May 6, 2019

2609 words 13 mins read

Paper Group ANR 299

Interactive Image Segmentation From A Feedback Control Perspective. Sparse Factorization Layers for Neural Networks with Limited Supervision. Broad Context Language Modeling as Reading Comprehension. A Comprehensive Study of Deep Bidirectional LSTM RNNs for Acoustic Modeling in Speech Recognition. Dialogue Session Segmentation by Embedding-Enhanced …

Interactive Image Segmentation From A Feedback Control Perspective


Title	Interactive Image Segmentation From A Feedback Control Perspective
Authors	Liangjia Zhu, Peter Karasev, Ivan Kolesov, Romeil Sandhu, Allen Tannenbaum
Abstract	Image segmentation is a fundamental problem in computational vision and medical imaging. Designing a generic, automated method that works for various objects and imaging modalities is a formidable task. Instead of proposing a new specific segmentation algorithm, we present a general design principle on how to integrate user interactions from the perspective of feedback control theory. Impulsive control and Lyapunov stability analysis are employed to design and analyze an interactive segmentation system. Then stabilization conditions are derived to guide algorithm design. Finally, the effectiveness and robustness of proposed method are demonstrated.
Tasks	Interactive Segmentation, Semantic Segmentation
Published	2016-06-26
URL	http://arxiv.org/abs/1606.08008v2
PDF	http://arxiv.org/pdf/1606.08008v2.pdf
PWC	https://paperswithcode.com/paper/interactive-image-segmentation-from-a
Repo
Framework

Sparse Factorization Layers for Neural Networks with Limited Supervision


Title	Sparse Factorization Layers for Neural Networks with Limited Supervision
Authors	Parker Koch, Jason J. Corso
Abstract	Whereas CNNs have demonstrated immense progress in many vision problems, they suffer from a dependence on monumental amounts of labeled training data. On the other hand, dictionary learning does not scale to the size of problems that CNNs can handle, despite being very effective at low-level vision tasks such as denoising and inpainting. Recently, interest has grown in adapting dictionary learning methods for supervised tasks such as classification and inverse problems. We propose two new network layers that are based on dictionary learning: a sparse factorization layer and a convolutional sparse factorization layer, analogous to fully-connected and convolutional layers, respectively. Using our derivations, these layers can be dropped in to existing CNNs, trained together in an end-to-end fashion with back-propagation, and leverage semisupervision in ways classical CNNs cannot. We experimentally compare networks with these two new layers against a baseline CNN. Our results demonstrate that networks with either of the sparse factorization layers are able to outperform classical CNNs when supervised data are few. They also show performance improvements in certain tasks when compared to the CNN with no sparse factorization layers with the same exact number of parameters.
Tasks	Denoising, Dictionary Learning
Published	2016-12-14
URL	http://arxiv.org/abs/1612.04468v1
PDF	http://arxiv.org/pdf/1612.04468v1.pdf
PWC	https://paperswithcode.com/paper/sparse-factorization-layers-for-neural
Repo
Framework

Broad Context Language Modeling as Reading Comprehension


Title	Broad Context Language Modeling as Reading Comprehension
Authors	Zewei Chu, Hai Wang, Kevin Gimpel, David McAllester
Abstract	Progress in text understanding has been driven by large datasets that test particular capabilities, like recent datasets for reading comprehension (Hermann et al., 2015). We focus here on the LAMBADA dataset (Paperno et al., 2016), a word prediction task requiring broader context than the immediate sentence. We view LAMBADA as a reading comprehension problem and apply comprehension models based on neural networks. Though these models are constrained to choose a word from the context, they improve the state of the art on LAMBADA from 7.3% to 49%. We analyze 100 instances, finding that neural network readers perform well in cases that involve selecting a name from the context based on dialogue or discourse cues but struggle when coreference resolution or external knowledge is needed.
Tasks	Coreference Resolution, Language Modelling, Reading Comprehension
Published	2016-10-26
URL	http://arxiv.org/abs/1610.08431v3
PDF	http://arxiv.org/pdf/1610.08431v3.pdf
PWC	https://paperswithcode.com/paper/broad-context-language-modeling-as-reading
Repo
Framework

A Comprehensive Study of Deep Bidirectional LSTM RNNs for Acoustic Modeling in Speech Recognition


Title	A Comprehensive Study of Deep Bidirectional LSTM RNNs for Acoustic Modeling in Speech Recognition
Authors	Albert Zeyer, Patrick Doetsch, Paul Voigtlaender, Ralf Schlüter, Hermann Ney
Abstract	We present a comprehensive study of deep bidirectional long short-term memory (LSTM) recurrent neural network (RNN) based acoustic models for automatic speech recognition (ASR). We study the effect of size and depth and train models of up to 8 layers. We investigate the training aspect and study different variants of optimization methods, batching, truncated backpropagation, different regularization techniques such as dropout and $L_2$ regularization, and different gradient clipping variants. The major part of the experimental analysis was performed on the Quaero corpus. Additional experiments also were performed on the Switchboard corpus. Our best LSTM model has a relative improvement in word error rate of over 14% compared to our best feed-forward neural network (FFNN) baseline on the Quaero task. On this task, we get our best result with an 8 layer bidirectional LSTM and we show that a pretraining scheme with layer-wise construction helps for deep LSTMs. Finally we compare the training calculation time of many of the presented experiments in relation with recognition performance. All the experiments were done with RETURNN, the RWTH extensible training framework for universal recurrent neural networks in combination with RASR, the RWTH ASR toolkit.
Tasks	Speech Recognition
Published	2016-06-22
URL	http://arxiv.org/abs/1606.06871v2
PDF	http://arxiv.org/pdf/1606.06871v2.pdf
PWC	https://paperswithcode.com/paper/a-comprehensive-study-of-deep-bidirectional
Repo
Framework

Dialogue Session Segmentation by Embedding-Enhanced TextTiling


Title	Dialogue Session Segmentation by Embedding-Enhanced TextTiling
Authors	Yiping Song, Lili Mou, Rui Yan, Li Yi, Zinan Zhu, Xiaohua Hu, Ming Zhang
Abstract	In human-computer conversation systems, the context of a user-issued utterance is particularly important because it provides useful background information of the conversation. However, it is unwise to track all previous utterances in the current session as not all of them are equally important. In this paper, we address the problem of session segmentation. We propose an embedding-enhanced TextTiling approach, inspired by the observation that conversation utterances are highly noisy, and that word embeddings provide a robust way of capturing semantics. Experimental results show that our approach achieves better performance than the TextTiling, MMD approaches.
Tasks	Word Embeddings
Published	2016-10-13
URL	http://arxiv.org/abs/1610.03955v1
PDF	http://arxiv.org/pdf/1610.03955v1.pdf
PWC	https://paperswithcode.com/paper/dialogue-session-segmentation-by-embedding
Repo
Framework

Privacy-Preserved Big Data Analysis Based on Asymmetric Imputation Kernels and Multiside Similarities


Title	Privacy-Preserved Big Data Analysis Based on Asymmetric Imputation Kernels and Multiside Similarities
Authors	Bo-Wei Chen
Abstract	This study presents an efficient approach for incomplete data classification, where the entries of samples are missing or masked due to privacy preservation. To deal with these incomplete data, a new kernel function with asymmetric intrinsic mappings is proposed in this study. Such a new kernel uses three-side similarities for kernel matrix formation. The similarity between a testing instance and a training sample relies not only on their distance but also on the relation between the testing sample and the centroid of the class, where the training sample belongs. This reduces biased estimation compared with typical methods when only one training sample is used for kernel matrix formation. Furthermore, centroid generation does not involve any clustering algorithms. The proposed kernel is capable of performing data imputation by using class-dependent averages. This enhances Fisher Discriminant Ratios and data discriminability. Experiments on two open databases were carried out for evaluating the proposed method. The result indicated that the accuracy of the proposed method was higher than that of the baseline. These findings thereby demonstrated the effectiveness of the proposed idea.
Tasks	Imputation
Published	2016-03-25
URL	http://arxiv.org/abs/1603.07828v2
PDF	http://arxiv.org/pdf/1603.07828v2.pdf
PWC	https://paperswithcode.com/paper/privacy-preserved-big-data-analysis-based-on
Repo
Framework

Distributed Gaussian Learning over Time-varying Directed Graphs


Title	Distributed Gaussian Learning over Time-varying Directed Graphs
Authors	Angelia Nedić, Alex Olshevsky, César A. Uribe
Abstract	We present a distributed (non-Bayesian) learning algorithm for the problem of parameter estimation with Gaussian noise. The algorithm is expressed as explicit updates on the parameters of the Gaussian beliefs (i.e. means and precision). We show a convergence rate of $O(1/k)$ with the constant term depending on the number of agents and the topology of the network. Moreover, we show almost sure convergence to the optimal solution of the estimation problem for the general case of time-varying directed graphs.
Tasks
Published	2016-12-06
URL	http://arxiv.org/abs/1612.01600v2
PDF	http://arxiv.org/pdf/1612.01600v2.pdf
PWC	https://paperswithcode.com/paper/distributed-gaussian-learning-over-time
Repo
Framework

3D Deeply Supervised Network for Automatic Liver Segmentation from CT Volumes


Title	3D Deeply Supervised Network for Automatic Liver Segmentation from CT Volumes
Authors	Qi Dou, Hao Chen, Yueming Jin, Lequan Yu, Jing Qin, Pheng-Ann Heng
Abstract	Automatic liver segmentation from CT volumes is a crucial prerequisite yet challenging task for computer-aided hepatic disease diagnosis and treatment. In this paper, we present a novel 3D deeply supervised network (3D DSN) to address this challenging task. The proposed 3D DSN takes advantage of a fully convolutional architecture which performs efficient end-to-end learning and inference. More importantly, we introduce a deep supervision mechanism during the learning process to combat potential optimization difficulties, and thus the model can acquire a much faster convergence rate and more powerful discrimination capability. On top of the high-quality score map produced by the 3D DSN, a conditional random field model is further employed to obtain refined segmentation results. We evaluated our framework on the public MICCAI-SLiver07 dataset. Extensive experiments demonstrated that our method achieves competitive segmentation results to state-of-the-art approaches with a much faster processing speed.
Tasks	Liver Segmentation
Published	2016-07-03
URL	http://arxiv.org/abs/1607.00582v1
PDF	http://arxiv.org/pdf/1607.00582v1.pdf
PWC	https://paperswithcode.com/paper/3d-deeply-supervised-network-for-automatic
Repo
Framework

Collaborative filtering via sparse Markov random fields


Title	Collaborative filtering via sparse Markov random fields
Authors	Truyen Tran, Dinh Phung, Svetha Venkatesh
Abstract	Recommender systems play a central role in providing individualized access to information and services. This paper focuses on collaborative filtering, an approach that exploits the shared structure among mind-liked users and similar items. In particular, we focus on a formal probabilistic framework known as Markov random fields (MRF). We address the open problem of structure learning and introduce a sparsity-inducing algorithm to automatically estimate the interaction structures between users and between items. Item-item and user-user correlation networks are obtained as a by-product. Large-scale experiments on movie recommendation and date matching datasets demonstrate the power of the proposed method.
Tasks	Recommendation Systems
Published	2016-02-09
URL	http://arxiv.org/abs/1602.02842v1
PDF	http://arxiv.org/pdf/1602.02842v1.pdf
PWC	https://paperswithcode.com/paper/collaborative-filtering-via-sparse-markov
Repo
Framework

Approximate maximum entropy principles via Goemans-Williamson with applications to provable variational methods


Title	Approximate maximum entropy principles via Goemans-Williamson with applications to provable variational methods
Authors	Yuanzhi Li, Andrej Risteski
Abstract	The well known maximum-entropy principle due to Jaynes, which states that given mean parameters, the maximum entropy distribution matching them is in an exponential family, has been very popular in machine learning due to its “Occam’s razor” interpretation. Unfortunately, calculating the potentials in the maximum-entropy distribution is intractable \cite{bresler2014hardness}. We provide computationally efficient versions of this principle when the mean parameters are pairwise moments: we design distributions that approximately match given pairwise moments, while having entropy which is comparable to the maximum entropy distribution matching those moments. We additionally provide surprising applications of the approximate maximum entropy principle to designing provable variational methods for partition function calculations for Ising models without any assumptions on the potentials of the model. More precisely, we show that in every temperature, we can get approximation guarantees for the log-partition function comparable to those in the low-temperature limit, which is the setting of optimization of quadratic forms over the hypercube. \cite{alon2006approximating}
Tasks
Published	2016-07-12
URL	http://arxiv.org/abs/1607.03360v1
PDF	http://arxiv.org/pdf/1607.03360v1.pdf
PWC	https://paperswithcode.com/paper/approximate-maximum-entropy-principles-via
Repo
Framework

Grading of Mammalian Cumulus Oocyte Complexes using Machine Learning for in Vitro Embryo Culture


Title	Grading of Mammalian Cumulus Oocyte Complexes using Machine Learning for in Vitro Embryo Culture
Authors	Viswanath P Sudarshan, Tobias Weiser, Phalgun Chintala, Subhamoy Mandal, Rahul Dutta
Abstract	Visual observation of Cumulus Oocyte Complexes provides only limited information about its functional competence, whereas the molecular evaluations methods are cumbersome or costly. Image analysis of mammalian oocytes can provide attractive alternative to address this challenge. However, it is complex, given the huge number of oocytes under inspection and the subjective nature of the features inspected for identification. Supervised machine learning methods like random forest with annotations from expert biologists can make the analysis task standardized and reduces inter-subject variability. We present a semi-automatic framework for predicting the class an oocyte belongs to, based on multi-object parametric segmentation on the acquired microscopic image followed by a feature based classification using random forests.
Tasks
Published	2016-03-05
URL	http://arxiv.org/abs/1603.01739v1
PDF	http://arxiv.org/pdf/1603.01739v1.pdf
PWC	https://paperswithcode.com/paper/grading-of-mammalian-cumulus-oocyte-complexes
Repo
Framework

Machine Learning for Dental Image Analysis


Title	Machine Learning for Dental Image Analysis
Authors	Young-jun Yu
Abstract	In order to study the application of artificial intelligence (AI) to dental imaging, we applied AI technology to classify a set of panoramic radiographs using (a) a convolutional neural network (CNN) which is a form of an artificial neural network (ANN), (b) representative image cognition algorithms that implement scale-invariant feature transform (SIFT), and (c) histogram of oriented gradients (HOG).
Tasks
Published	2016-11-30
URL	http://arxiv.org/abs/1611.09958v2
PDF	http://arxiv.org/pdf/1611.09958v2.pdf
PWC	https://paperswithcode.com/paper/machine-learning-for-dental-image-analysis
Repo
Framework

Starting Small – Learning with Adaptive Sample Sizes


Title	Starting Small – Learning with Adaptive Sample Sizes
Authors	Hadi Daneshmand, Aurelien Lucchi, Thomas Hofmann
Abstract	For many machine learning problems, data is abundant and it may be prohibitive to make multiple passes through the full training set. In this context, we investigate strategies for dynamically increasing the effective sample size, when using iterative methods such as stochastic gradient descent. Our interest is motivated by the rise of variance-reduced methods, which achieve linear convergence rates that scale favorably for smaller sample sizes. Exploiting this feature, we show – theoretically and empirically – how to obtain significant speed-ups with a novel algorithm that reaches statistical accuracy on an $n$-sample in $2n$, instead of $n \log n$ steps.
Tasks
Published	2016-03-09
URL	http://arxiv.org/abs/1603.02839v2
PDF	http://arxiv.org/pdf/1603.02839v2.pdf
PWC	https://paperswithcode.com/paper/starting-small-learning-with-adaptive-sample
Repo
Framework

Stock trend prediction using news sentiment analysis


Title	Stock trend prediction using news sentiment analysis
Authors	Joshi Kalyani, Prof. H. N. Bharathi, Prof. Rao Jyothi
Abstract	Efficient Market Hypothesis is the popular theory about stock prediction. With its failure much research has been carried in the area of prediction of stocks. This project is about taking non quantifiable data such as financial news articles about a company and predicting its future stock trend with news sentiment classification. Assuming that news articles have impact on stock market, this is an attempt to study relationship between news and stock trend. To show this, we created three different classification models which depict polarity of news articles being positive or negative. Observations show that RF and SVM perform well in all types of testing. Na"ive Bayes gives good result but not compared to the other two. Experiments are conducted to evaluate various aspects of the proposed model and encouraging results are obtained in all of the experiments. The accuracy of the prediction model is more than 80% and in comparison with news random labeling with 50% of accuracy; the model has increased the accuracy by 30%.
Tasks	Sentiment Analysis, Stock Prediction, Stock Trend Prediction
Published	2016-07-07
URL	http://arxiv.org/abs/1607.01958v1
PDF	http://arxiv.org/pdf/1607.01958v1.pdf
PWC	https://paperswithcode.com/paper/stock-trend-prediction-using-news-sentiment
Repo
Framework

Automatic 3D Reconstruction of Manifold Meshes via Delaunay Triangulation and Mesh Sweeping


Title	Automatic 3D Reconstruction of Manifold Meshes via Delaunay Triangulation and Mesh Sweeping
Authors	Andrea Romanoni, Amaël Delaunoy, Marc Pollefeys, Matteo Matteucci
Abstract	In this paper we propose a new approach to incrementally initialize a manifold surface for automatic 3D reconstruction from images. More precisely we focus on the automatic initialization of a 3D mesh as close as possible to the final solution; indeed many approaches require a good initial solution for further refinement via multi-view stereo techniques. Our novel algorithm automatically estimates an initial manifold mesh for surface evolving multi-view stereo algorithms, where the manifold property needs to be enforced. It bootstraps from 3D points extracted via Structure from Motion, then iterates between a state-of-the-art manifold reconstruction step and a novel mesh sweeping algorithm that looks for new 3D points in the neighborhood of the reconstructed manifold to be added in the manifold reconstruction. The experimental results show quantitatively that the mesh sweeping improves the resolution and the accuracy of the manifold reconstruction, allowing a better convergence of state-of-the-art surface evolution multi-view stereo algorithms.
Tasks	3D Reconstruction
Published	2016-04-21
URL	http://arxiv.org/abs/1604.06258v1
PDF	http://arxiv.org/pdf/1604.06258v1.pdf
PWC	https://paperswithcode.com/paper/automatic-3d-reconstruction-of-manifold
Repo
Framework