Paper Group ANR 13
Neonatal Seizure Detection using Convolutional Neural Networks. Accelerated Image Reconstruction for Nonlinear Diffractive Imaging. A watershed-based algorithm to segment and classify cells in fluorescence microscopy images. Function approximation with zonal function networks with activation functions analogous to the rectified linear unit function …
Neonatal Seizure Detection using Convolutional Neural Networks
| Title | Neonatal Seizure Detection using Convolutional Neural Networks |
| Authors | Alison O’Shea, Gordon Lightbody, Geraldine Boylan, Andriy Temko |
| Abstract | This study presents a novel end-to-end architecture that learns hierarchical representations from raw EEG data using fully convolutional deep neural networks for the task of neonatal seizure detection. The deep neural network acts as both feature extractor and classifier, allowing for end-to-end optimization of the seizure detector. The designed system is evaluated on a large dataset of continuous unedited multi-channel neonatal EEG totaling 835 hours and comprising of 1389 seizures. The proposed deep architecture, with sample-level filters, achieves an accuracy that is comparable to the state-of-the-art SVM-based neonatal seizure detector, which operates on a set of carefully designed hand-crafted features. The fully convolutional architecture allows for the localization of EEG waveforms and patterns that result in high seizure probabilities for further clinical examination. |
| Tasks | EEG, Seizure Detection |
| Published | 2017-09-18 |
| URL | http://arxiv.org/abs/1709.05849v1 |
| http://arxiv.org/pdf/1709.05849v1.pdf | |
| PWC | https://paperswithcode.com/paper/neonatal-seizure-detection-using |
| Repo | |
| Framework | |
Accelerated Image Reconstruction for Nonlinear Diffractive Imaging
| Title | Accelerated Image Reconstruction for Nonlinear Diffractive Imaging |
| Authors | Yanting Ma, Hassan Mansour, Dehong Liu, Petros T. Boufounos, Ulugbek S. Kamilov |
| Abstract | The problem of reconstructing an object from the measurements of the light it scatters is common in numerous imaging applications. While the most popular formulations of the problem are based on linearizing the object-light relationship, there is an increased interest in considering nonlinear formulations that can account for multiple light scattering. In this paper, we propose an image reconstruction method, called CISOR, for nonlinear diffractive imaging, based on a nonconvex optimization formulation with total variation (TV) regularization. The nonconvex solver used in CISOR is our new variant of fast iterative shrinkage/thresholding algorithm (FISTA). We provide fast and memory-efficient implementation of the new FISTA variant and prove that it reliably converges for our nonconvex optimization problem. In addition, we systematically compare our method with other state-of-the-art methods on simulated as well as experimentally measured data in both 2D and 3D settings. |
| Tasks | Image Reconstruction |
| Published | 2017-08-04 |
| URL | http://arxiv.org/abs/1708.01663v2 |
| http://arxiv.org/pdf/1708.01663v2.pdf | |
| PWC | https://paperswithcode.com/paper/accelerated-image-reconstruction-for |
| Repo | |
| Framework | |
A watershed-based algorithm to segment and classify cells in fluorescence microscopy images
| Title | A watershed-based algorithm to segment and classify cells in fluorescence microscopy images |
| Authors | Lena R. Bartell, Lawrence J. Bonassar, Itai Cohen |
| Abstract | Imaging assays of cellular function, especially those using fluorescent stains, are ubiquitous in the biological and medical sciences. Despite advances in computer vision, such images are often analyzed using only manual or rudimentary automated processes. Watershed-based segmentation is an effective technique for identifying objects in images; it outperforms commonly used image analysis methods, but requires familiarity with computer-vision techniques to be applied successfully. In this report, we present and implement a watershed-based image analysis and classification algorithm in a GUI, enabling a broad set of users to easily understand the algorithm and adjust the parameters to their specific needs. As an example, we implement this algorithm to find and classify cells in a complex imaging assay for mitochondrial function. In a second example, we demonstrate a workflow using manual comparisons and receiver operator characteristics to optimize the algorithm parameters for finding live and dead cells in a standard viability assay. Overall, this watershed-based algorithm is more advanced than traditional thresholding and can produce optimized, automated results. By incorporating associated pre-processing steps in the GUI, the algorithm is also easily adjusted, rendering it user-friendly. |
| Tasks | |
| Published | 2017-06-02 |
| URL | http://arxiv.org/abs/1706.00815v1 |
| http://arxiv.org/pdf/1706.00815v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-watershed-based-algorithm-to-segment-and |
| Repo | |
| Framework | |
Function approximation with zonal function networks with activation functions analogous to the rectified linear unit functions
| Title | Function approximation with zonal function networks with activation functions analogous to the rectified linear unit functions |
| Authors | Hrushikesh N. Mhaskar |
| Abstract | A zonal function (ZF) network on the $q$ dimensional sphere $\mathbb{S}^q$ is a network of the form $\mathbf{x}\mapsto \sum_{k=1}^n a_k\phi(\mathbf{x}\cdot\mathbf{x}_k)$ where $\phi :[-1,1]\to\mathbf{R}$ is the activation function, $\mathbf{x}_k\in\mathbb{S}^q$ are the centers, and $a_k\in\mathbb{R}$. While the approximation properties of such networks are well studied in the context of positive definite activation functions, recent interest in deep and shallow networks motivate the study of activation functions of the form $\phi(t)=t$, which are not positive definite. In this paper, we define an appropriate smoothess class and establish approximation properties of such networks for functions in this class. The centers can be chosen independently of the target function, and the coefficients are linear combinations of the training data. The constructions preserve rotational symmetries. |
| Tasks | |
| Published | 2017-09-24 |
| URL | http://arxiv.org/abs/1709.08174v2 |
| http://arxiv.org/pdf/1709.08174v2.pdf | |
| PWC | https://paperswithcode.com/paper/function-approximation-with-zonal-function |
| Repo | |
| Framework | |
Optimizing Region Selection for Weakly Supervised Object Detection
| Title | Optimizing Region Selection for Weakly Supervised Object Detection |
| Authors | Wenhui Jiang, Thuyen Ngo, B. S. Manjunath, Zhicheng Zhao, Fei Su |
| Abstract | Training object detectors with only image-level annotations is very challenging because the target objects are often surrounded by a large number of background clutters. Many existing approaches tackle this problem through object proposal mining. However, the collected positive regions are either low in precision or lack of diversity, and the strategy of collecting negative regions is not carefully designed, neither. Moreover, training is often slow because region selection and object detector training are processed separately. In this context, the primary contribution of this work is to improve weakly supervised detection with an optimized region selection strategy. The proposed method collects purified positive training regions by progressively removing easy background clutters, and selects discriminative negative regions by mining class-specific hard samples. This region selection procedure is further integrated into a CNN-based weakly supervised detection (WSD) framework, and can be performed in each stochastic gradient descent mini-batch during training. Therefore, the entire model can be trained end-to-end efficiently. Extensive evaluation results on PASCAL VOC 2007, VOC 2010 and VOC 2012 datasets are presented which demonstrate that the proposed method effectively improves WSD. |
| Tasks | Object Detection, Weakly Supervised Object Detection |
| Published | 2017-08-05 |
| URL | http://arxiv.org/abs/1708.01723v1 |
| http://arxiv.org/pdf/1708.01723v1.pdf | |
| PWC | https://paperswithcode.com/paper/optimizing-region-selection-for-weakly |
| Repo | |
| Framework | |
Bilinear residual Neural Network for the identification and forecasting of dynamical systems
| Title | Bilinear residual Neural Network for the identification and forecasting of dynamical systems |
| Authors | Ronan Fablet, Said Ouala, Cedric Herzet |
| Abstract | Due to the increasing availability of large-scale observation and simulation datasets, data-driven representations arise as efficient and relevant computation representations of dynamical systems for a wide range of applications, where model-driven models based on ordinary differential equation remain the state-of-the-art approaches. In this work, we investigate neural networks (NN) as physically-sound data-driven representations of such systems. Reinterpreting Runge-Kutta methods as graphical models, we consider a residual NN architecture and introduce bilinear layers to embed non-linearities which are intrinsic features of dynamical systems. From numerical experiments for classic dynamical systems, we demonstrate the relevance of the proposed NN-based architecture both in terms of forecasting performance and model identification. |
| Tasks | |
| Published | 2017-12-19 |
| URL | http://arxiv.org/abs/1712.07003v1 |
| http://arxiv.org/pdf/1712.07003v1.pdf | |
| PWC | https://paperswithcode.com/paper/bilinear-residual-neural-network-for-the |
| Repo | |
| Framework | |
Compact Multi-Class Boosted Trees
| Title | Compact Multi-Class Boosted Trees |
| Authors | Natalia Ponomareva, Thomas Colthurst, Gilbert Hendry, Salem Haykal, Soroush Radpour |
| Abstract | Gradient boosted decision trees are a popular machine learning technique, in part because of their ability to give good accuracy with small models. We describe two extensions to the standard tree boosting algorithm designed to increase this advantage. The first improvement extends the boosting formalism from scalar-valued trees to vector-valued trees. This allows individual trees to be used as multiclass classifiers, rather than requiring one tree per class, and drastically reduces the model size required for multiclass problems. We also show that some other popular vector-valued gradient boosted trees modifications fit into this formulation and can be easily obtained in our implementation. The second extension, layer-by-layer boosting, takes smaller steps in function space, which is empirically shown to lead to a faster convergence and to a more compact ensemble. We have added both improvements to the open-source TensorFlow Boosted trees (TFBT) package, and we demonstrate their efficacy on a variety of multiclass datasets. We expect these extensions will be of particular interest to boosted tree applications that require small models, such as embedded devices, applications requiring fast inference, or applications desiring more interpretable models. |
| Tasks | |
| Published | 2017-10-31 |
| URL | http://arxiv.org/abs/1710.11547v1 |
| http://arxiv.org/pdf/1710.11547v1.pdf | |
| PWC | https://paperswithcode.com/paper/compact-multi-class-boosted-trees |
| Repo | |
| Framework | |
A Search for Improved Performance in Regular Expressions
| Title | A Search for Improved Performance in Regular Expressions |
| Authors | Brendan Cody-Kenny, Michael Fenton, Adrian Ronayne, Eoghan Considine, Thomas McGuire, Michael O’Neill |
| Abstract | The primary aim of automated performance improvement is to reduce the running time of programs while maintaining (or improving on) functionality. In this paper, Genetic Programming is used to find performance improvements in regular expressions for an array of target programs, representing the first application of automated software improvement for run-time performance in the Regular Expression language. This particular problem is interesting as there may be many possible alternative regular expressions which perform the same task while exhibiting subtle differences in performance. A benchmark suite of candidate regular expressions is proposed for improvement. We show that the application of Genetic Programming techniques can result in performance improvements in all cases. As we start evolution from a known good regular expression, diversity is critical in escaping the local optima of the seed expression. In order to understand diversity during evolution we compare an initial population consisting of only seed programs with a population initialised using a combination of a single seed individual with individuals generated using PI Grow and Ramped-half-and-half initialisation mechanisms. |
| Tasks | |
| Published | 2017-04-13 |
| URL | http://arxiv.org/abs/1704.04119v1 |
| http://arxiv.org/pdf/1704.04119v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-search-for-improved-performance-in-regular |
| Repo | |
| Framework | |
Detecting Egregious Conversations between Customers and Virtual Agents
| Title | Detecting Egregious Conversations between Customers and Virtual Agents |
| Authors | Tommy Sandbank, Michal Shmueli-Scheuer, Jonathan Herzig, David Konopnicki, John Richards, David Piorkowski |
| Abstract | Virtual agents are becoming a prominent channel of interaction in customer service. Not all customer interactions are smooth, however, and some can become almost comically bad. In such instances, a human agent might need to step in and salvage the conversation. Detecting bad conversations is important since disappointing customer service may threaten customer loyalty and impact revenue. In this paper, we outline an approach to detecting such egregious conversations, using behavioral cues from the user, patterns in agent responses, and user-agent interaction. Using logs of two commercial systems, we show that using these features improves the detection F1-score by around 20% over using textual features alone. In addition, we show that those features are common across two quite different domains and, arguably, universal. |
| Tasks | |
| Published | 2017-11-15 |
| URL | http://arxiv.org/abs/1711.05780v2 |
| http://arxiv.org/pdf/1711.05780v2.pdf | |
| PWC | https://paperswithcode.com/paper/detecting-egregious-conversations-between |
| Repo | |
| Framework | |
Generating Liquid Simulations with Deformation-aware Neural Networks
| Title | Generating Liquid Simulations with Deformation-aware Neural Networks |
| Authors | Lukas Prantl, Boris Bonev, Nils Thuerey |
| Abstract | We propose a novel approach for deformation-aware neural networks that learn the weighting and synthesis of dense volumetric deformation fields. Our method specifically targets the space-time representation of physical surfaces from liquid simulations. Liquids exhibit highly complex, non-linear behavior under changing simulation conditions such as different initial conditions. Our algorithm captures these complex phenomena in two stages: a first neural network computes a weighting function for a set of pre-computed deformations, while a second network directly generates a deformation field for refining the surface. Key for successful training runs in this setting is a suitable loss function that encodes the effect of the deformations, and a robust calculation of the corresponding gradients. To demonstrate the effectiveness of our approach, we showcase our method with several complex examples of flowing liquids with topology changes. Our representation makes it possible to rapidly generate the desired implicit surfaces. We have implemented a mobile application to demonstrate that real-time interactions with complex liquid effects are possible with our approach. |
| Tasks | |
| Published | 2017-04-25 |
| URL | http://arxiv.org/abs/1704.07854v4 |
| http://arxiv.org/pdf/1704.07854v4.pdf | |
| PWC | https://paperswithcode.com/paper/generating-liquid-simulations-with |
| Repo | |
| Framework | |
Multi-task Learning Of Deep Neural Networks For Audio Visual Automatic Speech Recognition
| Title | Multi-task Learning Of Deep Neural Networks For Audio Visual Automatic Speech Recognition |
| Authors | Abhinav Thanda, Shankar M Venkatesan |
| Abstract | Multi-task learning (MTL) involves the simultaneous training of two or more related tasks over shared representations. In this work, we apply MTL to audio-visual automatic speech recognition(AV-ASR). Our primary task is to learn a mapping between audio-visual fused features and frame labels obtained from acoustic GMM/HMM model. This is combined with an auxiliary task which maps visual features to frame labels obtained from a separate visual GMM/HMM model. The MTL model is tested at various levels of babble noise and the results are compared with a base-line hybrid DNN-HMM AV-ASR model. Our results indicate that MTL is especially useful at higher level of noise. Compared to base-line, upto 7% relative improvement in WER is reported at -3 SNR dB |
| Tasks | Multi-Task Learning, Speech Recognition |
| Published | 2017-01-10 |
| URL | http://arxiv.org/abs/1701.02477v1 |
| http://arxiv.org/pdf/1701.02477v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-task-learning-of-deep-neural-networks |
| Repo | |
| Framework | |
Optimal Low-Rank Dynamic Mode Decomposition
| Title | Optimal Low-Rank Dynamic Mode Decomposition |
| Authors | Patrick Héas, Cédric Herzet |
| Abstract | Dynamic Mode Decomposition (DMD) has emerged as a powerful tool for analyzing the dynamics of non-linear systems from experimental datasets. Recently, several attempts have extended DMD to the context of low-rank approximations. This extension is of particular interest for reduced-order modeling in various applicative domains, e.g. for climate prediction, to study molecular dynamics or micro-electromechanical devices. This low-rank extension takes the form of a non-convex optimization problem. To the best of our knowledge, only sub-optimal algorithms have been proposed in the literature to compute the solution of this problem. In this paper, we prove that there exists a closed-form optimal solution to this problem and design an effective algorithm to compute it based on Singular Value Decomposition (SVD). A toy-example illustrates the gain in performance of the proposed algorithm compared to state-of-the-art techniques. |
| Tasks | |
| Published | 2017-01-04 |
| URL | http://arxiv.org/abs/1701.01064v3 |
| http://arxiv.org/pdf/1701.01064v3.pdf | |
| PWC | https://paperswithcode.com/paper/optimal-low-rank-dynamic-mode-decomposition |
| Repo | |
| Framework | |
Personalization of Saliency Estimation
| Title | Personalization of Saliency Estimation |
| Authors | Bingqing Yu, James J. Clark |
| Abstract | Most existing saliency models use low-level features or task descriptions when generating attention predictions. However, the link between observer characteristics and gaze patterns is rarely investigated. We present a novel saliency prediction technique which takes viewers’ identities and personal traits into consideration when modeling human attention. Instead of only computing image salience for average observers, we consider the interpersonal variation in the viewing behaviors of observers with different personal traits and backgrounds. We present an enriched derivative of the GAN network, which is able to generate personalized saliency predictions when fed with image stimuli and specific information about the observer. Our model contains a generator which generates grayscale saliency heat maps based on the image and an observer label. The generator is paired with an adversarial discriminator which learns to distinguish generated salience from ground truth salience. The discriminator also has the observer label as an input, which contributes to the personalization ability of our approach. We evaluate the performance of our personalized salience model by comparison with a benchmark model along with other un-personalized predictions, and illustrate improvements in prediction accuracy for all tested observer groups. |
| Tasks | Saliency Prediction |
| Published | 2017-11-21 |
| URL | http://arxiv.org/abs/1711.08000v1 |
| http://arxiv.org/pdf/1711.08000v1.pdf | |
| PWC | https://paperswithcode.com/paper/personalization-of-saliency-estimation |
| Repo | |
| Framework | |
Neural Face Editing with Intrinsic Image Disentangling
| Title | Neural Face Editing with Intrinsic Image Disentangling |
| Authors | Zhixin Shu, Ersin Yumer, Sunil Hadap, Kalyan Sunkavalli, Eli Shechtman, Dimitris Samaras |
| Abstract | Traditional face editing methods often require a number of sophisticated and task specific algorithms to be applied one after the other — a process that is tedious, fragile, and computationally intensive. In this paper, we propose an end-to-end generative adversarial network that infers a face-specific disentangled representation of intrinsic face properties, including shape (i.e. normals), albedo, and lighting, and an alpha matte. We show that this network can be trained on “in-the-wild” images by incorporating an in-network physically-based image formation module and appropriate loss functions. Our disentangling latent representation allows for semantically relevant edits, where one aspect of facial appearance can be manipulated while keeping orthogonal properties fixed, and we demonstrate its use for a number of facial editing applications. |
| Tasks | |
| Published | 2017-04-13 |
| URL | http://arxiv.org/abs/1704.04131v1 |
| http://arxiv.org/pdf/1704.04131v1.pdf | |
| PWC | https://paperswithcode.com/paper/neural-face-editing-with-intrinsic-image |
| Repo | |
| Framework | |
NPGLM: A Non-Parametric Method for Temporal Link Prediction
| Title | NPGLM: A Non-Parametric Method for Temporal Link Prediction |
| Authors | Sina Sajadmanesh, Jiawei Zhang, Hamid R. Rabiee |
| Abstract | In this paper, we try to solve the problem of temporal link prediction in information networks. This implies predicting the time it takes for a link to appear in the future, given its features that have been extracted at the current network snapshot. To this end, we introduce a probabilistic non-parametric approach, called “Non-Parametric Generalized Linear Model” (NP-GLM), which infers the hidden underlying probability distribution of the link advent time given its features. We then present a learning algorithm for NP-GLM and an inference method to answer time-related queries. Extensive experiments conducted on both synthetic data and real-world Sina Weibo social network demonstrate the effectiveness of NP-GLM in solving temporal link prediction problem vis-a-vis competitive baselines. |
| Tasks | Link Prediction |
| Published | 2017-06-21 |
| URL | http://arxiv.org/abs/1706.06783v1 |
| http://arxiv.org/pdf/1706.06783v1.pdf | |
| PWC | https://paperswithcode.com/paper/npglm-a-non-parametric-method-for-temporal |
| Repo | |
| Framework | |
