Paper Group ANR 152
Representing scenarios for process evolution management. Semantic Relation Classification: Task Formalisation and Refinement. Proceedings of the Artificial Intelligence for Cyber Security (AICS) Workshop 2019. Decoupling Semantic Context and Color Correlation with multi-class cross branch regularization. Towards a More Practice-Aware Runtime Analys …
Representing scenarios for process evolution management
| Title | Representing scenarios for process evolution management |
| Authors | Anton Kolonin |
| Abstract | In the following writing we discuss a conceptual framework for representing events and scenarios from the perspective of a novel form of causal analysis. This causal analysis is applied to the events and scenarios so as to determine measures that could be used to manage the development of the processes that they are a part of in real time. An overall terminological framework and entity-relationship model are suggested along with a specification of the functional sets involved in both reasoning and analytics. The model is considered to be a specific case of the generic problem of finding sequential series in disparate data. The specific inference and reasoning processes are identified for future implementation. |
| Tasks | |
| Published | 2018-07-05 |
| URL | http://arxiv.org/abs/1807.02072v1 |
| http://arxiv.org/pdf/1807.02072v1.pdf | |
| PWC | https://paperswithcode.com/paper/representing-scenarios-for-process-evolution |
| Repo | |
| Framework | |
Semantic Relation Classification: Task Formalisation and Refinement
| Title | Semantic Relation Classification: Task Formalisation and Refinement |
| Authors | Vivian S. Silva, Manuela Hürliman, Brian Davis, Siegfried Handschuh, André Freitas |
| Abstract | The identification of semantic relations between terms within texts is a fundamental task in Natural Language Processing which can support applications requiring a lightweight semantic interpretation model. Currently, semantic relation classification concentrates on relations which are evaluated over open-domain data. This work provides a critique on the set of abstract relations used for semantic relation classification with regard to their ability to express relationships between terms which are found in a domain-specific corpora. Based on this analysis, this work proposes an alternative semantic relation model based on reusing and extending the set of abstract relations present in the DOLCE ontology. The resulting set of relations is well grounded, allows to capture a wide range of relations and could thus be used as a foundation for automatic classification of semantic relations. |
| Tasks | Relation Classification |
| Published | 2018-06-20 |
| URL | http://arxiv.org/abs/1806.07721v1 |
| http://arxiv.org/pdf/1806.07721v1.pdf | |
| PWC | https://paperswithcode.com/paper/semantic-relation-classification-task |
| Repo | |
| Framework | |
Proceedings of the Artificial Intelligence for Cyber Security (AICS) Workshop 2019
| Title | Proceedings of the Artificial Intelligence for Cyber Security (AICS) Workshop 2019 |
| Authors | William W. Streilein, Brad Dillman |
| Abstract | This volume represents the proceedings of the Artificial Intelligence for Cyber Security (AICS) Workshop 2019, held on January 27, 2019 in Honolulu, Hawaii. |
| Tasks | |
| Published | 2018-12-17 |
| URL | http://arxiv.org/abs/1812.07469v2 |
| http://arxiv.org/pdf/1812.07469v2.pdf | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-artificial-intelligence |
| Repo | |
| Framework | |
Decoupling Semantic Context and Color Correlation with multi-class cross branch regularization
| Title | Decoupling Semantic Context and Color Correlation with multi-class cross branch regularization |
| Authors | Vishal Keshav, Tejpratap G. V. S. L |
| Abstract | This paper presents a novel design methodology for architecting a light-weight and faster DNN architecture for vision applications. The effectiveness of the architecture is demonstrated on Color-Constancy use case an inherent block in camera and imaging pipelines. Specifically, we present a multi-branch architecture that disassembles the contextual features and color properties from an image, and later combines them to predict a global property (e.g. Global Illumination). We also propose an implicit regularization technique by designing cross-branch regularization block that enables the network to retain high generalization accuracy. With a conservative use of best computational operators, the proposed architecture achieves state-of-the-art accuracy with 30X lesser model parameters and 70X faster inference time for color constancy. It is also shown that the proposed architecture is generic and achieves similar efficiency in other vision applications such as Low-Light photography. |
| Tasks | Color Constancy |
| Published | 2018-10-18 |
| URL | http://arxiv.org/abs/1810.07901v2 |
| http://arxiv.org/pdf/1810.07901v2.pdf | |
| PWC | https://paperswithcode.com/paper/decoupling-semantic-context-and-color |
| Repo | |
| Framework | |
Towards a More Practice-Aware Runtime Analysis of Evolutionary Algorithms
| Title | Towards a More Practice-Aware Runtime Analysis of Evolutionary Algorithms |
| Authors | Eduardo Carvalho Pinto, Carola Doerr |
| Abstract | Theory of evolutionary computation (EC) aims at providing mathematically founded statements about the performance of evolutionary algorithms (EAs). The predominant topic in this research domain is runtime analysis, which studies the time it takes a given EA to solve a given optimization problem. Runtime analysis has witnessed significant advances in the last couple of years, allowing us to compute precise runtime estimates for several EAs and several problems. Runtime analysis is, however (and unfortunately!), often judged by practitioners to be of little relevance for real applications of EAs. Several reasons for this claim exist. We address two of them in this present work: (1) EA implementations often differ from their vanilla pseudocode description, which, in turn, typically form the basis for runtime analysis. To close the resulting gap between empirically observed and theoretically derived performance estimates, we therefore suggest to take this discrepancy into account in the mathematical analysis and to adjust, for example, the cost assigned to the evaluation of search points that equal one of their direct parents (provided that this is easy to verify as is the case in almost all standard EAs). (2) Most runtime analysis results make statements about the expected time to reach an optimal solution (and possibly the distribution of this optimization time) only, thus explicitly or implicitly neglecting the importance of understanding how the function values evolve over time. We suggest to extend runtime statements to runtime profiles, covering the expected time needed to reach points of intermediate fitness values. As a direct consequence, we obtain a result showing that the greedy (2+1) GA of Sudholt [GECCO 2012] outperforms any unary unbiased black-box algorithm on OneMax. |
| Tasks | |
| Published | 2018-12-03 |
| URL | http://arxiv.org/abs/1812.00493v1 |
| http://arxiv.org/pdf/1812.00493v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-a-more-practice-aware-runtime |
| Repo | |
| Framework | |
Prospects for Declarative Mathematical Modeling of Complex Biological Systems
| Title | Prospects for Declarative Mathematical Modeling of Complex Biological Systems |
| Authors | Eric Mjolsness |
| Abstract | Declarative modeling uses symbolic expressions to represent models. With such expressions one can formalize high-level mathematical computations on models that would be difficult or impossible to perform directly on a lower-level simulation program, in a general-purpose programming language. Examples of such computations on models include model analysis, relatively general-purpose model-reduction maps, and the initial phases of model implementation, all of which should preserve or approximate the mathematical semantics of a complex biological model. The potential advantages are particularly relevant in the case of developmental modeling, wherein complex spatial structures exhibit dynamics at molecular, cellular, and organogenic levels to relate genotype to multicellular phenotype. Multiscale modeling can benefit from both the expressive power of declarative modeling languages and the application of model reduction methods to link models across scale. Based on previous work, here we define declarative modeling of complex biological systems by defining the operator algebra semantics of an increasingly powerful series of declarative modeling languages including reaction-like dynamics of parameterized and extended objects; we define semantics-preserving implementation and semantics-approximating model reduction transformations; and we outline a “meta-hierarchy” for organizing declarative models and the mathematical methods that can fruitfully manipulate them. |
| Tasks | |
| Published | 2018-04-30 |
| URL | https://arxiv.org/abs/1804.11044v2 |
| https://arxiv.org/pdf/1804.11044v2.pdf | |
| PWC | https://paperswithcode.com/paper/prospects-for-declarative-mathematical |
| Repo | |
| Framework | |
Green Stability Assumption: Unsupervised Learning for Statistics-Based Illumination Estimation
| Title | Green Stability Assumption: Unsupervised Learning for Statistics-Based Illumination Estimation |
| Authors | Nikola Banić, Sven Lončarić |
| Abstract | In the image processing pipeline of almost every digital camera there is a part dedicated to computational color constancy i.e. to removing the influence of illumination on the colors of the image scene. Some of the best known illumination estimation methods are the so called statistics-based methods. They are less accurate than the learning-based illumination estimation methods, but they are faster and simpler to implement in embedded systems, which is one of the reasons for their widespread usage. Although in the relevant literature it often appears as if they require no training, this is not true because they have parameter values that need to be fine-tuned in order to be more accurate. In this paper it is first shown that the accuracy of statistics-based methods reported in most papers was not obtained by means of the necessary cross-validation, but by using the whole benchmark datasets for both training and testing. After that the corrected results are given for the best known benchmark datasets. Finally, the so called green stability assumption is proposed that can be used to fine-tune the values of the parameters of the statistics-based methods by using only non-calibrated images without known ground-truth illumination. The obtained accuracy is practically the same as when using calibrated training images, but the whole process is much faster. The experimental results are presented and discussed. The source code is available at http://www.fer.unizg.hr/ipg/resources/color_constancy/. |
| Tasks | Color Constancy |
| Published | 2018-02-02 |
| URL | http://arxiv.org/abs/1802.00776v1 |
| http://arxiv.org/pdf/1802.00776v1.pdf | |
| PWC | https://paperswithcode.com/paper/green-stability-assumption-unsupervised |
| Repo | |
| Framework | |
Learning disentangled representation from 12-lead electrograms: application in localizing the origin of Ventricular Tachycardia
| Title | Learning disentangled representation from 12-lead electrograms: application in localizing the origin of Ventricular Tachycardia |
| Authors | Prashnna K Gyawali, B. Milan Horacek, John L. Sapp, Linwei Wang |
| Abstract | The increasing availability of electrocardiogram (ECG) data has motivated the use of data-driven models for automating various clinical tasks based on ECG data. The development of subject-specific models are limited by the cost and difficulty of obtaining sufficient training data for each individual. The alternative of population model, however, faces challenges caused by the significant inter-subject variations within the ECG data. We address this challenge by investigating for the first time the problem of learning representations for clinically-informative variables while disentangling other factors of variations within the ECG data. In this work, we present a conditional variational autoencoder (VAE) to extract the subject-specific adjustment to the ECG data, conditioned on task-specific representations learned from a deterministic encoder. To encourage the representation for inter-subject variations to be independent from the task-specific representation, maximum mean discrepancy is used to match all the moments between the distributions learned by the VAE conditioning on the code from the deterministic encoder. The learning of the task-specific representation is regularized by a weak supervision in the form of contrastive regularization. We apply the proposed method to a novel yet important clinical task of classifying the origin of ventricular tachycardia (VT) into pre-defined segments, demonstrating the efficacy of the proposed method against the standard VAE. |
| Tasks | |
| Published | 2018-08-04 |
| URL | http://arxiv.org/abs/1808.01524v1 |
| http://arxiv.org/pdf/1808.01524v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-disentangled-representation-from-12 |
| Repo | |
| Framework | |
Anomaly Detection for Skin Disease Images Using Variational Autoencoder
| Title | Anomaly Detection for Skin Disease Images Using Variational Autoencoder |
| Authors | Yuchen Lu, Peng Xu |
| Abstract | In this paper, we demonstrate the potential of applying Variational Autoencoder (VAE) [10] for anomaly detection in skin disease images. VAE is a class of deep generative models which is trained by maximizing the evidence lower bound of data distribution [10]. When trained on only normal data, the resulting model is able to perform efficient inference and to determine if a test image is normal or not. We perform experiments on ISIC2018 Challenge Disease Classification dataset (Task 3) and compare different methods to use VAE to detect anomaly. The model is able to detect all diseases with 0.779 AUCROC. If we focus on specific diseases, the model is able to detect melanoma with 0.864 AUCROC and detect actinic keratosis with 0.872 AUCROC, even if it only sees the images of nevus. To the best of our knowledge, this is the first applied work of deep generative models for anomaly detection in dermatology. |
| Tasks | Anomaly Detection |
| Published | 2018-07-03 |
| URL | http://arxiv.org/abs/1807.01349v2 |
| http://arxiv.org/pdf/1807.01349v2.pdf | |
| PWC | https://paperswithcode.com/paper/anomaly-detection-for-skin-disease-images |
| Repo | |
| Framework | |
Deep Residual Learning in the JPEG Transform Domain
| Title | Deep Residual Learning in the JPEG Transform Domain |
| Authors | Max Ehrlich, Larry Davis |
| Abstract | We introduce a general method of performing Residual Network inference and learning in the JPEG transform domain that allows the network to consume compressed images as input. Our formulation leverages the linearity of the JPEG transform to redefine convolution and batch normalization with a tune-able numerical approximation for ReLu. The result is mathematically equivalent to the spatial domain network up to the ReLu approximation accuracy. A formulation for image classification and a model conversion algorithm for spatial domain networks are given as examples of the method. We show that the sparsity of the JPEG format allows for faster processing of images with little to no penalty in the network accuracy. |
| Tasks | Image Classification |
| Published | 2018-12-31 |
| URL | https://arxiv.org/abs/1812.11690v3 |
| https://arxiv.org/pdf/1812.11690v3.pdf | |
| PWC | https://paperswithcode.com/paper/deep-residual-learning-in-the-jpeg-transform |
| Repo | |
| Framework | |
Scaling limit of the Stein variational gradient descent: the mean field regime
| Title | Scaling limit of the Stein variational gradient descent: the mean field regime |
| Authors | Jianfeng Lu, Yulong Lu, James Nolen |
| Abstract | We study an interacting particle system in $\mathbf{R}^d$ motivated by Stein variational gradient descent [Q. Liu and D. Wang, NIPS 2016], a deterministic algorithm for sampling from a given probability density with unknown normalization. We prove that in the large particle limit the empirical measure of the particle system converges to a solution of a non-local and nonlinear PDE. We also prove global existence, uniqueness and regularity of the solution to the limiting PDE. Finally, we prove that the solution to the PDE converges to the unique invariant solution in long time limit. |
| Tasks | |
| Published | 2018-05-10 |
| URL | http://arxiv.org/abs/1805.04035v3 |
| http://arxiv.org/pdf/1805.04035v3.pdf | |
| PWC | https://paperswithcode.com/paper/scaling-limit-of-the-stein-variational |
| Repo | |
| Framework | |
Object Discovery in Videos as Foreground Motion Clustering
| Title | Object Discovery in Videos as Foreground Motion Clustering |
| Authors | Christopher Xie, Yu Xiang, Zaid Harchaoui, Dieter Fox |
| Abstract | We consider the problem of providing dense segmentation masks for object discovery in videos. We formulate the object discovery problem as foreground motion clustering, where the goal is to cluster foreground pixels in videos into different objects. We introduce a novel pixel-trajectory recurrent neural network that learns feature embeddings of foreground pixel trajectories linked across time. By clustering the pixel trajectories using the learned feature embeddings, our method establishes correspondences between foreground object masks across video frames. To demonstrate the effectiveness of our framework for object discovery, we conduct experiments on commonly used datasets for motion segmentation, where we achieve state-of-the-art performance. |
| Tasks | Motion Segmentation, Object Discovery In Videos |
| Published | 2018-12-06 |
| URL | http://arxiv.org/abs/1812.02772v2 |
| http://arxiv.org/pdf/1812.02772v2.pdf | |
| PWC | https://paperswithcode.com/paper/object-discovery-in-videos-as-foreground |
| Repo | |
| Framework | |
EmotionLines: An Emotion Corpus of Multi-Party Conversations
| Title | EmotionLines: An Emotion Corpus of Multi-Party Conversations |
| Authors | Sheng-Yeh Chen, Chao-Chun Hsu, Chuan-Chun Kuo, Ting-Hao, Huang, Lun-Wei Ku |
| Abstract | Feeling emotion is a critical characteristic to distinguish people from machines. Among all the multi-modal resources for emotion detection, textual datasets are those containing the least additional information in addition to semantics, and hence are adopted widely for testing the developed systems. However, most of the textual emotional datasets consist of emotion labels of only individual words, sentences or documents, which makes it challenging to discuss the contextual flow of emotions. In this paper, we introduce EmotionLines, the first dataset with emotions labeling on all utterances in each dialogue only based on their textual content. Dialogues in EmotionLines are collected from Friends TV scripts and private Facebook messenger dialogues. Then one of seven emotions, six Ekman’s basic emotions plus the neutral emotion, is labeled on each utterance by 5 Amazon MTurkers. A total of 29,245 utterances from 2,000 dialogues are labeled in EmotionLines. We also provide several strong baselines for emotion detection models on EmotionLines in this paper. |
| Tasks | |
| Published | 2018-02-23 |
| URL | http://arxiv.org/abs/1802.08379v2 |
| http://arxiv.org/pdf/1802.08379v2.pdf | |
| PWC | https://paperswithcode.com/paper/emotionlines-an-emotion-corpus-of-multi-party |
| Repo | |
| Framework | |
Segmentation-Free Approaches for Handwritten Numeral String Recognition
| Title | Segmentation-Free Approaches for Handwritten Numeral String Recognition |
| Authors | Andre G Hochuli, Luiz E S Oliveira, Alceu S Britto Jr, Robert Sabourin |
| Abstract | This paper presents segmentation-free strategies for the recognition of handwritten numeral strings of unknown length. A synthetic dataset of touching numeral strings of sizes 2-, 3- and 4-digits was created to train end-to-end solutions based on Convolutional Neural Networks. A robust experimental protocol is used to show that the proposed segmentation-free methods may reach the state-of-the-art performance without suffering the heavy burden of over-segmentation based methods. In addition, they confirmed the importance of introducing contextual information in the design of end-to-end solutions, such as the proposed length classifier when recognizing numeral strings. |
| Tasks | |
| Published | 2018-04-24 |
| URL | http://arxiv.org/abs/1804.09279v3 |
| http://arxiv.org/pdf/1804.09279v3.pdf | |
| PWC | https://paperswithcode.com/paper/segmentation-free-approaches-for-handwritten |
| Repo | |
| Framework | |
A Deep Learning Approach for Forecasting Air Pollution in South Korea Using LSTM
| Title | A Deep Learning Approach for Forecasting Air Pollution in South Korea Using LSTM |
| Authors | Tien-Cuong Bui, Van-Duc Le, Sang-Kyun Cha |
| Abstract | Tackling air pollution is an imperative problem in South Korea, especially in urban areas, over the last few years. More specially, South Korea has joined the ranks of the world’s most polluted countries alongside with other Asian capitals, such as Beijing or Delhi. Much research is being conducted in environmental science to evaluate the dangerous impact of particulate matters on public health. Besides that, deterministic models of air pollutant behavior are also generated; however, this is both complex and often inaccurate. On the contrary, deep recurrent neural network reveals potent potential on forecasting out-comes of time-series data and has become more prevalent. This paper uses Recurrent Neural Network (RNN) with Long Short-Term Memory units as a framework for leveraging knowledge from time-series data of air pollution and meteorological information in Daegu, Seoul, Beijing, and Shenyang. Additionally, we use encoder-decoder model, which is similar to machine comprehension problems, as a crucial part of our prediction machine. Finally, we investigate the prediction accuracy of various configurations. Our experiments prevent the efficiency of integrating multiple layers of RNN on prediction model when forecasting far timesteps ahead. This research is a significant motivation for not only continuing researching on urban air quality but also help the government leverage that insight to enact beneficial policies |
| Tasks | Reading Comprehension, Time Series |
| Published | 2018-04-21 |
| URL | http://arxiv.org/abs/1804.07891v3 |
| http://arxiv.org/pdf/1804.07891v3.pdf | |
| PWC | https://paperswithcode.com/paper/a-deep-learning-approach-for-forecasting-air |
| Repo | |
| Framework | |
