January 31, 2020

3294 words 16 mins read

Paper Group ANR 147

Unsupervised Video Depth Estimation Based on Ego-motion and Disparity Consensus. Study of Robust Distributed Diffusion RLS Algorithms with Side Information for Adaptive Networks. Semi-Supervised Natural Language Approach for Fine-Grained Classification of Medical Reports. A Strongly Consistent Sparse $k$-means Clustering with Direct $l_1$ Penalizat …

Unsupervised Video Depth Estimation Based on Ego-motion and Disparity Consensus


Title	Unsupervised Video Depth Estimation Based on Ego-motion and Disparity Consensus
Authors	Lingtao Zhou, Jiaojiao Fang, Guizhong Liu
Abstract	Unsupervised learning based depth estimation methods have received more and more attention as they do not need vast quantities of densely labeled data for training which are touch to acquire. In this paper, we propose a novel unsupervised monocular video depth estimation method in natural scenes by taking advantage of the state-of-the-art method of Zhou et al. which jointly estimates depth and camera motion. Our method advances beyond the baseline method by three aspects: 1) we add an additional signal as supervision to the baseline method by incorporating left-right binocular images reconstruction loss based on the estimated disparities, thus the left frame can be reconstructed by the temporal frames and right frames of stereo vision; 2) the network is trained by jointly using two kinds of view syntheses loss and left-right disparity consistency regularization to estimate depth and pose simultaneously; 3) we use the edge aware smooth L2 regularization to smooth the depth map while preserving the contour of the target. Extensive experiments on the KITTI autonomous driving dataset and Make3D dataset indicate the superiority of our algorithm in training efficiency. We can achieve competitive results with the baseline by only 3/5 times training data. The experimental results also show that our method even outperforms the classical supervised methods that using either ground truth depth or given pose for training.
Tasks	Autonomous Driving, Depth And Camera Motion, Depth Estimation, L2 Regularization
Published	2019-09-03
URL	https://arxiv.org/abs/1909.01028v1
PDF	https://arxiv.org/pdf/1909.01028v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-video-depth-estimation-based-on
Repo
Framework

Study of Robust Distributed Diffusion RLS Algorithms with Side Information for Adaptive Networks


Title	Study of Robust Distributed Diffusion RLS Algorithms with Side Information for Adaptive Networks
Authors	Y. Yu, H. Zhao, R. C. de Lamare, Y. Zakharov, L. Lu
Abstract	This work develops robust diffusion recursive least squares algorithms to mitigate the performance degradation often experienced in networks of agents in the presence of impulsive noise. The first algorithm minimizes an exponentially weighted least-squares cost function subject to a time-dependent constraint on the squared norm of the intermediate update at each node. A recursive strategy for computing the constraint is proposed using side information from the neighboring nodes to further improve the robustness. We also analyze the mean-square convergence behavior of the proposed algorithm. The second proposed algorithm is a modification of the first one based on the dichotomous coordinate descent iterations. It has a performance similar to that of the former, however its complexity is significantly lower especially when input regressors of agents have a shift structure and it is well suited to practical implementation. Simulations show the superiority of the proposed algorithms over previously reported techniques in various impulsive noise scenarios.
Tasks
Published	2019-02-04
URL	http://arxiv.org/abs/1902.01005v1
PDF	http://arxiv.org/pdf/1902.01005v1.pdf
PWC	https://paperswithcode.com/paper/study-of-robust-distributed-diffusion-rls
Repo
Framework

Semi-Supervised Natural Language Approach for Fine-Grained Classification of Medical Reports


Title	Semi-Supervised Natural Language Approach for Fine-Grained Classification of Medical Reports
Authors	Neil Deshmukh, Selin Gumustop, Romane Gauriau, Varun Buch, Bradley Wright, Christopher Bridge, Ram Naidu, Katherine Andriole, Bernardo Bizzo
Abstract	Although machine learning has become a powerful tool to augment doctors in clinical analysis, the immense amount of labeled data that is necessary to train supervised learning approaches burdens each development task as time and resource intensive. The vast majority of dense clinical information is stored in written reports, detailing pertinent patient information. The challenge with utilizing natural language data for standard model development is due to the complex nature of the modality. In this research, a model pipeline was developed to utilize an unsupervised approach to train an encoder-language model, a recurrent network, to generate document encodings; which then can be used as features passed into a decoder-classifier model that requires magnitudes less labeled data than previous approaches to differentiate between fine-grained disease classes accurately. The language model was trained on unlabeled radiology reports from the Massachusetts General Hospital Radiology Department (n=218,159) and terminated with a loss of 1.62. The classification models were trained on three labeled datasets of head CT studies of reported patients, presenting large vessel occlusion (n=1403), acute ischemic strokes (n=331), and intracranial hemorrhage (n=4350), to identify a variety of different findings directly from the radiology report data; resulting in AUCs of 0.98, 0.95, and 0.99, respectively, for the large vessel occlusion, acute ischemic stroke, and intracranial hemorrhage datasets. The output encodings are able to be used in conjunction with imaging data, to create models that can process a multitude of different modalities. The ability to automatically extract relevant features from textual data allows for faster model development and integration of textual modality, overall, allowing clinical reports to become a more viable input for more encompassing and accurate deep learning models.
Tasks	Language Modelling
Published	2019-10-29
URL	https://arxiv.org/abs/1910.13573v2
PDF	https://arxiv.org/pdf/1910.13573v2.pdf
PWC	https://paperswithcode.com/paper/semi-supervised-natural-language-approach-for
Repo
Framework

A Strongly Consistent Sparse $k$-means Clustering with Direct $l_1$ Penalization on Variable Weights


Title	A Strongly Consistent Sparse $k$-means Clustering with Direct $l_1$ Penalization on Variable Weights
Authors	Saptarshi Chakraborty, Swagatam Das
Abstract	We propose the Lasso Weighted $k$-means ($LW$-$k$-means) algorithm as a simple yet efficient sparse clustering procedure for high-dimensional data where the number of features ($p$) can be much larger compared to the number of observations ($n$). In the $LW$-$k$-means algorithm, we introduce a lasso-based penalty term, directly on the feature weights to incorporate feature selection in the framework of sparse clustering. $LW$-$k$-means does not make any distributional assumption of the given dataset and thus, induces a non-parametric method for feature selection. We also analytically investigate the convergence of the underlying optimization procedure in $LW$-$k$-means and establish the strong consistency of our algorithm. $LW$-$k$-means is tested on several real-life and synthetic datasets and through detailed experimental analysis, we find that the performance of the method is highly competitive against some state-of-the-art procedures for clustering and feature selection, not only in terms of clustering accuracy but also with respect to computational time.
Tasks	Feature Selection
Published	2019-03-24
URL	http://arxiv.org/abs/1903.10039v1
PDF	http://arxiv.org/pdf/1903.10039v1.pdf
PWC	https://paperswithcode.com/paper/a-strongly-consistent-sparse-k-means
Repo
Framework

Joint Learning of Graph Representation and Node Features in Graph Convolutional Neural Networks


Title	Joint Learning of Graph Representation and Node Features in Graph Convolutional Neural Networks
Authors	Jiaxiang Tang, Wei Hu, Xiang Gao, Zongming Guo
Abstract	Graph Convolutional Neural Networks (GCNNs) extend classical CNNs to graph data domain, such as brain networks, social networks and 3D point clouds. It is critical to identify an appropriate graph for the subsequent graph convolution. Existing methods manually construct or learn one fixed graph for all the layers of a GCNN. In order to adapt to the underlying structure of node features in different layers, we propose dynamic learning of graphs and node features jointly in GCNNs. In particular, we cast the graph optimization problem as distance metric learning to capture pairwise similarities of features in each layer. We deploy the Mahalanobis distance metric and further decompose the metric matrix into a low-dimensional matrix, which converts graph learning to the optimization of a low-dimensional matrix for efficient implementation. Extensive experiments on point clouds and citation network datasets demonstrate the superiority of the proposed method in terms of both accuracies and robustness.
Tasks	Metric Learning
Published	2019-09-11
URL	https://arxiv.org/abs/1909.04931v1
PDF	https://arxiv.org/pdf/1909.04931v1.pdf
PWC	https://paperswithcode.com/paper/joint-learning-of-graph-representation-and
Repo
Framework

Maximum Correntropy Criterion with Variable Center


Title	Maximum Correntropy Criterion with Variable Center
Authors	Badong Chen, Xin Wang, Yingsong Li, Jose C. Principe
Abstract	Correntropy is a local similarity measure defined in kernel space and the maximum correntropy criterion (MCC) has been successfully applied in many areas of signal processing and machine learning in recent years. The kernel function in correntropy is usually restricted to the Gaussian function with center located at zero. However, zero-mean Gaussian function may not be a good choice for many practical applications. In this study, we propose an extended version of correntropy, whose center can locate at any position. Accordingly, we propose a new optimization criterion called maximum correntropy criterion with variable center (MCC-VC). We also propose an efficient approach to optimize the kernel width and center location in MCC-VC. Simulation results of regression with linear in parameters (LIP) models confirm the desirable performance of the new method.
Tasks
Published	2019-04-13
URL	http://arxiv.org/abs/1904.06501v1
PDF	http://arxiv.org/pdf/1904.06501v1.pdf
PWC	https://paperswithcode.com/paper/maximum-correntropy-criterion-with-variable
Repo
Framework

Facebook AI’s WAT19 Myanmar-English Translation Task Submission


Title	Facebook AI’s WAT19 Myanmar-English Translation Task Submission
Authors	Peng-Jen Chen, Jiajun Shen, Matt Le, Vishrav Chaudhary, Ahmed El-Kishky, Guillaume Wenzek, Myle Ott, Marc’Aurelio Ranzato
Abstract	This paper describes Facebook AI’s submission to the WAT 2019 Myanmar-English translation task. Our baseline systems are BPE-based transformer models. We explore methods to leverage monolingual data to improve generalization, including self-training, back-translation and their combination. We further improve results by using noisy channel re-ranking and ensembling. We demonstrate that these techniques can significantly improve not only a system trained with additional monolingual data, but even the baseline system trained exclusively on the provided small parallel dataset. Our system ranks first in both directions according to human evaluation and BLEU, with a gain of over 8 BLEU points above the second best system.
Tasks
Published	2019-10-15
URL	https://arxiv.org/abs/1910.06848v1
PDF	https://arxiv.org/pdf/1910.06848v1.pdf
PWC	https://paperswithcode.com/paper/facebook-ais-wat19-myanmar-english
Repo
Framework

Fast Glioblastoma Detection in Fluid-attenuated inversion recovery (FLAIR) images by Topological Explainable Automatic Machine Learning


Title	Fast Glioblastoma Detection in Fluid-attenuated inversion recovery (FLAIR) images by Topological Explainable Automatic Machine Learning
Authors	Matteo Rucco
Abstract	Glioblastoma multiforme (GBM) is a fast-growing and highly invasive brain tumor, it tends to occur in adults between the ages of 45 and 70 and it accounts for 52 percent of all primary brain tumors. Usually, GBMs are detected by magnetic resonance images (MRI). Among MRI images, Fluid-attenuated inversion recovery (FLAIR) sequence produces high quality digital tumor representation. Fast detection and segmentation techniques are needed for overcoming subjective medical doctors (MDs) judgment. In this work, a new framework for radiomics analysis of GBM on FLAIR images is proposed. The framework can be used both for an initial detection of GBM and in case for its segmentation. The novelty of the methodology is the combination of new topological features computed by topological data analysis, textural features and of automatic interpretable machine learning algorithm. The framework was evaluated on a public available dataset and it reaches up to the 97% of accuracy on the detection task and up to 95% of accuracy on the segmentation task.
Tasks	Interpretable Machine Learning, Topological Data Analysis
Published	2019-12-17
URL	https://arxiv.org/abs/1912.08167v5
PDF	https://arxiv.org/pdf/1912.08167v5.pdf
PWC	https://paperswithcode.com/paper/fast-glioblastoma-detection-in-fluid
Repo
Framework


Title	Graph Attention Memory for Visual Navigation
Authors	Dong Li, Qichao Zhang, Dongbin Zhao, Yuzheng Zhuang, Bin Wang, Wulong Liu, Rasul Tutunov, Jun Wang
Abstract	Visual navigation in complex environments is inefficient with traditional reactive policy or general-purposed recurrent policy. To address the long-term memory issue, this paper proposes a graph attention memory (GAM) architecture consisting of memory construction module, graph attention module and control module. The memory construction module builds the topological graph based on supervised learning by taking the exploration prior. Then, guided attention features are extracted with the graph attention module. Finally, the deep reinforcement learning based control module makes decisions based on visual observations and guided attention features. Detailed convergence analysis of GAM is presented in this paper. We evaluate GAM-based navigation system in two complex 3D environments. Experimental results show that the GAM-based navigation system significantly improves learning efficiency and outperforms all baselines in average success rate.
Tasks	Visual Navigation
Published	2019-05-11
URL	https://arxiv.org/abs/1905.13315v2
PDF	https://arxiv.org/pdf/1905.13315v2.pdf
PWC	https://paperswithcode.com/paper/190513315
Repo
Framework

SensAI+Expanse Adaptation on Human Behaviour Towards Emotional Valence Prediction


Title	SensAI+Expanse Adaptation on Human Behaviour Towards Emotional Valence Prediction
Authors	Nuno A. C. Henriques, Helder Coelho, Leonel Garcia-Marques
Abstract	An agent, artificial or human, must be continuously adjusting its behaviour in order to thrive in a more or less demanding environment. An artificial agent with the ability to predict human emotional valence in a geospatial and temporal context requires proper adaptation to its mobile device environment with resource consumption strict restrictions (e.g., power from battery). The developed distributed system includes a mobile device embodied agent (SensAI) plus Cloud-expanded (Expanse) cognition and memory resources. The system is designed with several adaptive mechanisms in a best effort for the agent to cope with its interacting humans and to be resilient on collecting data for machine learning towards prediction. These mechanisms encompass homeostatic-like adjustments such as auto recovering from an unexpected failure in the mobile device, forgetting repeated data to save local memory, adjusting actions to a proper moment (e.g., notify only when human is interacting), and the Expanse complementary learning algorithms’ parameters with auto adjustments. Regarding emotional valence prediction performance, results from a comparison study between state-of-the-art algorithms revealed Extreme Gradient Boosting on average the best model for prediction with efficient energy use, and explainable using feature importance inspection. Therefore, this work contributes with a smartphone sensing-based system, distributed in the Cloud, robust to unexpected behaviours from humans and the environment, able to predict emotional valence states with very good performance.
Tasks	Feature Importance
Published	2019-12-20
URL	https://arxiv.org/abs/1912.10084v4
PDF	https://arxiv.org/pdf/1912.10084v4.pdf
PWC	https://paperswithcode.com/paper/sensaiexpanse-adaptation-on-human-behaviour
Repo
Framework

Single Sample Feature Importance: An Interpretable Algorithm for Low-Level Feature Analysis


Title	Single Sample Feature Importance: An Interpretable Algorithm for Low-Level Feature Analysis
Authors	Joseph Gatto, Ravi Lanka, Yumi Iwashita, Adrian Stoica
Abstract	Have you ever wondered how your feature space is impacting the prediction of a specific sample in your dataset? In this paper, we introduce Single Sample Feature Importance (SSFI), which is an interpretable feature importance algorithm that allows for the identification of the most important features that contribute to the prediction of a single sample. When a dataset can be learned by a Random Forest classifier or regressor, SSFI shows how the Random Forest’s prediction path can be utilized for low-level feature importance calculation. SSFI results in a relative ranking of features, highlighting those with the greatest impact on a data point’s prediction. We demonstrate these results both numerically and visually on four different datasets.
Tasks	Feature Importance
Published	2019-11-27
URL	https://arxiv.org/abs/1911.11901v1
PDF	https://arxiv.org/pdf/1911.11901v1.pdf
PWC	https://paperswithcode.com/paper/single-sample-feature-importance-an
Repo
Framework

Classification of Histopathological Biopsy Images Using Ensemble of Deep Learning Networks


Title	Classification of Histopathological Biopsy Images Using Ensemble of Deep Learning Networks
Authors	Sara Hosseinzadeh Kassani, Peyman Hosseinzadeh Kassani, Michal J. Wesolowski, Kevin A. Schneider, Ralph Deters
Abstract	Breast cancer is one of the leading causes of death across the world in women. Early diagnosis of this type of cancer is critical for treatment and patient care. Computer-aided detection (CAD) systems using convolutional neural networks (CNN) could assist in the classification of abnormalities. In this study, we proposed an ensemble deep learning-based approach for automatic binary classification of breast histology images. The proposed ensemble model adapts three pre-trained CNNs, namely VGG19, MobileNet, and DenseNet. The ensemble model is used for the feature representation and extraction steps. The extracted features are then fed into a multi-layer perceptron classifier to carry out the classification task. Various pre-processing and CNN tuning techniques such as stain-normalization, data augmentation, hyperparameter tuning, and fine-tuning are used to train the model. The proposed method is validated on four publicly available benchmark datasets, i.e., ICIAR, BreakHis, PatchCamelyon, and Bioimaging. The proposed multi-model ensemble method obtains better predictions than single classifiers and machine learning algorithms with accuracies of 98.13%, 95.00%, 94.64% and 83.10% for BreakHis, ICIAR, PatchCamelyon and Bioimaging datasets, respectively.
Tasks	Data Augmentation
Published	2019-09-26
URL	https://arxiv.org/abs/1909.11870v1
PDF	https://arxiv.org/pdf/1909.11870v1.pdf
PWC	https://paperswithcode.com/paper/classification-of-histopathological-biopsy
Repo
Framework

Evolution Attack On Neural Networks


Title	Evolution Attack On Neural Networks
Authors	YiGui Luo, RuiJia Yang, Wei Sha, WeiYi Ding, YouTeng Sun, YiSi Wang
Abstract	Many studies have been done to prove the vulnerability of neural networks to adversarial example. A trained and well-behaved model can be fooled by a visually imperceptible perturbation, i.e., an originally correctly classified image could be misclassified after a slight perturbation. In this paper, we propose a black-box strategy to attack such networks using an evolution algorithm. First, we formalize the generation of an adversarial example into the optimization problem of perturbations that represent the noise added to an original image at each pixel. To solve this optimization problem in a black-box way, we find that an evolution algorithm perfectly meets our requirement since it can work without any gradient information. Therefore, we test various evolution algorithms, including a simple genetic algorithm, a parameter-exploring policy gradient, an OpenAI evolution strategy, and a covariance matrix adaptive evolution strategy. Experimental results show that a covariance matrix adaptive evolution Strategy performs best in this optimization problem. Additionally, we also perform several experiments to explore the effect of different regularizations on improving the quality of an adversarial example.
Tasks
Published	2019-06-21
URL	https://arxiv.org/abs/1906.09072v1
PDF	https://arxiv.org/pdf/1906.09072v1.pdf
PWC	https://paperswithcode.com/paper/evolution-attack-on-neural-networks
Repo
Framework

Deep Learning for Large-Scale Real-World ACARS and ADS-B Radio Signal Classification


Title	Deep Learning for Large-Scale Real-World ACARS and ADS-B Radio Signal Classification
Authors	Shichuan Chen, Shilian Zheng, Lifeng Yang, Xiaoniu Yang
Abstract	Radio signal classification has a very wide range of applications in the field of wireless communications and electromagnetic spectrum management. In recent years, deep learning has been used to solve the problem of radio signal classification and has achieved good results. However, the radio signal data currently used is very limited in scale. In order to verify the performance of the deep learning-based radio signal classification on real-world radio signal data, in this paper we conduct experiments on large-scale real-world ACARS and ADS-B signal data with sample sizes of 900,000 and 13,000,000, respectively, and with categories of 3,143 and 5,157 respectively. We use the same Inception-Residual neural network model structure for ACARS signal classification and ADS-B signal classification to verify the ability of a single basic deep neural network model structure to process different types of radio signals, i.e., communication bursts in ACARS and pulse bursts in ADS-B. We build an experimental system for radio signal deep learning experiments. Experimental results show that the signal classification accuracy of ACARS and ADS-B is 98.1% and 96.3%, respectively. When the signal-to-noise ratio (with injected additive white Gaussian noise) is greater than 9 dB, the classification accuracy is greater than 92%. These experimental results validate the ability of deep learning to classify large-scale real-world radio signals. The results of the transfer learning experiment show that the model trained on large-scale ADS-B datasets is more conducive to the learning and training of new tasks than the model trained on small-scale datasets.
Tasks	Transfer Learning
Published	2019-04-20
URL	https://arxiv.org/abs/1904.09425v3
PDF	https://arxiv.org/pdf/1904.09425v3.pdf
PWC	https://paperswithcode.com/paper/deep-learning-for-large-scale-real-world
Repo
Framework

Energy-Inspired Models: Learning with Sampler-Induced Distributions


Title	Energy-Inspired Models: Learning with Sampler-Induced Distributions
Authors	Dieterich Lawson, George Tucker, Bo Dai, Rajesh Ranganath
Abstract	Energy-based models (EBMs) are powerful probabilistic models, but suffer from intractable sampling and density evaluation due to the partition function. As a result, inference in EBMs relies on approximate sampling algorithms, leading to a mismatch between the model and inference. Motivated by this, we consider the sampler-induced distribution as the model of interest and maximize the likelihood of this model. This yields a class of energy-inspired models (EIMs) that incorporate learned energy functions while still providing exact samples and tractable log-likelihood lower bounds. We describe and evaluate three instantiations of such models based on truncated rejection sampling, self-normalized importance sampling, and Hamiltonian importance sampling. These models outperform or perform comparably to the recently proposed Learned Accept/Reject Sampling algorithm and provide new insights on ranking Noise Contrastive Estimation and Contrastive Predictive Coding. Moreover, EIMs allow us to generalize a recent connection between multi-sample variational lower bounds and auxiliary variable variational inference. We show how recent variational bounds can be unified with EIMs as the variational family.
Tasks
Published	2019-10-31
URL	https://arxiv.org/abs/1910.14265v2
PDF	https://arxiv.org/pdf/1910.14265v2.pdf
PWC	https://paperswithcode.com/paper/energy-inspired-models-learning-with-sampler
Repo
Framework