or contour curve that arises by projecting from a viewpoint. Qualitative changes in that curve occur when the viewpoint crosses the visual event surface. We examine the components of this ruled surface, and observe that these coincide with the iterated singular loci of the coisotropic hypersurfaces associated with the original curve or surface. We derive formulas, due to Salmon and Petitjean, for the degrees of these surfaces, and show how to compute exact representations for all visual event surfaces using algebraic methods. |
| Tasks | |
| Published | 2017-07-06 |
| URL | http://arxiv.org/abs/1707.01877v2 |
| http://arxiv.org/pdf/1707.01877v2.pdf | |
| PWC | https://paperswithcode.com/paper/changing-views-on-curves-and-surfaces |
| Repo | |
| Framework | |
Simplified Long Short-term Memory Recurrent Neural Networks: part I
| Title | Simplified Long Short-term Memory Recurrent Neural Networks: part I |
| Authors | Atra Akandeh, Fathi M. Salem |
| Abstract | We present five variants of the standard Long Short-term Memory (LSTM) recurrent neural networks by uniformly reducing blocks of adaptive parameters in the gating mechanisms. For simplicity, we refer to these models as LSTM1, LSTM2, LSTM3, LSTM4, and LSTM5, respectively. Such parameter-reduced variants enable speeding up data training computations and would be more suitable for implementations onto constrained embedded platforms. We comparatively evaluate and verify our five variant models on the classical MNIST dataset and demonstrate that these variant models are comparable to a standard implementation of the LSTM model while using less number of parameters. Moreover, we observe that in some cases the standard LSTM’s accuracy performance will drop after a number of epochs when using the ReLU nonlinearity; in contrast, however, LSTM3, LSTM4 and LSTM5 will retain their performance. |
| Tasks | |
| Published | 2017-07-14 |
| URL | http://arxiv.org/abs/1707.04619v1 |
| http://arxiv.org/pdf/1707.04619v1.pdf | |
| PWC | https://paperswithcode.com/paper/simplified-long-short-term-memory-recurrent-1 |
| Repo | |
| Framework | |
Generative Adversarial Networks recover features in astrophysical images of galaxies beyond the deconvolution limit
| Title | Generative Adversarial Networks recover features in astrophysical images of galaxies beyond the deconvolution limit |
| Authors | Kevin Schawinski, Ce Zhang, Hantian Zhang, Lucas Fowler, Gokula Krishnan Santhanam |
| Abstract | Observations of astrophysical objects such as galaxies are limited by various sources of random and systematic noise from the sky background, the optical system of the telescope and the detector used to record the data. Conventional deconvolution techniques are limited in their ability to recover features in imaging data by the Shannon-Nyquist sampling theorem. Here we train a generative adversarial network (GAN) on a sample of $4,550$ images of nearby galaxies at $0.01<z<0.02$ from the Sloan Digital Sky Survey and conduct $10\times$ cross validation to evaluate the results. We present a method using a GAN trained on galaxy images that can recover features from artificially degraded images with worse seeing and higher noise than the original with a performance which far exceeds simple deconvolution. The ability to better recover detailed features such as galaxy morphology from low-signal-to-noise and low angular resolution imaging data significantly increases our ability to study existing data sets of astrophysical objects as well as future observations with observatories such as the Large Synoptic Sky Telescope (LSST) and the Hubble and James Webb space telescopes. |
| Tasks | |
| Published | 2017-02-01 |
| URL | http://arxiv.org/abs/1702.00403v1 |
| http://arxiv.org/pdf/1702.00403v1.pdf | |
| PWC | https://paperswithcode.com/paper/generative-adversarial-networks-recover |
| Repo | |
| Framework | |
Distributed Deep Transfer Learning by Basic Probability Assignment
| Title | Distributed Deep Transfer Learning by Basic Probability Assignment |
| Authors | Arash Shahriari |
| Abstract | Transfer learning is a popular practice in deep neural networks, but fine-tuning of large number of parameters is a hard task due to the complex wiring of neurons between splitting layers and imbalance distributions of data in pretrained and transferred domains. The reconstruction of the original wiring for the target domain is a heavy burden due to the size of interconnections across neurons. We propose a distributed scheme that tunes the convolutional filters individually while backpropagates them jointly by means of basic probability assignment. Some of the most recent advances in evidence theory show that in a vast variety of the imbalanced regimes, optimizing of some proper objective functions derived from contingency matrices prevents biases towards high-prior class distributions. Therefore, the original filters get gradually transferred based on individual contributions to overall performance of the target domain. This largely reduces the expected complexity of transfer learning whilst highly improves precision. Our experiments on standard benchmarks and scenarios confirm the consistent improvement of our distributed deep transfer learning strategy. |
| Tasks | Transfer Learning |
| Published | 2017-10-20 |
| URL | http://arxiv.org/abs/1710.07437v1 |
| http://arxiv.org/pdf/1710.07437v1.pdf | |
| PWC | https://paperswithcode.com/paper/distributed-deep-transfer-learning-by-basic |
| Repo | |
| Framework | |
Algorithmic clothing: hybrid recommendation, from street-style-to-shop
| Title | Algorithmic clothing: hybrid recommendation, from street-style-to-shop |
| Authors | Y Qian, P Giaccone, M Sasdelli, E Vasquez, B Sengupta |
| Abstract | In this paper we detail Cortexica’s (https://www.cortexica.com) recommendation framework – particularly, we describe how a hybrid visual recommender system can be created by combining conditional random fields for segmentation and deep neural networks for object localisation and feature representation. The recommendation system that is built after localisation, segmentation and classification has two properties – first, it is knowledge based in the sense that it learns pairwise preference/occurrence matrix by utilising knowledge from experts (images from fashion blogs) and second, it is content-based as it utilises a deep learning based framework for learning feature representation. Such a construct is especially useful when there is a scarcity of user preference data, that forms the foundation of many collaborative recommendation algorithms. |
| Tasks | Recommendation Systems |
| Published | 2017-05-26 |
| URL | http://arxiv.org/abs/1705.09451v2 |
| http://arxiv.org/pdf/1705.09451v2.pdf | |
| PWC | https://paperswithcode.com/paper/algorithmic-clothing-hybrid-recommendation |
| Repo | |
| Framework | |
Multi-point Vibration Measurement for Mode Identification of Bridge Structures using Video-based Motion Magnification
| Title | Multi-point Vibration Measurement for Mode Identification of Bridge Structures using Video-based Motion Magnification |
| Authors | Zhexiong Shang, Zhigang Shen |
| Abstract | Image-based vibration mode identification gained increased attentions in civil and construction communities. A recent video-based motion magnification method was developed to measure and visualize small structure motions. This new approach presents a potential for low-cost vibration measurement and mode shape identification. Pilot studies using this approach on simple rigid body structures was reported. Its validity on complex outdoor structures have not been investigated. The objective is to investigate the capacity of video-based motion magnification approach in measuring the modal frequency and visualizing the mode shapes of complex steel bridges. A novel method that increases the performance of the current motion magnification for efficient structure modal analysis is introduced. This method was tested in both indoor and outdoor environments for validation. The results of the investigation show that motion magnification can be an efficient tool for modal analysis on complex bridge structures. With the developed method, mode frequencies of multiple structures are simultaneously measured and mode shapes of each structure are automatically visualized. |
| Tasks | |
| Published | 2017-12-18 |
| URL | http://arxiv.org/abs/1712.06566v1 |
| http://arxiv.org/pdf/1712.06566v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-point-vibration-measurement-for-mode |
| Repo | |
| Framework | |
Online and Offline Domain Adaptation for Reducing BCI Calibration Effort
| Title | Online and Offline Domain Adaptation for Reducing BCI Calibration Effort |
| Authors | Dongrui Wu |
| Abstract | Many real-world brain-computer interface (BCI) applications rely on single-trial classification of event-related potentials (ERPs) in EEG signals. However, because different subjects have different neural responses to even the same stimulus, it is very difficult to build a generic ERP classifier whose parameters fit all subjects. The classifier needs to be calibrated for each individual subject, using some labeled subject-specific data. This paper proposes both online and offline weighted adaptation regularization (wAR) algorithms to reduce this calibration effort, i.e., to minimize the amount of labeled subject-specific EEG data required in BCI calibration, and hence to increase the utility of the BCI system. We demonstrate using a visually-evoked potential oddball task and three different EEG headsets that both online and offline wAR algorithms significantly outperform several other algorithms. Moreover, through source domain selection, we can reduce their computational cost by about 50%, making them more suitable for real-time applications. |
| Tasks | Calibration, Domain Adaptation, EEG |
| Published | 2017-02-09 |
| URL | http://arxiv.org/abs/1702.02897v1 |
| http://arxiv.org/pdf/1702.02897v1.pdf | |
| PWC | https://paperswithcode.com/paper/online-and-offline-domain-adaptation-for |
| Repo | |
| Framework | |
Bayesian Inference over the Stiefel Manifold via the Givens Representation
| Title | Bayesian Inference over the Stiefel Manifold via the Givens Representation |
| Authors | Arya A Pourzanjani, Richard M Jiang, Brian Mitchell, Paul J Atzberger, Linda R Petzold |
| Abstract | We introduce an approach based on the Givens representation for posterior inference in statistical models with orthogonal matrix parameters, such as factor models and probabilistic principal component analysis (PPCA). We show how the Givens representation can be used to develop practical methods for transforming densities over the Stiefel manifold into densities over subsets of Euclidean space. We show how to deal with issues arising from the topology of the Stiefel manifold and how to inexpensively compute the change-of-measure terms. We introduce an auxiliary parameter approach that limits the impact of topological issues. We provide both analysis of our methods and numerical examples demonstrating the effectiveness of the approach. We also discuss how our Givens representation can be used to define general classes of distributions over the space of orthogonal matrices. We then give demonstrations on several examples showing how the Givens approach performs in practice in comparison with other methods. |
| Tasks | Bayesian Inference, Dimensionality Reduction |
| Published | 2017-10-25 |
| URL | https://arxiv.org/abs/1710.09443v4 |
| https://arxiv.org/pdf/1710.09443v4.pdf | |
| PWC | https://paperswithcode.com/paper/general-bayesian-inference-over-the-stiefel |
| Repo | |
| Framework | |
