Paper Group ANR 607
Dilated Convolutional Neural Networks for Cardiovascular MR Segmentation in Congenital Heart Disease. The Effect of Negators, Modals, and Degree Adverbs on Sentiment Composition. Unsupervised Learning Layers for Video Analysis. Parametrizing filters of a CNN with a GAN. Sound Event Detection Using Spatial Features and Convolutional Recurrent Neural …
Dilated Convolutional Neural Networks for Cardiovascular MR Segmentation in Congenital Heart Disease
| Title | Dilated Convolutional Neural Networks for Cardiovascular MR Segmentation in Congenital Heart Disease |
| Authors | Jelmer M. Wolterink, Tim Leiner, Max A. Viergever, Ivana Išgum |
| Abstract | We propose an automatic method using dilated convolutional neural networks (CNNs) for segmentation of the myocardium and blood pool in cardiovascular MR (CMR) of patients with congenital heart disease (CHD). Ten training and ten test CMR scans cropped to an ROI around the heart were provided in the MICCAI 2016 HVSMR challenge. A dilated CNN with a receptive field of 131x131 voxels was trained for myocardium and blood pool segmentation in axial, sagittal and coronal image slices. Performance was evaluated within the HVSMR challenge. Automatic segmentation of the test scans resulted in Dice indices of 0.80$\pm$0.06 and 0.93$\pm$0.02, average distances to boundaries of 0.96$\pm$0.31 and 0.89$\pm$0.24 mm, and Hausdorff distances of 6.13$\pm$3.76 and 7.07$\pm$3.01 mm for the myocardium and blood pool, respectively. Segmentation took 41.5$\pm$14.7 s per scan. In conclusion, dilated CNNs trained on a small set of CMR images of CHD patients showing large anatomical variability provide accurate myocardium and blood pool segmentations. |
| Tasks | |
| Published | 2017-04-12 |
| URL | http://arxiv.org/abs/1704.03669v1 |
| http://arxiv.org/pdf/1704.03669v1.pdf | |
| PWC | https://paperswithcode.com/paper/dilated-convolutional-neural-networks-for |
| Repo | |
| Framework | |
The Effect of Negators, Modals, and Degree Adverbs on Sentiment Composition
| Title | The Effect of Negators, Modals, and Degree Adverbs on Sentiment Composition |
| Authors | Svetlana Kiritchenko, Saif M. Mohammad |
| Abstract | Negators, modals, and degree adverbs can significantly affect the sentiment of the words they modify. Often, their impact is modeled with simple heuristics; although, recent work has shown that such heuristics do not capture the true sentiment of multi-word phrases. We created a dataset of phrases that include various negators, modals, and degree adverbs, as well as their combinations. Both the phrases and their constituent content words were annotated with real-valued scores of sentiment association. Using phrasal terms in the created dataset, we analyze the impact of individual modifiers and the average effect of the groups of modifiers on overall sentiment. We find that the effect of modifiers varies substantially among the members of the same group. Furthermore, each individual modifier can affect sentiment words in different ways. Therefore, solutions based on statistical learning seem more promising than fixed hand-crafted rules on the task of automatic sentiment prediction. |
| Tasks | |
| Published | 2017-12-05 |
| URL | http://arxiv.org/abs/1712.01794v1 |
| http://arxiv.org/pdf/1712.01794v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-effect-of-negators-modals-and-degree |
| Repo | |
| Framework | |
Unsupervised Learning Layers for Video Analysis
| Title | Unsupervised Learning Layers for Video Analysis |
| Authors | Liang Zhao, Yang Wang, Yi Yang, Wei Xu |
| Abstract | This paper presents two unsupervised learning layers (UL layers) for label-free video analysis: one for fully connected layers, and the other for convolutional ones. The proposed UL layers can play two roles: they can be the cost function layer for providing global training signal; meanwhile they can be added to any regular neural network layers for providing local training signals and combined with the training signals backpropagated from upper layers for extracting both slow and fast changing features at layers of different depths. Therefore, the UL layers can be used in either pure unsupervised or semi-supervised settings. Both a closed-form solution and an online learning algorithm for two UL layers are provided. Experiments with unlabeled synthetic and real-world videos demonstrated that the neural networks equipped with UL layers and trained with the proposed online learning algorithm can extract shape and motion information from video sequences of moving objects. The experiments demonstrated the potential applications of UL layers and online learning algorithm to head orientation estimation and moving object localization. |
| Tasks | Object Localization |
| Published | 2017-05-24 |
| URL | http://arxiv.org/abs/1705.08918v1 |
| http://arxiv.org/pdf/1705.08918v1.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-learning-layers-for-video |
| Repo | |
| Framework | |
Parametrizing filters of a CNN with a GAN
| Title | Parametrizing filters of a CNN with a GAN |
| Authors | Yannic Kilcher, Gary Becigneul, Thomas Hofmann |
| Abstract | It is commonly agreed that the use of relevant invariances as a good statistical bias is important in machine-learning. However, most approaches that explicitly incorporate invariances into a model architecture only make use of very simple transformations, such as translations and rotations. Hence, there is a need for methods to model and extract richer transformations that capture much higher-level invariances. To that end, we introduce a tool allowing to parametrize the set of filters of a trained convolutional neural network with the latent space of a generative adversarial network. We then show that the method can capture highly non-linear invariances of the data by visualizing their effect in the data space. |
| Tasks | |
| Published | 2017-10-31 |
| URL | http://arxiv.org/abs/1710.11386v1 |
| http://arxiv.org/pdf/1710.11386v1.pdf | |
| PWC | https://paperswithcode.com/paper/parametrizing-filters-of-a-cnn-with-a-gan |
| Repo | |
| Framework | |
Sound Event Detection Using Spatial Features and Convolutional Recurrent Neural Network
| Title | Sound Event Detection Using Spatial Features and Convolutional Recurrent Neural Network |
| Authors | Sharath Adavanne, Pasi Pertilä, Tuomas Virtanen |
| Abstract | This paper proposes to use low-level spatial features extracted from multichannel audio for sound event detection. We extend the convolutional recurrent neural network to handle more than one type of these multichannel features by learning from each of them separately in the initial stages. We show that instead of concatenating the features of each channel into a single feature vector the network learns sound events in multichannel audio better when they are presented as separate layers of a volume. Using the proposed spatial features over monaural features on the same network gives an absolute F-score improvement of 6.1% on the publicly available TUT-SED 2016 dataset and 2.7% on the TUT-SED 2009 dataset that is fifteen times larger. |
| Tasks | Sound Event Detection |
| Published | 2017-06-07 |
| URL | http://arxiv.org/abs/1706.02291v1 |
| http://arxiv.org/pdf/1706.02291v1.pdf | |
| PWC | https://paperswithcode.com/paper/sound-event-detection-using-spatial-features |
| Repo | |
| Framework | |
Implicit Regularization in Deep Learning
| Title | Implicit Regularization in Deep Learning |
| Authors | Behnam Neyshabur |
| Abstract | In an attempt to better understand generalization in deep learning, we study several possible explanations. We show that implicit regularization induced by the optimization method is playing a key role in generalization and success of deep learning models. Motivated by this view, we study how different complexity measures can ensure generalization and explain how optimization algorithms can implicitly regularize complexity measures. We empirically investigate the ability of these measures to explain different observed phenomena in deep learning. We further study the invariances in neural networks, suggest complexity measures and optimization algorithms that have similar invariances to those in neural networks and evaluate them on a number of learning tasks. |
| Tasks | |
| Published | 2017-09-06 |
| URL | http://arxiv.org/abs/1709.01953v2 |
| http://arxiv.org/pdf/1709.01953v2.pdf | |
| PWC | https://paperswithcode.com/paper/implicit-regularization-in-deep-learning |
| Repo | |
| Framework | |
Logical and Inequality Implications for Reducing the Size and Complexity of Quadratic Unconstrained Binary Optimization Problems
| Title | Logical and Inequality Implications for Reducing the Size and Complexity of Quadratic Unconstrained Binary Optimization Problems |
| Authors | Fred Glover, Mark Lewis, Gary Kochenberger |
| Abstract | The quadratic unconstrained binary optimization (QUBO) problem arises in diverse optimization applications ranging from Ising spin problems to classical problems in graph theory and binary discrete optimization. The use of preprocessing to transform the graph representing the QUBO problem into a smaller equivalent graph is important for improving solution quality and time for both exact and metaheuristic algorithms and is a step towards mapping large scale QUBO to hardware graphs used in quantum annealing computers. In an earlier paper (Lewis and Glover, 2016) a set of rules was introduced that achieved significant QUBO reductions as verified through computational testing. Here this work is extended with additional rules that provide further reductions that succeed in exactly solving 10% of the benchmark QUBO problems. An algorithm and associated data structures to efficiently implement the entire set of rules is detailed and computational experiments are reported that demonstrate their efficacy. |
| Tasks | |
| Published | 2017-05-26 |
| URL | http://arxiv.org/abs/1705.09545v1 |
| http://arxiv.org/pdf/1705.09545v1.pdf | |
| PWC | https://paperswithcode.com/paper/logical-and-inequality-implications-for |
| Repo | |
| Framework | |
Fully Automatic Segmentation of Lumbar Vertebrae from CT Images using Cascaded 3D Fully Convolutional Networks
| Title | Fully Automatic Segmentation of Lumbar Vertebrae from CT Images using Cascaded 3D Fully Convolutional Networks |
| Authors | Rens Janssens, Guodong Zeng, Guoyan Zheng |
| Abstract | We present a method to address the challenging problem of segmentation of lumbar vertebrae from CT images acquired with varying fields of view. Our method is based on cascaded 3D Fully Convolutional Networks (FCNs) consisting of a localization FCN and a segmentation FCN. More specifically, in the first step we train a regression 3D FCN (we call it “LocalizationNet”) to find the bounding box of the lumbar region. After that, a 3D U-net like FCN (we call it “SegmentationNet”) is then developed, which after training, can perform a pixel-wise multi-class segmentation to map a cropped lumber region volumetric data to its volume-wise labels. Evaluated on publicly available datasets, our method achieved an average Dice coefficient of 95.77 $\pm$ 0.81% and an average symmetric surface distance of 0.37 $\pm$ 0.06 mm. |
| Tasks | |
| Published | 2017-12-05 |
| URL | http://arxiv.org/abs/1712.01509v1 |
| http://arxiv.org/pdf/1712.01509v1.pdf | |
| PWC | https://paperswithcode.com/paper/fully-automatic-segmentation-of-lumbar |
| Repo | |
| Framework | |
A Conservation Law Method in Optimization
| Title | A Conservation Law Method in Optimization |
| Authors | Bin Shi |
| Abstract | We propose some algorithms to find local minima in nonconvex optimization and to obtain global minima in some degree from the Newton Second Law without friction. With the key observation of the velocity observable and controllable in the motion, the algorithms simulate the Newton Second Law without friction based on symplectic Euler scheme. From the intuitive analysis of analytical solution, we give a theoretical analysis for the high-speed convergence in the algorithm proposed. Finally, we propose the experiments for strongly convex function, non-strongly convex function and nonconvex function in high-dimension. |
| Tasks | |
| Published | 2017-08-27 |
| URL | http://arxiv.org/abs/1708.08035v3 |
| http://arxiv.org/pdf/1708.08035v3.pdf | |
| PWC | https://paperswithcode.com/paper/a-conservation-law-method-in-optimization |
| Repo | |
| Framework | |
Causal nearest neighbor rules for optimal treatment regimes
| Title | Causal nearest neighbor rules for optimal treatment regimes |
| Authors | Xin Zhou, Michael R. Kosorok |
| Abstract | The estimation of optimal treatment regimes is of considerable interest to precision medicine. In this work, we propose a causal $k$-nearest neighbor method to estimate the optimal treatment regime. The method roots in the framework of causal inference, and estimates the causal treatment effects within the nearest neighborhood. Although the method is simple, it possesses nice theoretical properties. We show that the causal $k$-nearest neighbor regime is universally consistent. That is, the causal $k$-nearest neighbor regime will eventually learn the optimal treatment regime as the sample size increases. We also establish its convergence rate. However, the causal $k$-nearest neighbor regime may suffer from the curse of dimensionality, i.e. performance deteriorates as dimensionality increases. To alleviate this problem, we develop an adaptive causal $k$-nearest neighbor method to perform metric selection and variable selection simultaneously. The performance of the proposed methods is illustrated in simulation studies and in an analysis of a chronic depression clinical trial. |
| Tasks | Causal Inference |
| Published | 2017-11-22 |
| URL | http://arxiv.org/abs/1711.08451v1 |
| http://arxiv.org/pdf/1711.08451v1.pdf | |
| PWC | https://paperswithcode.com/paper/causal-nearest-neighbor-rules-for-optimal |
| Repo | |
| Framework | |
Dilated Deep Residual Network for Image Denoising
| Title | Dilated Deep Residual Network for Image Denoising |
| Authors | Tianyang Wang, Mingxuan Sun, Kaoning Hu |
| Abstract | Variations of deep neural networks such as convolutional neural network (CNN) have been successfully applied to image denoising. The goal is to automatically learn a mapping from a noisy image to a clean image given training data consisting of pairs of noisy and clean images. Most existing CNN models for image denoising have many layers. In such cases, the models involve a large amount of parameters and are computationally expensive to train. In this paper, we develop a dilated residual CNN for Gaussian image denoising. Compared with the recently proposed residual denoiser, our method can achieve comparable performance with less computational cost. Specifically, we enlarge receptive field by adopting dilated convolution in residual network, and the dilation factor is set to a certain value. We utilize appropriate zero padding to make the dimension of the output the same as the input. It has been proven that the expansion of receptive field can boost the CNN performance in image classification, and we further demonstrate that it can also lead to competitive performance for denoising problem. Moreover, we present a formula to calculate receptive field size when dilated convolution is incorporated. Thus, the change of receptive field can be interpreted mathematically. To validate the efficacy of our approach, we conduct extensive experiments for both gray and color image denoising with specific or randomized noise levels. Both of the quantitative measurements and the visual results of denoising are promising comparing with state-of-the-art baselines. |
| Tasks | Denoising, Image Classification, Image Denoising |
| Published | 2017-08-18 |
| URL | http://arxiv.org/abs/1708.05473v3 |
| http://arxiv.org/pdf/1708.05473v3.pdf | |
| PWC | https://paperswithcode.com/paper/dilated-deep-residual-network-for-image |
| Repo | |
| Framework | |
Object classification in images of Neoclassical furniture using Deep Learning
| Title | Object classification in images of Neoclassical furniture using Deep Learning |
| Authors | Bernhard Bermeitinger, André Freitas, Simon Donig, Siegfried Handschuh |
| Abstract | This short paper outlines research results on object classification in images of Neoclassical furniture. The motivation was to provide an object recognition framework which is able to support the alignment of furniture images with a symbolic level model. A data-driven bottom-up research routine in the Neoclassica research framework is the main use-case. It strives to deliver tools for analyzing the spread of aesthetic forms which are considered as a cultural transfer process. |
| Tasks | Object Classification, Object Recognition |
| Published | 2017-03-07 |
| URL | http://arxiv.org/abs/1703.02445v1 |
| http://arxiv.org/pdf/1703.02445v1.pdf | |
| PWC | https://paperswithcode.com/paper/object-classification-in-images-of-1 |
| Repo | |
| Framework | |
The University of Edinburgh’s Neural MT Systems for WMT17
| Title | The University of Edinburgh’s Neural MT Systems for WMT17 |
| Authors | Rico Sennrich, Alexandra Birch, Anna Currey, Ulrich Germann, Barry Haddow, Kenneth Heafield, Antonio Valerio Miceli Barone, Philip Williams |
| Abstract | This paper describes the University of Edinburgh’s submissions to the WMT17 shared news translation and biomedical translation tasks. We participated in 12 translation directions for news, translating between English and Czech, German, Latvian, Russian, Turkish and Chinese. For the biomedical task we submitted systems for English to Czech, German, Polish and Romanian. Our systems are neural machine translation systems trained with Nematus, an attentional encoder-decoder. We follow our setup from last year and build BPE-based models with parallel and back-translated monolingual training data. Novelties this year include the use of deep architectures, layer normalization, and more compact models due to weight tying and improvements in BPE segmentations. We perform extensive ablative experiments, reporting on the effectivenes of layer normalization, deep architectures, and different ensembling techniques. |
| Tasks | Machine Translation |
| Published | 2017-08-02 |
| URL | http://arxiv.org/abs/1708.00726v1 |
| http://arxiv.org/pdf/1708.00726v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-university-of-edinburghs-neural-mt |
| Repo | |
| Framework | |
The Inflation Technique Completely Solves the Causal Compatibility Problem
| Title | The Inflation Technique Completely Solves the Causal Compatibility Problem |
| Authors | Miguel Navascues, Elie Wolfe |
| Abstract | The causal compatibility question asks whether a given causal structure graph — possibly involving latent variables — constitutes a genuinely plausible causal explanation for a given probability distribution over the graph’s observed variables. Algorithms predicated on merely necessary constraints for causal compatibility typically suffer from false negatives, i.e. they admit incompatible distributions as apparently compatible with the given graph. In [arXiv:1609.00672], one of us introduced the inflation technique for formulating useful relaxations of the causal compatibility problem in terms of linear programming. In this work, we develop a formal hierarchy of such causal compatibility relaxations. We prove that inflation is asymptotically tight, i.e., that the hierarchy converges to a zero-error test for causal compatibility. In this sense, the inflation technique fulfills a longstanding desideratum in the field of causal inference. We quantify the rate of convergence by showing that any distribution which passes the $n^{th}$-order inflation test must be $O\left(n^{-1/2}\right)$-close in Euclidean norm to some distribution genuinely compatible with the given causal structure. Furthermore, we show that for many causal structures, the (unrelaxed) causal compatibility problem is faithfully formulated already by either the first or second order inflation test. |
| Tasks | Causal Inference |
| Published | 2017-07-20 |
| URL | https://arxiv.org/abs/1707.06476v2 |
| https://arxiv.org/pdf/1707.06476v2.pdf | |
| PWC | https://paperswithcode.com/paper/the-inflation-technique-solves-completely-the |
| Repo | |
| Framework | |
Deep Depth Inference using Binocular and Monocular Cues
| Title | Deep Depth Inference using Binocular and Monocular Cues |
| Authors | Xinqing Guo, Zhang Chen, Siyuan Li, Yang Yang, Jingyi Yu |
| Abstract | Human visual system relies on both binocular stereo cues and monocular focusness cues to gain effective 3D perception. In computer vision, the two problems are traditionally solved in separate tracks. In this paper, we present a unified learning-based technique that simultaneously uses both types of cues for depth inference. Specifically, we use a pair of focal stacks as input to emulate human perception. We first construct a comprehensive focal stack training dataset synthesized by depth-guided light field rendering. We then construct three individual networks: a FocusNet to extract depth from a single focal stack, a EDoFNet to obtain the extended depth of field (EDoF) image from the focal stack, and a StereoNet to conduct stereo matching. We then integrate them into a unified solution to obtain high quality depth maps. Comprehensive experiments show that our approach outperforms the state-of-the-art in both accuracy and speed and effectively emulates human vision systems. |
| Tasks | Stereo Matching, Stereo Matching Hand |
| Published | 2017-11-29 |
| URL | http://arxiv.org/abs/1711.10729v3 |
| http://arxiv.org/pdf/1711.10729v3.pdf | |
| PWC | https://paperswithcode.com/paper/deep-depth-inference-using-binocular-and |
| Repo | |
| Framework | |
