July 27, 2019

3164 words 15 mins read

Paper Group ANR 687

Knowledge Concentration: Learning 100K Object Classifiers in a Single CNN. Segmentation of Glioma Tumors in Brain Using Deep Convolutional Neural Network. Representing Hybrid Automata by Action Language Modulo Theories. Interactive Graphics for Visually Diagnosing Forest Classifiers in R. Learning the kernel matrix by resampling. Multi-stage Neural …

Knowledge Concentration: Learning 100K Object Classifiers in a Single CNN


Title	Knowledge Concentration: Learning 100K Object Classifiers in a Single CNN
Authors	Jiyang Gao, Zijian, Guo, Zhen Li, Ram Nevatia
Abstract	Fine-grained image labels are desirable for many computer vision applications, such as visual search or mobile AI assistant. These applications rely on image classification models that can produce hundreds of thousands (e.g. 100K) of diversified fine-grained image labels on input images. However, training a network at this vocabulary scale is challenging, and suffers from intolerable large model size and slow training speed, which leads to unsatisfying classification performance. A straightforward solution would be training separate expert networks (specialists), with each specialist focusing on learning one specific vertical (e.g. cars, birds…). However, deploying dozens of expert networks in a practical system would significantly increase system complexity and inference latency, and consumes large amounts of computational resources. To address these challenges, we propose a Knowledge Concentration method, which effectively transfers the knowledge from dozens of specialists (multiple teacher networks) into one single model (one student network) to classify 100K object categories. There are three salient aspects in our method: (1) a multi-teacher single-student knowledge distillation framework; (2) a self-paced learning mechanism to allow the student to learn from different teachers at various paces; (3) structurally connected layers to expand the student network capacity with limited extra parameters. We validate our method on OpenImage and a newly collected dataset, Entity-Foto-Tree (EFT), with 100K categories, and show that the proposed model performs significantly better than the baseline generalist model.
Tasks	Image Classification
Published	2017-11-21
URL	http://arxiv.org/abs/1711.07607v2
PDF	http://arxiv.org/pdf/1711.07607v2.pdf
PWC	https://paperswithcode.com/paper/knowledge-concentration-learning-100k-object
Repo
Framework

Segmentation of Glioma Tumors in Brain Using Deep Convolutional Neural Network


Title	Segmentation of Glioma Tumors in Brain Using Deep Convolutional Neural Network
Authors	Saddam Hussain, Syed Muhammad Anwar, Muhammad Majid
Abstract	Detection of brain tumor using a segmentation based approach is critical in cases, where survival of a subject depends on an accurate and timely clinical diagnosis. Gliomas are the most commonly found tumors having irregular shape and ambiguous boundaries, making them one of the hardest tumors to detect. The automation of brain tumor segmentation remains a challenging problem mainly due to significant variations in its structure. An automated brain tumor segmentation algorithm using deep convolutional neural network (DCNN) is presented in this paper. A patch based approach along with an inception module is used for training the deep network by extracting two co-centric patches of different sizes from the input images. Recent developments in deep neural networks such as drop-out, batch normalization, non-linear activation and inception module are used to build a new ILinear nexus architecture. The module overcomes the over-fitting problem arising due to scarcity of data using drop-out regularizer. Images are normalized and bias field corrected in the pre-processing step and then extracted patches are passed through a DCNN, which assigns an output label to the central pixel of each patch. Morphological operators are used for post-processing to remove small false positives around the edges. A two-phase weighted training method is introduced and evaluated using BRATS 2013 and BRATS 2015 datasets, where it improves the performance parameters of state-of-the-art techniques under similar settings.
Tasks	Brain Tumor Segmentation
Published	2017-08-01
URL	http://arxiv.org/abs/1708.00377v1
PDF	http://arxiv.org/pdf/1708.00377v1.pdf
PWC	https://paperswithcode.com/paper/segmentation-of-glioma-tumors-in-brain-using
Repo
Framework

Representing Hybrid Automata by Action Language Modulo Theories


Title	Representing Hybrid Automata by Action Language Modulo Theories
Authors	Joohyung Lee, Nikhil Loney, Yunsong Meng
Abstract	Both hybrid automata and action languages are formalisms for describing the evolution of dynamic systems. This paper establishes a formal relationship between them. We show how to succinctly represent hybrid automata in an action language which in turn is defined as a high-level notation for answer set programming modulo theories (ASPMT) — an extension of answer set programs to the first-order level similar to the way satisfiability modulo theories (SMT) extends propositional satisfiability (SAT). We first show how to represent linear hybrid automata with convex invariants by an action language modulo theories. A further translation into SMT allows for computing them using SMT solvers that support arithmetic over reals. Next, we extend the representation to the general class of non-linear hybrid automata allowing even non-convex invariants. We represent them by an action language modulo ODE (Ordinary Differential Equations), which can be compiled into satisfiability modulo ODE. We developed a prototype system cplus2aspmt based on these translations, which allows for a succinct representation of hybrid transition systems that can be computed effectively by the state-of-the-art SMT solver dReal.
Tasks
Published	2017-07-20
URL	http://arxiv.org/abs/1707.06387v2
PDF	http://arxiv.org/pdf/1707.06387v2.pdf
PWC	https://paperswithcode.com/paper/representing-hybrid-automata-by-action
Repo
Framework

Interactive Graphics for Visually Diagnosing Forest Classifiers in R


Title	Interactive Graphics for Visually Diagnosing Forest Classifiers in R
Authors	Natalia da Silva, Dianne Cook, Eun-Kyung Lee
Abstract	This paper describes structuring data and constructing plots to explore forest classification models interactively. A forest classifier is an example of an ensemble, produced by bagging multiple trees. The process of bagging and combining results from multiple trees, produces numerous diagnostics which, with interactive graphics, can provide a lot of insight into class structure in high dimensions. Various aspects are explored in this paper, to assess model complexity, individual model contributions, variable importance and dimension reduction, and uncertainty in prediction associated with individual observations. The ideas are applied to the random forest algorithm, and to the projection pursuit forest, but could be more broadly applied to other bagged ensembles. Interactive graphics are built in R, using the ggplot2, plotly, and shiny packages.
Tasks	Dimensionality Reduction
Published	2017-04-08
URL	http://arxiv.org/abs/1704.02502v1
PDF	http://arxiv.org/pdf/1704.02502v1.pdf
PWC	https://paperswithcode.com/paper/interactive-graphics-for-visually-diagnosing
Repo
Framework

Learning the kernel matrix by resampling


Title	Learning the kernel matrix by resampling
Authors	Xiao-Lei Zhang
Abstract	In this abstract paper, we introduce a new kernel learning method by a nonparametric density estimator. The estimator consists of a group of k-centroids clusterings. Each clustering randomly selects data points with randomly selected features as its centroids, and learns a one-hot encoder by one-nearest-neighbor optimization. The estimator generates a sparse representation for each data point. Then, we construct a nonlinear kernel matrix from the sparse representation of data. One major advantage of the proposed kernel method is that it is relatively insensitive to its free parameters, and therefore, it can produce reasonable results without parameter tuning. Another advantage is that it is simple. We conjecture that the proposed method can find its applications in many learning tasks or methods where sparse representation or kernel matrix is explored. In this preliminary study, we have applied the kernel matrix to spectral clustering. Our experimental results demonstrate that the kernel generated by the proposed method outperforms the well-tuned Gaussian RBF kernel. This abstract paper is used to protect the idea, full versions will be updated later.
Tasks
Published	2017-08-01
URL	http://arxiv.org/abs/1708.00365v1
PDF	http://arxiv.org/pdf/1708.00365v1.pdf
PWC	https://paperswithcode.com/paper/learning-the-kernel-matrix-by-resampling
Repo
Framework

Multi-stage Neural Networks with Single-sided Classifiers for False Positive Reduction and its Evaluation using Lung X-ray CT Images


Title	Multi-stage Neural Networks with Single-sided Classifiers for False Positive Reduction and its Evaluation using Lung X-ray CT Images
Authors	Masaharu Sakamoto, Hiroki Nakano, Kun Zhao, Taro Sekiyama
Abstract	Lung nodule classification is a class imbalanced problem because nodules are found with much lower frequency than non-nodules. In the class imbalanced problem, conventional classifiers tend to be overwhelmed by the majority class and ignore the minority class. We therefore propose cascaded convolutional neural networks to cope with the class imbalanced problem. In the proposed approach, multi-stage convolutional neural networks that perform as single-sided classifiers filter out obvious non-nodules. Successively, a convolutional neural network trained with a balanced data set calculates nodule probabilities. The proposed method achieved the sensitivity of 92.4% and 94.5% at 4 and 8 false positives per scan in Free Receiver Operating Characteristics (FROC) curve analysis, respectively.
Tasks	Lung Nodule Classification
Published	2017-03-01
URL	http://arxiv.org/abs/1703.00311v3
PDF	http://arxiv.org/pdf/1703.00311v3.pdf
PWC	https://paperswithcode.com/paper/multi-stage-neural-networks-with-single-sided
Repo
Framework

Together We Know How to Achieve: An Epistemic Logic of Know-How (Extended Abstract)


Title	Together We Know How to Achieve: An Epistemic Logic of Know-How (Extended Abstract)
Authors	Pavel Naumov, Jia Tao
Abstract	The existence of a coalition strategy to achieve a goal does not necessarily mean that the coalition has enough information to know how to follow the strategy. Neither does it mean that the coalition knows that such a strategy exists. The paper studies an interplay between the distributed knowledge, coalition strategies, and coalition “know-how” strategies. The main technical result is a sound and complete trimodal logical system that describes the properties of this interplay.
Tasks
Published	2017-07-27
URL	http://arxiv.org/abs/1707.08759v1
PDF	http://arxiv.org/pdf/1707.08759v1.pdf
PWC	https://paperswithcode.com/paper/together-we-know-how-to-achieve-an-epistemic-1
Repo
Framework

Momo: Monocular Motion Estimation on Manifolds


Title	Momo: Monocular Motion Estimation on Manifolds
Authors	Johannes Graeter, Tobias Strauss, Martin Lauer
Abstract	Knowledge about the location of a vehicle is indispensable for autonomous driving. In order to apply global localisation methods, a pose prior must be known which can be obtained from visual odometry. The quality and robustness of that prior determine the success of localisation. Momo is a monocular frame-to-frame motion estimation methodology providing a high quality visual odometry for that purpose. By taking into account the motion model of the vehicle, reliability and accuracy of the pose prior are significantly improved. We show that especially in low-structure environments Momo outperforms the state of the art. Moreover, the method is designed so that multiple cameras with or without overlap can be integrated. The evaluation on the KITTI-dataset and on a proper multi-camera dataset shows that even with only 100–300 feature matches the prior is estimated with high accuracy and in real-time.
Tasks	Autonomous Driving, Motion Estimation, Visual Odometry
Published	2017-08-01
URL	http://arxiv.org/abs/1708.00397v1
PDF	http://arxiv.org/pdf/1708.00397v1.pdf
PWC	https://paperswithcode.com/paper/momo-monocular-motion-estimation-on-manifolds
Repo
Framework

On Approximation Guarantees for Greedy Low Rank Optimization


Title	On Approximation Guarantees for Greedy Low Rank Optimization
Authors	Rajiv Khanna, Ethan Elenberg, Alexandros G. Dimakis, Sahand Negahban
Abstract	We provide new approximation guarantees for greedy low rank matrix estimation under standard assumptions of restricted strong convexity and smoothness. Our novel analysis also uncovers previously unknown connections between the low rank estimation and combinatorial optimization, so much so that our bounds are reminiscent of corresponding approximation bounds in submodular maximization. Additionally, we also provide statistical recovery guarantees. Finally, we present empirical comparison of greedy estimation with established baselines on two important real-world problems.
Tasks	Combinatorial Optimization
Published	2017-03-08
URL	http://arxiv.org/abs/1703.02721v1
PDF	http://arxiv.org/pdf/1703.02721v1.pdf
PWC	https://paperswithcode.com/paper/on-approximation-guarantees-for-greedy-low
Repo
Framework

Scalable Peaceman-Rachford Splitting Method with Proximal Terms


Title	Scalable Peaceman-Rachford Splitting Method with Proximal Terms
Authors	Sen Na, Mingyuan Ma, Mladen Kolar
Abstract	Along with developing of Peaceman-Rachford Splittling Method (PRSM), many batch algorithms based on it have been studied very deeply. But almost no algorithm focused on the performance of stochastic version of PRSM. In this paper, we propose a new stochastic algorithm based on PRSM, prove its convergence rate in ergodic sense, and test its performance on both artificial and real data. We show that our proposed algorithm, Stochastic Scalable PRSM (SS-PRSM), enjoys the $O(1/K)$ convergence rate, which is the same as those newest stochastic algorithms that based on ADMM but faster than general Stochastic ADMM (which is $O(1/\sqrt{K})$). Our algorithm also owns wide flexibility, outperforms many state-of-the-art stochastic algorithms coming from ADMM, and has low memory cost in large-scale splitting optimization problems.
Tasks
Published	2017-11-14
URL	http://arxiv.org/abs/1711.04955v2
PDF	http://arxiv.org/pdf/1711.04955v2.pdf
PWC	https://paperswithcode.com/paper/scalable-peaceman-rachford-splitting-method
Repo
Framework

Unsupervised Object Discovery and Co-Localization by Deep Descriptor Transforming


Title	Unsupervised Object Discovery and Co-Localization by Deep Descriptor Transforming
Authors	Xiu-Shen Wei, Chen-Lin Zhang, Jianxin Wu, Chunhua Shen, Zhi-Hua Zhou
Abstract	Reusable model design becomes desirable with the rapid expansion of computer vision and machine learning applications. In this paper, we focus on the reusability of pre-trained deep convolutional models. Specifically, different from treating pre-trained models as feature extractors, we reveal more treasures beneath convolutional layers, i.e., the convolutional activations could act as a detector for the common object in the image co-localization problem. We propose a simple yet effective method, termed Deep Descriptor Transforming (DDT), for evaluating the correlations of descriptors and then obtaining the category-consistent regions, which can accurately locate the common object in a set of unlabeled images, i.e., unsupervised object discovery. Empirical studies validate the effectiveness of the proposed DDT method. On benchmark image co-localization datasets, DDT consistently outperforms existing state-of-the-art methods by a large margin. Moreover, DDT also demonstrates good generalization ability for unseen categories and robustness for dealing with noisy data. Beyond those, DDT can be also employed for harvesting web images into valid external data sources for improving performance of both image recognition and object detection.
Tasks	Object Detection
Published	2017-07-20
URL	http://arxiv.org/abs/1707.06397v1
PDF	http://arxiv.org/pdf/1707.06397v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-object-discovery-and-co
Repo
Framework

Fast and accurate classification of echocardiograms using deep learning


Title	Fast and accurate classification of echocardiograms using deep learning
Authors	Ali Madani, Ramy Arnaout, Mohammad Mofrad, Rima Arnaout
Abstract	Echocardiography is essential to modern cardiology. However, human interpretation limits high throughput analysis, limiting echocardiography from reaching its full clinical and research potential for precision medicine. Deep learning is a cutting-edge machine-learning technique that has been useful in analyzing medical images but has not yet been widely applied to echocardiography, partly due to the complexity of echocardiograms’ multi view, multi modality format. The essential first step toward comprehensive computer assisted echocardiographic interpretation is determining whether computers can learn to recognize standard views. To this end, we anonymized 834,267 transthoracic echocardiogram (TTE) images from 267 patients (20 to 96 years, 51 percent female, 26 percent obese) seen between 2000 and 2017 and labeled them according to standard views. Images covered a range of real world clinical variation. We built a multilayer convolutional neural network and used supervised learning to simultaneously classify 15 standard views. Eighty percent of data used was randomly chosen for training and 20 percent reserved for validation and testing on never seen echocardiograms. Using multiple images from each clip, the model classified among 12 video views with 97.8 percent overall test accuracy without overfitting. Even on single low resolution images, test accuracy among 15 views was 91.7 percent versus 70.2 to 83.5 percent for board-certified echocardiographers. Confusional matrices, occlusion experiments, and saliency mapping showed that the model finds recognizable similarities among related views and classifies using clinically relevant image features. In conclusion, deep neural networks can classify essential echocardiographic views simultaneously and with high accuracy. Our results provide a foundation for more complex deep learning assisted echocardiographic interpretation.
Tasks
Published	2017-06-27
URL	http://arxiv.org/abs/1706.08658v1
PDF	http://arxiv.org/pdf/1706.08658v1.pdf
PWC	https://paperswithcode.com/paper/fast-and-accurate-classification-of
Repo
Framework

Fast 2-D Complex Gabor Filter with Kernel Decomposition


Title	Fast 2-D Complex Gabor Filter with Kernel Decomposition
Authors	Suhyuk Um, Jaeyoon Kim, Dongbo Min
Abstract	2-D complex Gabor filtering has found numerous applications in the fields of computer vision and image processing. Especially, in some applications, it is often needed to compute 2-D complex Gabor filter bank consisting of the 2-D complex Gabor filtering outputs at multiple orientations and frequencies. Although several approaches for fast 2-D complex Gabor filtering have been proposed, they primarily focus on reducing the runtime of performing the 2-D complex Gabor filtering once at specific orientation and frequency. To obtain the 2-D complex Gabor filter bank output, existing methods are repeatedly applied with respect to multiple orientations and frequencies. In this paper, we propose a novel approach that efficiently computes the 2-D complex Gabor filter bank by reducing the computational redundancy that arises when performing the Gabor filtering at multiple orientations and frequencies. The proposed method first decomposes the Gabor basis kernels to allow a fast convolution with the Gaussian kernel in a separable manner. This enables reducing the runtime of the 2-D complex Gabor filter bank by reusing intermediate results of the 2-D complex Gabor filtering computed at a specific orientation. Furthermore, we extend this idea into 2-D localized sliding discrete Fourier transform (SDFT) using the Gaussian kernel in the DFT computation, which lends a spatial localization ability as in the 2-D complex Gabor filter. Experimental results demonstrate that our method runs faster than state-of-the-arts methods for fast 2-D complex Gabor filtering, while maintaining similar filtering quality.
Tasks
Published	2017-04-18
URL	http://arxiv.org/abs/1704.05231v1
PDF	http://arxiv.org/pdf/1704.05231v1.pdf
PWC	https://paperswithcode.com/paper/fast-2-d-complex-gabor-filter-with-kernel
Repo
Framework

Deep Within-Class Covariance Analysis for Robust Audio Representation Learning


Title	Deep Within-Class Covariance Analysis for Robust Audio Representation Learning
Authors	Hamid Eghbal-zadeh, Matthias Dorfer, Gerhard Widmer
Abstract	Convolutional Neural Networks (CNNs) can learn effective features, though have been shown to suffer from a performance drop when the distribution of the data changes from training to test data. In this paper we analyze the internal representations of CNNs and observe that the representations of unseen data in each class, spread more (with higher variance) in the embedding space of the CNN compared to representations of the training data. More importantly, this difference is more extreme if the unseen data comes from a shifted distribution. Based on this observation, we objectively evaluate the degree of representation’s variance in each class via eigenvalue decomposition on the within-class covariance of the internal representations of CNNs and observe the same behaviour. This can be problematic as larger variances might lead to mis-classification if the sample crosses the decision boundary of its class. We apply nearest neighbor classification on the representations and empirically show that the embeddings with the high variance actually have significantly worse KNN classification performances, although this could not be foreseen from their end-to-end classification results. To tackle this problem, we propose Deep Within-Class Covariance Analysis (DWCCA), a deep neural network layer that significantly reduces the within-class covariance of a DNN’s representation, improving performance on unseen test data from a shifted distribution. We empirically evaluate DWCCA on two datasets for Acoustic Scene Classification (DCASE2016 and DCASE2017). We demonstrate that not only does DWCCA significantly improve the network’s internal representation, it also increases the end-to-end classification accuracy, especially when the test set exhibits a distribution shift. By adding DWCCA to a VGG network, we achieve around 6 percentage points improvement in the case of a distribution mismatch.
Tasks	Acoustic Scene Classification, Representation Learning, Scene Classification
Published	2017-11-10
URL	http://arxiv.org/abs/1711.04022v2
PDF	http://arxiv.org/pdf/1711.04022v2.pdf
PWC	https://paperswithcode.com/paper/deep-within-class-covariance-analysis-for
Repo
Framework

Evaluation of Machine Learning Methods to Predict Coronary Artery Disease Using Metabolomic Data


Title	Evaluation of Machine Learning Methods to Predict Coronary Artery Disease Using Metabolomic Data
Authors	Henrietta Forssen, Riyaz S. Patel, Natalie Fitzpatrick, Aroon Hingorani, Adam Timmis, Harry Hemingway, Spiros C. Denaxas
Abstract	Metabolomic data can potentially enable accurate, non-invasive and low-cost prediction of coronary artery disease. Regression-based analytical approaches however might fail to fully account for interactions between metabolites, rely on a priori selected input features and thus might suffer from poorer accuracy. Supervised machine learning methods can potentially be used in order to fully exploit the dimensionality and richness of the data. In this paper, we systematically implement and evaluate a set of supervised learning methods (L1 regression, random forest classifier) and compare them to traditional regression-based approaches for disease prediction using metabolomic data.
Tasks	Disease Prediction
Published	2017-02-28
URL	http://arxiv.org/abs/1703.02116v1
PDF	http://arxiv.org/pdf/1703.02116v1.pdf
PWC	https://paperswithcode.com/paper/evaluation-of-machine-learning-methods-to
Repo
Framework