Paper Group ANR 527
Automatically identifying, counting, and describing wild animals in camera-trap images with deep learning. Calculating Semantic Similarity between Academic Articles using Topic Event and Ontology. Finding Bottlenecks: Predicting Student Attrition with Unsupervised Classifier. An automatic deep learning approach for coronary artery calcium segmentat …
Automatically identifying, counting, and describing wild animals in camera-trap images with deep learning
| Title | Automatically identifying, counting, and describing wild animals in camera-trap images with deep learning |
| Authors | Mohammed Sadegh Norouzzadeh, Anh Nguyen, Margaret Kosmala, Ali Swanson, Meredith Palmer, Craig Packer, Jeff Clune |
| Abstract | Having accurate, detailed, and up-to-date information about the location and behavior of animals in the wild would revolutionize our ability to study and conserve ecosystems. We investigate the ability to automatically, accurately, and inexpensively collect such data, which could transform many fields of biology, ecology, and zoology into “big data” sciences. Motion sensor “camera traps” enable collecting wildlife pictures inexpensively, unobtrusively, and frequently. However, extracting information from these pictures remains an expensive, time-consuming, manual task. We demonstrate that such information can be automatically extracted by deep learning, a cutting-edge type of artificial intelligence. We train deep convolutional neural networks to identify, count, and describe the behaviors of 48 species in the 3.2-million-image Snapshot Serengeti dataset. Our deep neural networks automatically identify animals with over 93.8% accuracy, and we expect that number to improve rapidly in years to come. More importantly, if our system classifies only images it is confident about, our system can automate animal identification for 99.3% of the data while still performing at the same 96.6% accuracy as that of crowdsourced teams of human volunteers, saving more than 8.4 years (at 40 hours per week) of human labeling effort (i.e. over 17,000 hours) on this 3.2-million-image dataset. Those efficiency gains immediately highlight the importance of using deep neural networks to automate data extraction from camera-trap images. Our results suggest that this technology could enable the inexpensive, unobtrusive, high-volume, and even real-time collection of a wealth of information about vast numbers of animals in the wild. |
| Tasks | |
| Published | 2017-03-16 |
| URL | http://arxiv.org/abs/1703.05830v5 |
| http://arxiv.org/pdf/1703.05830v5.pdf | |
| PWC | https://paperswithcode.com/paper/automatically-identifying-counting-and |
| Repo | |
| Framework | |
Calculating Semantic Similarity between Academic Articles using Topic Event and Ontology
| Title | Calculating Semantic Similarity between Academic Articles using Topic Event and Ontology |
| Authors | Ming Liu, Bo Lang, Zepeng Gu |
| Abstract | Determining semantic similarity between academic documents is crucial to many tasks such as plagiarism detection, automatic technical survey and semantic search. Current studies mostly focus on semantic similarity between concepts, sentences and short text fragments. However, document-level semantic matching is still based on statistical information in surface level, neglecting article structures and global semantic meanings, which may cause the deviation in document understanding. In this paper, we focus on the document-level semantic similarity issue for academic literatures with a novel method. We represent academic articles with topic events that utilize multiple information profiles, such as research purposes, methodologies and domains to integrally describe the research work, and calculate the similarity between topic events based on the domain ontology to acquire the semantic similarity between articles. Experiments show that our approach achieves significant performance compared to state-of-the-art methods. |
| Tasks | Semantic Similarity, Semantic Textual Similarity |
| Published | 2017-11-30 |
| URL | http://arxiv.org/abs/1711.11508v1 |
| http://arxiv.org/pdf/1711.11508v1.pdf | |
| PWC | https://paperswithcode.com/paper/calculating-semantic-similarity-between |
| Repo | |
| Framework | |
Finding Bottlenecks: Predicting Student Attrition with Unsupervised Classifier
| Title | Finding Bottlenecks: Predicting Student Attrition with Unsupervised Classifier |
| Authors | Seyed Sajjadi, Bruce Shapiro, Christopher McKinlay, Allen Sarkisyan, Carol Shubin, Efunwande Osoba |
| Abstract | With pressure to increase graduation rates and reduce time to degree in higher education, it is important to identify at-risk students early. Automated early warning systems are therefore highly desirable. In this paper, we use unsupervised clustering techniques to predict the graduation status of declared majors in five departments at California State University Northridge (CSUN), based on a minimal number of lower division courses in each major. In addition, we use the detected clusters to identify hidden bottleneck courses. |
| Tasks | |
| Published | 2017-05-07 |
| URL | http://arxiv.org/abs/1705.02687v1 |
| http://arxiv.org/pdf/1705.02687v1.pdf | |
| PWC | https://paperswithcode.com/paper/finding-bottlenecks-predicting-student |
| Repo | |
| Framework | |
An automatic deep learning approach for coronary artery calcium segmentation
| Title | An automatic deep learning approach for coronary artery calcium segmentation |
| Authors | G. Santini, D. Della Latta, N. Martini, G. Valvano, A. Gori, A. Ripoli, C. L. Susini, L. Landini, D. Chiappino |
| Abstract | Coronary artery calcium (CAC) is a significant marker of atherosclerosis and cardiovascular events. In this work we present a system for the automatic quantification of calcium score in ECG-triggered non-contrast enhanced cardiac computed tomography (CT) images. The proposed system uses a supervised deep learning algorithm, i.e. convolutional neural network (CNN) for the segmentation and classification of candidate lesions as coronary or not, previously extracted in the region of the heart using a cardiac atlas. We trained our network with 45 CT volumes; 18 volumes were used to validate the model and 56 to test it. Individual lesions were detected with a sensitivity of 91.24%, a specificity of 95.37% and a positive predicted value (PPV) of 90.5%; comparing calcium score obtained by the system and calcium score manually evaluated by an expert operator, a Pearson coefficient of 0.983 was obtained. A high agreement (Cohen’s k = 0.879) between manual and automatic risk prediction was also observed. These results demonstrated that convolutional neural networks can be effectively applied for the automatic segmentation and classification of coronary calcifications. |
| Tasks | Computed Tomography (CT) |
| Published | 2017-10-09 |
| URL | http://arxiv.org/abs/1710.03023v1 |
| http://arxiv.org/pdf/1710.03023v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-automatic-deep-learning-approach-for |
| Repo | |
| Framework | |
Large-Scale Stochastic Learning using GPUs
| Title | Large-Scale Stochastic Learning using GPUs |
| Authors | Thomas Parnell, Celestine Dünner, Kubilay Atasu, Manolis Sifalakis, Haris Pozidis |
| Abstract | In this work we propose an accelerated stochastic learning system for very large-scale applications. Acceleration is achieved by mapping the training algorithm onto massively parallel processors: we demonstrate a parallel, asynchronous GPU implementation of the widely used stochastic coordinate descent/ascent algorithm that can provide up to 35x speed-up over a sequential CPU implementation. In order to train on very large datasets that do not fit inside the memory of a single GPU, we then consider techniques for distributed stochastic learning. We propose a novel method for optimally aggregating model updates from worker nodes when the training data is distributed either by example or by feature. Using this technique, we demonstrate that one can scale out stochastic learning across up to 8 worker nodes without any significant loss of training time. Finally, we combine GPU acceleration with the optimized distributed method to train on a dataset consisting of 200 million training examples and 75 million features. We show by scaling out across 4 GPUs, one can attain a high degree of training accuracy in around 4 seconds: a 20x speed-up in training time compared to a multi-threaded, distributed implementation across 4 CPUs. |
| Tasks | |
| Published | 2017-02-22 |
| URL | http://arxiv.org/abs/1702.07005v1 |
| http://arxiv.org/pdf/1702.07005v1.pdf | |
| PWC | https://paperswithcode.com/paper/large-scale-stochastic-learning-using-gpus |
| Repo | |
| Framework | |
Beyond Shared Hierarchies: Deep Multitask Learning through Soft Layer Ordering
| Title | Beyond Shared Hierarchies: Deep Multitask Learning through Soft Layer Ordering |
| Authors | Elliot Meyerson, Risto Miikkulainen |
| Abstract | Existing deep multitask learning (MTL) approaches align layers shared between tasks in a parallel ordering. Such an organization significantly constricts the types of shared structure that can be learned. The necessity of parallel ordering for deep MTL is first tested by comparing it with permuted ordering of shared layers. The results indicate that a flexible ordering can enable more effective sharing, thus motivating the development of a soft ordering approach, which learns how shared layers are applied in different ways for different tasks. Deep MTL with soft ordering outperforms parallel ordering methods across a series of domains. These results suggest that the power of deep MTL comes from learning highly general building blocks that can be assembled to meet the demands of each task. |
| Tasks | |
| Published | 2017-10-31 |
| URL | http://arxiv.org/abs/1711.00108v2 |
| http://arxiv.org/pdf/1711.00108v2.pdf | |
| PWC | https://paperswithcode.com/paper/beyond-shared-hierarchies-deep-multitask |
| Repo | |
| Framework | |
SVDNet for Pedestrian Retrieval
| Title | SVDNet for Pedestrian Retrieval |
| Authors | Yifan Sun, Liang Zheng, Weijian Deng, Shengjin Wang |
| Abstract | This paper proposes the SVDNet for retrieval problems, with focus on the application of person re-identification (re-ID). We view each weight vector within a fully connected (FC) layer in a convolutional neuron network (CNN) as a projection basis. It is observed that the weight vectors are usually highly correlated. This problem leads to correlations among entries of the FC descriptor, and compromises the retrieval performance based on the Euclidean distance. To address the problem, this paper proposes to optimize the deep representation learning process with Singular Vector Decomposition (SVD). Specifically, with the restraint and relaxation iteration (RRI) training scheme, we are able to iteratively integrate the orthogonality constraint in CNN training, yielding the so-called SVDNet. We conduct experiments on the Market-1501, CUHK03, and Duke datasets, and show that RRI effectively reduces the correlation among the projection vectors, produces more discriminative FC descriptors, and significantly improves the re-ID accuracy. On the Market-1501 dataset, for instance, rank-1 accuracy is improved from 55.3% to 80.5% for CaffeNet, and from 73.8% to 82.3% for ResNet-50. |
| Tasks | Person Re-Identification, Representation Learning |
| Published | 2017-03-16 |
| URL | http://arxiv.org/abs/1703.05693v4 |
| http://arxiv.org/pdf/1703.05693v4.pdf | |
| PWC | https://paperswithcode.com/paper/svdnet-for-pedestrian-retrieval |
| Repo | |
| Framework | |
Toward `verifying’ a Water Treatment System
| Title | Toward `verifying’ a Water Treatment System | |
| Authors | Jingyi Wang, Jun Sun, Yifan Jia, Shengchao Qin, Zhiwu Xu |
| Abstract | Modeling and verifying real-world cyber-physical systems is challenging, which is especially so for complex systems where manually modeling is infeasible. In this work, we report our experience on combining model learning and abstraction refinement to analyze a challenging system, i.e., a real-world Secure Water Treatment system (SWaT). Given a set of safety requirements, the objective is to either show that the system is safe with a high probability (so that a system shutdown is rarely triggered due to safety violation) or not. As the system is too complicated to be manually modeled, we apply latest automatic model learning techniques to construct a set of Markov chains through abstraction and refinement, based on two long system execution logs (one for training and the other for testing). For each probabilistic safety property, we either report it does not hold with a certain level of probabilistic confidence, or report that it holds by showing the evidence in the form of an abstract Markov chain. The Markov chains can subsequently be implemented as runtime monitors in SWaT. |
| Tasks | |
| Published | 2017-12-12 |
| URL | http://arxiv.org/abs/1712.04155v2 |
| http://arxiv.org/pdf/1712.04155v2.pdf | |
| PWC | https://paperswithcode.com/paper/toward-verifying-a-water-treatment-system |
| Repo | |
| Framework | |
Fortia-FBK at SemEval-2017 Task 5: Bullish or Bearish? Inferring Sentiment towards Brands from Financial News Headlines
| Title | Fortia-FBK at SemEval-2017 Task 5: Bullish or Bearish? Inferring Sentiment towards Brands from Financial News Headlines |
| Authors | Youness Mansar, Lorenzo Gatti, Sira Ferradans, Marco Guerini, Jacopo Staiano |
| Abstract | In this paper, we describe a methodology to infer Bullish or Bearish sentiment towards companies/brands. More specifically, our approach leverages affective lexica and word embeddings in combination with convolutional neural networks to infer the sentiment of financial news headlines towards a target company. Such architecture was used and evaluated in the context of the SemEval 2017 challenge (task 5, subtask 2), in which it obtained the best performance. |
| Tasks | Word Embeddings |
| Published | 2017-04-04 |
| URL | http://arxiv.org/abs/1704.00939v1 |
| http://arxiv.org/pdf/1704.00939v1.pdf | |
| PWC | https://paperswithcode.com/paper/fortia-fbk-at-semeval-2017-task-5-bullish-or |
| Repo | |
| Framework | |
Proximally Guided Stochastic Subgradient Method for Nonsmooth, Nonconvex Problems
| Title | Proximally Guided Stochastic Subgradient Method for Nonsmooth, Nonconvex Problems |
| Authors | Damek Davis, Benjamin Grimmer |
| Abstract | In this paper, we introduce a stochastic projected subgradient method for weakly convex (i.e., uniformly prox-regular) nonsmooth, nonconvex functions—a wide class of functions which includes the additive and convex composite classes. At a high-level, the method is an inexact proximal point iteration in which the strongly convex proximal subproblems are quickly solved with a specialized stochastic projected subgradient method. The primary contribution of this paper is a simple proof that the proposed algorithm converges at the same rate as the stochastic gradient method for smooth nonconvex problems. This result appears to be the first convergence rate analysis of a stochastic (or even deterministic) subgradient method for the class of weakly convex functions. |
| Tasks | |
| Published | 2017-07-12 |
| URL | http://arxiv.org/abs/1707.03505v5 |
| http://arxiv.org/pdf/1707.03505v5.pdf | |
| PWC | https://paperswithcode.com/paper/proximally-guided-stochastic-subgradient |
| Repo | |
| Framework | |
Speeding up the Köhler’s method of contrast thresholding
| Title | Speeding up the Köhler’s method of contrast thresholding |
| Authors | Guillaume Noyel |
| Abstract | K{"o}hler’s method is a useful multi-thresholding technique based on boundary contrast. However, the direct algorithm has a too high complexity-O(N 2) i.e. quadratic with the pixel numbers N-to process images at a sufficient speed for practical applications. In this paper, a new algorithm to speed up K{"o}hler’s method is introduced with a complexity in O(N M), M is the number of grey levels. The proposed algorithm is designed for parallelisation and vector processing , which are available in current processors, using OpenMP (Open Multi-Processing) and SIMD instructions (Single Instruction on Multiple Data). A fast implementation allows a gain factor of 405 in an image of 18 million pixels and a video processing in real time (gain factor of 96). |
| Tasks | |
| Published | 2017-07-17 |
| URL | http://arxiv.org/abs/1707.05062v2 |
| http://arxiv.org/pdf/1707.05062v2.pdf | |
| PWC | https://paperswithcode.com/paper/speeding-up-the-kohlers-method-of-contrast |
| Repo | |
| Framework | |
Anomaly Detection in Wireless Sensor Networks
| Title | Anomaly Detection in Wireless Sensor Networks |
| Authors | Pelumi Oluwasanya |
| Abstract | Wireless sensor networks usually comprise a large number of sensors monitoring changes in variables. These changes in variables represent changes in physical quantities. The changes can occur for various reasons; these reasons are highlighted in this work. Outliers are unusual measurements. Outliers are important; they are information-bearing occurrences. This work seeks to identify them based on an approach presented in [1]. A critical review of most previous works in this area has been presented in [2], and few more are considered here just to set the stage. The main work can be described as this; given a set of measurements from sensors that represent a normal situation, [1] proceeds by first estimating the probability density function (pdf) of the set using a data-split approach, then estimate the entropy of the set using the arithmetic mean as an approximation for the expectation. The increase in entropy that occurs when strange data is recorded is used to detect unusual measurements in the test set depending on the desired confidence interval or false alarm rate. The results presented in [1] have been confirmed for different test signals such as the Gaussian, Beta, in one dimension and beta in two dimensions, and a beta and uniform mixture distribution in two dimensions. Finally, the method was confirmed on real data and the results are presented. The major drawbacks of [1] were identified, and a method that seeks to mitigate this using the Bhattacharyya distance is presented. This method detects more subtle anomalies, especially the type that would pass as normal in [1]. Finally, recommendations for future research are presented: the subject of interpretability, especially for subtle measurements, being the most elusive as of today. |
| Tasks | Anomaly Detection |
| Published | 2017-08-27 |
| URL | http://arxiv.org/abs/1708.08053v1 |
| http://arxiv.org/pdf/1708.08053v1.pdf | |
| PWC | https://paperswithcode.com/paper/anomaly-detection-in-wireless-sensor-networks |
| Repo | |
| Framework | |
Image Denoising via CNNs: An Adversarial Approach
| Title | Image Denoising via CNNs: An Adversarial Approach |
| Authors | Nithish Divakar, R. Venkatesh Babu |
| Abstract | Is it possible to recover an image from its noisy version using convolutional neural networks? This is an interesting problem as convolutional layers are generally used as feature detectors for tasks like classification, segmentation and object detection. We present a new CNN architecture for blind image denoising which synergically combines three architecture components, a multi-scale feature extraction layer which helps in reducing the effect of noise on feature maps, an l_p regularizer which helps in selecting only the appropriate feature maps for the task of reconstruction, and finally a three step training approach which leverages adversarial training to give the final performance boost to the model. The proposed model shows competitive denoising performance when compared to the state-of-the-art approaches. |
| Tasks | Denoising, Image Denoising, Object Detection |
| Published | 2017-08-01 |
| URL | http://arxiv.org/abs/1708.00159v1 |
| http://arxiv.org/pdf/1708.00159v1.pdf | |
| PWC | https://paperswithcode.com/paper/image-denoising-via-cnns-an-adversarial |
| Repo | |
| Framework | |
Multitask Evolution with Cartesian Genetic Programming
| Title | Multitask Evolution with Cartesian Genetic Programming |
| Authors | Eric O. Scott, Kenneth A. De Jong |
| Abstract | We introduce a genetic programming method for solving multiple Boolean circuit synthesis tasks simultaneously. This allows us to solve a set of elementary logic functions twice as easily as with a direct, single-task approach. |
| Tasks | |
| Published | 2017-02-07 |
| URL | http://arxiv.org/abs/1702.02217v2 |
| http://arxiv.org/pdf/1702.02217v2.pdf | |
| PWC | https://paperswithcode.com/paper/multitask-evolution-with-cartesian-genetic |
| Repo | |
| Framework | |
TumorNet: Lung Nodule Characterization Using Multi-View Convolutional Neural Network with Gaussian Process
| Title | TumorNet: Lung Nodule Characterization Using Multi-View Convolutional Neural Network with Gaussian Process |
| Authors | Sarfaraz Hussein, Robert Gillies, Kunlin Cao, Qi Song, Ulas Bagci |
| Abstract | Characterization of lung nodules as benign or malignant is one of the most important tasks in lung cancer diagnosis, staging and treatment planning. While the variation in the appearance of the nodules remains large, there is a need for a fast and robust computer aided system. In this work, we propose an end-to-end trainable multi-view deep Convolutional Neural Network (CNN) for nodule characterization. First, we use median intensity projection to obtain a 2D patch corresponding to each dimension. The three images are then concatenated to form a tensor, where the images serve as different channels of the input image. In order to increase the number of training samples, we perform data augmentation by scaling, rotating and adding noise to the input image. The trained network is used to extract features from the input image followed by a Gaussian Process (GP) regression to obtain the malignancy score. We also empirically establish the significance of different high level nodule attributes such as calcification, sphericity and others for malignancy determination. These attributes are found to be complementary to the deep multi-view CNN features and a significant improvement over other methods is obtained. |
| Tasks | Data Augmentation, Lung Cancer Diagnosis |
| Published | 2017-03-02 |
| URL | http://arxiv.org/abs/1703.00645v1 |
| http://arxiv.org/pdf/1703.00645v1.pdf | |
| PWC | https://paperswithcode.com/paper/tumornet-lung-nodule-characterization-using |
| Repo | |
| Framework | |
