Paper Group ANR 473
Classification of lung nodules in CT images based on Wasserstein distance in differential geometry. Graph Laplacian mixture model. Learning Concept Abstractness Using Weak Supervision. From Selective Deep Convolutional Features to Compact Binary Representations for Image Retrieval. Deep neural networks algorithms for stochastic control problems on …
Classification of lung nodules in CT images based on Wasserstein distance in differential geometry
Title | Classification of lung nodules in CT images based on Wasserstein distance in differential geometry |
Authors | Min Zhang, Qianli Ma, Chengfeng Wen, Hai Chen, Deruo Liu, Xianfeng Gu, Jie He, Xiaoyin Xu |
Abstract | Lung nodules are commonly detected in screening for patients with a risk for lung cancer. Though the status of large nodules can be easily diagnosed by fine needle biopsy or bronchoscopy, small nodules are often difficult to classify on computed tomography (CT). Recent works have shown that shape analysis of lung nodules can be used to differentiate benign lesions from malignant ones, though existing methods are limited in their sensitivity and specificity. In this work we introduced a new 3D shape analysis within the framework of differential geometry to calculate the Wasserstein distance between benign and malignant lung nodules to derive an accurate classification scheme. The Wasserstein distance between the nodules is calculated based on our new spherical optimal mass transport, this new algorithm works directly on sphere by using spherical metric, which is much more accurate and efficient than previous methods. In the process of deformation, the area-distortion factor gives a probability measure on the unit sphere, which forms the Wasserstein space. From known cases of benign and malignant lung nodules, we can calculate a unique optimal mass transport map between their correspondingly deformed Wasserstein spaces. This transportation cost defines the Wasserstein distance between them and can be used to classify new lung nodules into either the benign or malignant class. To the best of our knowledge, this is the first work that utilizes Wasserstein distance for lung nodule classification. The advantages of Wasserstein distance are it is invariant under rigid motions and scalings, thus it intrinsically measures shape distance even when the underlying shapes are of high complexity, making it well suited to classify lung nodules as they have different sizes, orientations, and appearances. |
Tasks | 3D Shape Analysis, Computed Tomography (CT), Lung Nodule Classification |
Published | 2018-06-30 |
URL | http://arxiv.org/abs/1807.00094v1 |
http://arxiv.org/pdf/1807.00094v1.pdf | |
PWC | https://paperswithcode.com/paper/classification-of-lung-nodules-in-ct-images |
Repo | |
Framework | |
Graph Laplacian mixture model
Title | Graph Laplacian mixture model |
Authors | Hermina Petric Maretic, Pascal Frossard |
Abstract | Graph learning methods have recently been receiving increasing interest as means to infer structure in datasets. Most of the recent approaches focus on different relationships between a graph and data sample distributions, mostly in settings where all available data relate to the same graph. This is, however, not always the case, as data is often available in mixed form, yielding the need for methods that are able to cope with mixture data and learn multiple graphs. We propose a novel generative model that represents a collection of distinct data which naturally live on different graphs. We assume the mapping of data to graphs is not known and investigate the problem of jointly clustering a set of data and learning a graph for each of the clusters. Experiments demonstrate promising performance in data clustering and multiple graph inference, and show desirable properties in terms of interpretability and coping with high dimensionality on weather and traffic data, as well as digit classification. |
Tasks | |
Published | 2018-10-23 |
URL | https://arxiv.org/abs/1810.10053v2 |
https://arxiv.org/pdf/1810.10053v2.pdf | |
PWC | https://paperswithcode.com/paper/graph-laplacian-mixture-model |
Repo | |
Framework | |
Learning Concept Abstractness Using Weak Supervision
Title | Learning Concept Abstractness Using Weak Supervision |
Authors | Ella Rabinovich, Benjamin Sznajder, Artem Spector, Ilya Shnayderman, Ranit Aharonov, David Konopnicki, Noam Slonim |
Abstract | We introduce a weakly supervised approach for inferring the property of abstractness of words and expressions in the complete absence of labeled data. Exploiting only minimal linguistic clues and the contextual usage of a concept as manifested in textual data, we train sufficiently powerful classifiers, obtaining high correlation with human labels. The results imply the applicability of this approach to additional properties of concepts, additional languages, and resource-scarce scenarios. |
Tasks | |
Published | 2018-09-05 |
URL | http://arxiv.org/abs/1809.01285v1 |
http://arxiv.org/pdf/1809.01285v1.pdf | |
PWC | https://paperswithcode.com/paper/learning-concept-abstractness-using-weak |
Repo | |
Framework | |
From Selective Deep Convolutional Features to Compact Binary Representations for Image Retrieval
Title | From Selective Deep Convolutional Features to Compact Binary Representations for Image Retrieval |
Authors | Thanh-Toan Do, Tuan Hoang, Dang-Khoa Le Tan, Huu Le, Tam V. Nguyen, Ngai-Man Cheung |
Abstract | In the large-scale image retrieval task, the two most important requirements are the discriminability of image representations and the efficiency in computation and storage of representations. Regarding the former requirement, Convolutional Neural Network (CNN) is proven to be a very powerful tool to extract highly discriminative local descriptors for effective image search. Additionally, in order to further improve the discriminative power of the descriptors, recent works adopt fine-tuned strategies. In this paper, taking a different approach, we propose a novel, computationally efficient, and competitive framework. Specifically, we firstly propose various strategies to compute masks, namely SIFT-mask, SUM-mask, and MAX-mask, to select a representative subset of local convolutional features and eliminate redundant features. Our in-depth analyses demonstrate that proposed masking schemes are effective to address the burstiness drawback and improve retrieval accuracy. Secondly, we propose to employ recent embedding and aggregating methods which can significantly boost the feature discriminability. Regarding the computation and storage efficiency, we include a hashing module to produce very compact binary image representations. Extensive experiments on six image retrieval benchmarks demonstrate that our proposed framework achieves the state-of-the-art retrieval performances. |
Tasks | Image Retrieval |
Published | 2018-02-07 |
URL | http://arxiv.org/abs/1802.02899v3 |
http://arxiv.org/pdf/1802.02899v3.pdf | |
PWC | https://paperswithcode.com/paper/from-selective-deep-convolutional-features-to |
Repo | |
Framework | |
Deep neural networks algorithms for stochastic control problems on finite horizon, part I: convergence analysis
Title | Deep neural networks algorithms for stochastic control problems on finite horizon, part I: convergence analysis |
Authors | Côme Huré, Huyên Pham, Achref Bachouch, Nicolas Langrené |
Abstract | This paper develops algorithms for high-dimensional stochastic control problems based on deep learning and dynamic programming (DP). Differently from the classical approximate DP approach, we first approximate the optimal policy by means of neural networks in the spirit of deep reinforcement learning, and then the value function by Monte Carlo regression. This is achieved in the DP recursion by performance or hybrid iteration, and regress now or later/quantization methods from numerical probabilities. We provide a theoretical justification of these algorithms. Consistency and rate of convergence for the control and value function estimates are analyzed and expressed in terms of the universal approximation error of the neural networks. Numerical results on various applications are presented in a companion paper [2] and illustrate the performance of our algorithms. |
Tasks | Quantization |
Published | 2018-12-11 |
URL | http://arxiv.org/abs/1812.04300v1 |
http://arxiv.org/pdf/1812.04300v1.pdf | |
PWC | https://paperswithcode.com/paper/deep-neural-networks-algorithms-for-1 |
Repo | |
Framework | |
Robot Vision: Calibration of Wide-Angle Lens Cameras Using Collinearity Condition and K-Nearest Neighbour Regression
Title | Robot Vision: Calibration of Wide-Angle Lens Cameras Using Collinearity Condition and K-Nearest Neighbour Regression |
Authors | Jacky C. K. Chow, Ivan Detchev, Kathleen Ang, Kristian Morin, Karthik Mahadevan, Nicholas Louie |
Abstract | Visual perception is regularly used by humans and robots for navigation. By either implicitly or explicitly mapping the environment, ego-motion can be determined and a path of actions can be planned. The process of mapping and navigation are delicately intertwined; therefore, improving one can often lead to an improvement of the other. Both processes are sensitive to the interior orientation parameters of the camera system and mathematically modelling these systematic errors can often improve the precision and accuracy of the overall solution. This paper presents an automatic camera calibration method suitable for any lens, without having prior knowledge about the sensor. Statistical inference is performed to map the environment and localize the camera simultaneously. K-nearest neighbour regression is used to model the geometric distortions of the images. A normal-angle lens Nikon camera and wide-angle lens GoPro camera were calibrated using the proposed method, as well as the conventional bundle adjustment with self-calibration method (for comparison). Results showed that the mapping error was reduced from an average of 14.9 mm to 1.2 mm (i.e. a 92% improvement) and 66.6 mm to 1.5 mm (i.e. a 98% improvement) using the proposed method for the Nikon and GoPro cameras, respectively. In contrast, the conventional approach achieved an average 3D error of 0.9 mm (i.e. 94% improvement) and 3.3 mm (i.e. 95% improvement) for the Nikon and GoPro cameras, respectively. Thus, the proposed method performs well irrespective of the lens/sensor used: it yields results that are comparable to the conventional approach for normal-angle lens cameras, and it has the additional benefit of improving calibration results for wide-angle lens cameras. |
Tasks | Calibration |
Published | 2018-09-29 |
URL | http://arxiv.org/abs/1810.00128v1 |
http://arxiv.org/pdf/1810.00128v1.pdf | |
PWC | https://paperswithcode.com/paper/robot-vision-calibration-of-wide-angle-lens |
Repo | |
Framework | |
Small-scale Pedestrian Detection Based on Somatic Topology Localization and Temporal Feature Aggregation
Title | Small-scale Pedestrian Detection Based on Somatic Topology Localization and Temporal Feature Aggregation |
Authors | Tao Song, Leiyu Sun, Di Xie, Haiming Sun, Shiliang Pu |
Abstract | A critical issue in pedestrian detection is to detect small-scale objects that will introduce feeble contrast and motion blur in images and videos, which in our opinion should partially resort to deep-rooted annotation bias. Motivated by this, we propose a novel method integrated with somatic topological line localization (TLL) and temporal feature aggregation for detecting multi-scale pedestrians, which works particularly well with small-scale pedestrians that are relatively far from the camera. Moreover, a post-processing scheme based on Markov Random Field (MRF) is introduced to eliminate ambiguities in occlusion cases. Applying with these methodologies comprehensively, we achieve best detection performance on Caltech benchmark and improve performance of small-scale objects significantly (miss rate decreases from 74.53% to 60.79%). Beyond this, we also achieve competitive performance on CityPersons dataset and show the existence of annotation bias in KITTI dataset. |
Tasks | Pedestrian Detection |
Published | 2018-07-04 |
URL | http://arxiv.org/abs/1807.01438v1 |
http://arxiv.org/pdf/1807.01438v1.pdf | |
PWC | https://paperswithcode.com/paper/small-scale-pedestrian-detection-based-on |
Repo | |
Framework | |
Theoretical Analysis of Adversarial Learning: A Minimax Approach
Title | Theoretical Analysis of Adversarial Learning: A Minimax Approach |
Authors | Zhuozhuo Tu, Jingwei Zhang, Dacheng Tao |
Abstract | Here we propose a general theoretical method for analyzing the risk bound in the presence of adversaries. Specifically, we try to fit the adversarial learning problem into the minimax framework. We first show that the original adversarial learning problem can be reduced to a minimax statistical learning problem by introducing a transport map between distributions. Then, we prove a new risk bound for this minimax problem in terms of covering numbers under a weak version of Lipschitz condition. Our method can be applied to multi-class classification problems and commonly used loss functions such as the hinge and ramp losses. As some illustrative examples, we derive the adversarial risk bounds for SVMs, deep neural networks, and PCA, and our bounds have two data-dependent terms, which can be optimized for achieving adversarial robustness. |
Tasks | |
Published | 2018-11-13 |
URL | http://arxiv.org/abs/1811.05232v2 |
http://arxiv.org/pdf/1811.05232v2.pdf | |
PWC | https://paperswithcode.com/paper/theoretical-analysis-of-adversarial-learning |
Repo | |
Framework | |
Dynamic Sentence Sampling for Efficient Training of Neural Machine Translation
Title | Dynamic Sentence Sampling for Efficient Training of Neural Machine Translation |
Authors | Rui Wang, Masao Utiyama, Eiichiro Sumita |
Abstract | Traditional Neural machine translation (NMT) involves a fixed training procedure where each sentence is sampled once during each epoch. In reality, some sentences are well-learned during the initial few epochs; however, using this approach, the well-learned sentences would continue to be trained along with those sentences that were not well learned for 10-30 epochs, which results in a wastage of time. Here, we propose an efficient method to dynamically sample the sentences in order to accelerate the NMT training. In this approach, a weight is assigned to each sentence based on the measured difference between the training costs of two iterations. Further, in each epoch, a certain percentage of sentences are dynamically sampled according to their weights. Empirical results based on the NIST Chinese-to-English and the WMT English-to-German tasks depict that the proposed method can significantly accelerate the NMT training and improve the NMT performance. |
Tasks | Machine Translation |
Published | 2018-05-01 |
URL | https://arxiv.org/abs/1805.00178v3 |
https://arxiv.org/pdf/1805.00178v3.pdf | |
PWC | https://paperswithcode.com/paper/dynamic-sentence-sampling-for-efficient |
Repo | |
Framework | |
Driver Behavior Recognition via Interwoven Deep Convolutional Neural Nets with Multi-stream Inputs
Title | Driver Behavior Recognition via Interwoven Deep Convolutional Neural Nets with Multi-stream Inputs |
Authors | Chaoyun Zhang, Rui Li, Woojin Kim, Daesub Yoon, Paul Patras |
Abstract | Recognizing driver behaviors is becoming vital for in-vehicle systems that seek to reduce the incidence of car accidents rooted in cognitive distraction. In this paper, we harness the exceptional feature extraction abilities of deep learning and propose a dedicated Interwoven Deep Convolutional Neural Network (InterCNN) architecture to tackle the accurate classification of driver behaviors in real-time. The proposed solution exploits information from multi-stream inputs, i.e., in-vehicle cameras with different fields of view and optical flows computed based on recorded images, and merges through multiple fusion layers abstract features that it extracts. This builds a tight ensembling system, which significantly improves the robustness of the model. We further introduce a temporal voting scheme based on historical inference instances, in order to enhance accuracy. Experiments conducted with a real world dataset that we collect in a mock-up car environment demonstrate that the proposed InterCNN with MobileNet convolutional blocks can classify 9 different behaviors with 73.97% accuracy, and 5 aggregated behaviors with 81.66% accuracy. Our architecture is highly computationally efficient, as it performs inferences within 15ms, which satisfies the real-time constraints of intelligent cars. In addition, our InterCNN is robust to lossy input, as the classification remains accurate when two input streams are occluded. |
Tasks | |
Published | 2018-11-22 |
URL | http://arxiv.org/abs/1811.09128v1 |
http://arxiv.org/pdf/1811.09128v1.pdf | |
PWC | https://paperswithcode.com/paper/driver-behavior-recognition-via-interwoven |
Repo | |
Framework | |
Predicting Smoking Events with a Time-Varying Semi-Parametric Hawkes Process Model
Title | Predicting Smoking Events with a Time-Varying Semi-Parametric Hawkes Process Model |
Authors | Matthew Engelhard, Hongteng Xu, Lawrence Carin, Jason A Oliver, Matthew Hallyburton, F Joseph McClernon |
Abstract | Health risks from cigarette smoking – the leading cause of preventable death in the United States – can be substantially reduced by quitting. Although most smokers are motivated to quit, the majority of quit attempts fail. A number of studies have explored the role of self-reported symptoms, physiologic measurements, and environmental context on smoking risk, but less work has focused on the temporal dynamics of smoking events, including daily patterns and related nicotine effects. In this work, we examine these dynamics and improve risk prediction by modeling smoking as a self-triggering process, in which previous smoking events modify current risk. Specifically, we fit smoking events self-reported by 42 smokers to a time-varying semi-parametric Hawkes process (TV-SPHP) developed for this purpose. Results show that the TV-SPHP achieves superior prediction performance compared to related and existing models, with the incorporation of time-varying predictors having greatest benefit over longer prediction windows. Moreover, the impact function illustrates previously unknown temporal dynamics of smoking, with possible connections to nicotine metabolism to be explored in future work through a randomized study design. By more effectively predicting smoking events and exploring a self-triggering component of smoking risk, this work supports development of novel or improved cessation interventions that aim to reduce death from smoking. |
Tasks | |
Published | 2018-09-05 |
URL | http://arxiv.org/abs/1809.01740v1 |
http://arxiv.org/pdf/1809.01740v1.pdf | |
PWC | https://paperswithcode.com/paper/predicting-smoking-events-with-a-time-varying |
Repo | |
Framework | |
Impact of Ground Truth Annotation Quality on Performance of Semantic Image Segmentation of Traffic Conditions
Title | Impact of Ground Truth Annotation Quality on Performance of Semantic Image Segmentation of Traffic Conditions |
Authors | Vlad Taran, Yuri Gordienko, Alexandr Rokovyi, Oleg Alienin, Sergii Stirenko |
Abstract | Preparation of high-quality datasets for the urban scene understanding is a labor-intensive task, especially, for datasets designed for the autonomous driving applications. The application of the coarse ground truth (GT) annotations of these datasets without detriment to the accuracy of semantic image segmentation (by the mean intersection over union - mIoU) could simplify and speedup the dataset preparation and model fine tuning before its practical application. Here the results of the comparative analysis for semantic segmentation accuracy obtained by PSPNet deep learning architecture are presented for fine and coarse annotated images from Cityscapes dataset. Two scenarios were investigated: scenario 1 - the fine GT images for training and prediction, and scenario 2 - the fine GT images for training and the coarse GT images for prediction. The obtained results demonstrated that for the most important classes the mean accuracy values of semantic image segmentation for coarse GT annotations are higher than for the fine GT ones, and the standard deviation values are vice versa. It means that for some applications some unimportant classes can be excluded and the model can be tuned further for some classes and specific regions on the coarse GT dataset without loss of the accuracy even. Moreover, this opens the perspectives to use deep neural networks for the preparation of such coarse GT datasets. |
Tasks | Autonomous Driving, Scene Understanding, Semantic Segmentation |
Published | 2018-12-30 |
URL | http://arxiv.org/abs/1901.00001v1 |
http://arxiv.org/pdf/1901.00001v1.pdf | |
PWC | https://paperswithcode.com/paper/impact-of-ground-truth-annotation-quality-on |
Repo | |
Framework | |
On Distributed Multi-player Multiarmed Bandit Problems in Abruptly Changing Environment
Title | On Distributed Multi-player Multiarmed Bandit Problems in Abruptly Changing Environment |
Authors | Lai Wei, Vaibhav Srivastava |
Abstract | We study the multi-player stochastic multiarmed bandit (MAB) problem in an abruptly changing environment. We consider a collision model in which a player receives reward at an arm if it is the only player to select the arm. We design two novel algorithms, namely, Round-Robin Sliding-Window Upper Confidence Bound# (RR-SW-UCB#), and the Sliding-Window Distributed Learning with Prioritization (SW-DLP). We rigorously analyze these algorithms and show that the expected cumulative group regret for these algorithms is upper bounded by sublinear functions of time, i.e., the time average of the regret asymptotically converges to zero. We complement our analytic results with numerical illustrations. |
Tasks | |
Published | 2018-12-12 |
URL | http://arxiv.org/abs/1812.05165v1 |
http://arxiv.org/pdf/1812.05165v1.pdf | |
PWC | https://paperswithcode.com/paper/on-distributed-multi-player-multiarmed-bandit |
Repo | |
Framework | |
Formal Synthesis of Analytic Controllers for Sampled-Data Systems via Genetic Programming
Title | Formal Synthesis of Analytic Controllers for Sampled-Data Systems via Genetic Programming |
Authors | Cees F. Verdier, Manuel Mazo Jr |
Abstract | This paper presents an automatic formal controller synthesis method for nonlinear sampled-data systems with safety and reachability specifications. Fundamentally, the presented method is not restricted to polynomial systems and controllers. We consider periodically switched controllers based on a Control Lyapunov Barrier-like functions. The proposed method utilizes genetic programming to synthesize these functions as well as the controller modes. Correctness of the controller are subsequently verified by means of a Satisfiability Modulo Theories solver. Effectiveness of the proposed methodology is demonstrated on multiple systems. |
Tasks | |
Published | 2018-12-06 |
URL | http://arxiv.org/abs/1812.02711v1 |
http://arxiv.org/pdf/1812.02711v1.pdf | |
PWC | https://paperswithcode.com/paper/formal-synthesis-of-analytic-controllers-for |
Repo | |
Framework | |
Tensor Methods for Nonlinear Matrix Completion
Title | Tensor Methods for Nonlinear Matrix Completion |
Authors | Greg Ongie, Daniel Pimentel-Alarcón, Laura Balzano, Rebecca Willett, Robert D. Nowak |
Abstract | In the low-rank matrix completion (LRMC) problem, the low-rank assumption means that the columns (or rows) of the matrix to be completed are points on a low-dimensional linear algebraic variety. This paper extends this thinking to cases where the columns are points on a low-dimensional nonlinear algebraic variety, a problem we call Low Algebraic Dimension Matrix Completion (LADMC). Matrices whose columns belong to a union of subspaces are an important special case. We propose a LADMC algorithm that leverages existing LRMC methods on a tensorized representation of the data. For example, a second-order tensorized representation is formed by taking the Kronecker product of each column with itself, and we consider higher order tensorizations as well. This approach will succeed in many cases where traditional LRMC is guaranteed to fail because the data are low-rank in the tensorized representation but not in the original representation. We provide a formal mathematical justification for the success of our method. In particular, we give bounds of the rank of these data in the tensorized representation, and we prove sampling requirements to guarantee uniqueness of the solution. We also provide experimental results showing that the new approach outperforms existing state-of-the-art methods for matrix completion under a union of subspaces model. |
Tasks | Low-Rank Matrix Completion, Matrix Completion |
Published | 2018-04-26 |
URL | https://arxiv.org/abs/1804.10266v2 |
https://arxiv.org/pdf/1804.10266v2.pdf | |
PWC | https://paperswithcode.com/paper/tensor-methods-for-nonlinear-matrix |
Repo | |
Framework | |