Paper Group ANR 498
Online Subspace Tracking for Damage Propagation Modeling and Predictive Analytics: Big Data Perspective. SCR-Apriori for Mining `Sets of Contrasting Rules’. Visual-Relation Conscious Image Generation from Structured-Text. An Algorithmic Equity Toolkit for Technology Audits by Community Advocates and Activists. Weakly Supervised Attention Networks f …
Online Subspace Tracking for Damage Propagation Modeling and Predictive Analytics: Big Data Perspective
| Title | Online Subspace Tracking for Damage Propagation Modeling and Predictive Analytics: Big Data Perspective |
| Authors | Farhan Khan |
| Abstract | We analyze damage propagation modeling of turbo-engines in a data-driven approach. We investigate subspace tracking assuming a low dimensional manifold structure and a static behavior during the healthy state of the machines. Our damage propagation model is based on the deviation of the data from the static behavior and uses the notion of health index as a measure of the condition. Hence, we incorporate condition-based maintenance and estimate the remaining useful life based on the current and previous health indexes. This paper proposes an algorithm that adapts well to the dynamics of the data and underlying system, and reduces the computational complexity by utilizing the low dimensional manifold structure of the data. A significant performance improvement is demonstrated over existing methods by using the proposed algorithm on CMAPSS Turbo-engine datasets. |
| Tasks | |
| Published | 2019-07-26 |
| URL | https://arxiv.org/abs/1907.11477v1 |
| https://arxiv.org/pdf/1907.11477v1.pdf | |
| PWC | https://paperswithcode.com/paper/online-subspace-tracking-for-damage |
| Repo | |
| Framework | |
SCR-Apriori for Mining `Sets of Contrasting Rules’
| Title | SCR-Apriori for Mining `Sets of Contrasting Rules’ | |
| Authors | Marharyta Aleksandrova, Oleg Chertov |
| Abstract | In this paper, we propose an efficient algorithm for mining novel `Set of Contrasting Rules’-pattern (SCR-pattern), which consists of several association rules. This pattern is of high interest due to the guaranteed quality of the rules forming it and its ability to discover useful knowledge. However, SCR-pattern has no efficient mining algorithm. We propose SCR-Apriori algorithm, which results in the same set of SCR-patterns as the state-of-the-art approache, but is less computationally expensive. We also show experimentally that by incorporating the knowledge about the pattern structure into Apriori algorithm, SCR-Apriori can significantly prune the search space of frequent itemsets to be analysed. | |
| Tasks | |
| Published | 2019-12-20 |
| URL | https://arxiv.org/abs/1912.09817v1 |
| https://arxiv.org/pdf/1912.09817v1.pdf | |
| PWC | https://paperswithcode.com/paper/scr-apriori-for-mining-sets-of-contrasting |
| Repo | |
| Framework | |
Visual-Relation Conscious Image Generation from Structured-Text
| Title | Visual-Relation Conscious Image Generation from Structured-Text |
| Authors | Duc Minh Vo, Akihiro Sugimoto |
| Abstract | We introduce visual-relation layout for image generation where relationships among entities from given structured-texts are explicitly employed for entities’ localization. Our end-to-end network consists of the visual-relation layout module and the pyramid of GANs, namely stacking-GANs. The former firstly predicts a relation-unit for each relationship in a given text. It then unifies all the relation-units to produce the visual-relation layout, i.e., bounding-boxes for all the entities so that each of them uniquely corresponds to each entity while keeping its involved relationships. Accordingly, the visual-relation layout reflects the scene structure given in the input text. The latter is the stack of three GANs conditioned on the visual-relation layout and the output of previous GAN, consistently capturing the scene structure. Our network realistically renders entities’ details in high resolution while keeping the scene structure. Experimental results on two public datasets show outperformances of our method against state-of-the-art methods. |
| Tasks | Image Generation, Text-to-Image Generation |
| Published | 2019-08-05 |
| URL | https://arxiv.org/abs/1908.01741v2 |
| https://arxiv.org/pdf/1908.01741v2.pdf | |
| PWC | https://paperswithcode.com/paper/visual-relation-conscious-image-generation |
| Repo | |
| Framework | |
An Algorithmic Equity Toolkit for Technology Audits by Community Advocates and Activists
| Title | An Algorithmic Equity Toolkit for Technology Audits by Community Advocates and Activists |
| Authors | Michael Katell, Meg Young, Bernease Herman, Dharma Dailey, Aaron Tam, Vivian Guetler, Corinne Binz, Daniella Raz, P. M. Krafft |
| Abstract | A wave of recent scholarship documenting the discriminatory harms of algorithmic systems has spurred widespread interest in algorithmic accountability and regulation. Yet effective accountability and regulation is stymied by a persistent lack of resources supporting public understanding of algorithms and artificial intelligence. Through interactions with a US-based civil rights organization and their coalition of community organizations, we identify a need for (i) heuristics that aid stakeholders in distinguishing between types of analytic and information systems in lay language, and (ii) risk assessment tools for such systems that begin by making algorithms more legible. The present work delivers a toolkit to achieve these aims. This paper both presents the Algorithmic Equity Toolkit (AEKit) Equity as an artifact, and details how our participatory process shaped its design. Our work fits within human-computer interaction scholarship as a demonstration of the value of HCI methods and approaches to problems in the area of algorithmic transparency and accountability. |
| Tasks | |
| Published | 2019-12-06 |
| URL | https://arxiv.org/abs/1912.02943v1 |
| https://arxiv.org/pdf/1912.02943v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-algorithmic-equity-toolkit-for-technology |
| Repo | |
| Framework | |
Weakly Supervised Attention Networks for Fine-Grained Opinion Mining and Public Health
| Title | Weakly Supervised Attention Networks for Fine-Grained Opinion Mining and Public Health |
| Authors | Giannis Karamanolakis, Daniel Hsu, Luis Gravano |
| Abstract | In many review classification applications, a fine-grained analysis of the reviews is desirable, because different segments (e.g., sentences) of a review may focus on different aspects of the entity in question. However, training supervised models for segment-level classification requires segment labels, which may be more difficult or expensive to obtain than review labels. In this paper, we employ Multiple Instance Learning (MIL) and use only weak supervision in the form of a single label per review. First, we show that when inappropriate MIL aggregation functions are used, then MIL-based networks are outperformed by simpler baselines. Second, we propose a new aggregation function based on the sigmoid attention mechanism and show that our proposed model outperforms the state-of-the-art models for segment-level sentiment classification (by up to 9.8% in F1). Finally, we highlight the importance of fine-grained predictions in an important public-health application: finding actionable reports of foodborne illness. We show that our model achieves 48.6% higher recall compared to previous models, thus increasing the chance of identifying previously unknown foodborne outbreaks. |
| Tasks | Multiple Instance Learning, Opinion Mining, Sentiment Analysis |
| Published | 2019-09-30 |
| URL | https://arxiv.org/abs/1910.00054v1 |
| https://arxiv.org/pdf/1910.00054v1.pdf | |
| PWC | https://paperswithcode.com/paper/weakly-supervised-attention-networks-for-fine |
| Repo | |
| Framework | |
Analysis of Generalized Expectation-Maximization for Gaussian Mixture Models: A Control Systems Perspective
| Title | Analysis of Generalized Expectation-Maximization for Gaussian Mixture Models: A Control Systems Perspective |
| Authors | Sarthak Chatterjee, Orlando Romero, Sérgio Pequito |
| Abstract | The Expectation-Maximization (EM) algorithm is one of the most popular methods used to solve the problem of parametric distribution-based clustering in unsupervised learning. In this paper, we propose to analyze a subclass of generalized EM (GEM) algorithms in the context of Gaussian mixture models, where the maximization step in the EM is replaced by an increasing step. We show that this subclass of GEM algorithms can be understood as a linear time-invariant (LTI) system with a feedback nonlinearity. Therefore, we explore some of its convergence properties by leveraging tools from robust control theory. Lastly, we explain how the proposed GEM can be designed, and present a pedagogical example to understand the advantages of the proposed approach. |
| Tasks | |
| Published | 2019-03-03 |
| URL | https://arxiv.org/abs/1903.00979v3 |
| https://arxiv.org/pdf/1903.00979v3.pdf | |
| PWC | https://paperswithcode.com/paper/analysis-of-gradient-based-expectation |
| Repo | |
| Framework | |
A Coarse-to-Fine Framework for Learned Color Enhancement with Non-Local Attention
| Title | A Coarse-to-Fine Framework for Learned Color Enhancement with Non-Local Attention |
| Authors | Chaowei Shan, Zhizheng Zhang, Zhibo Chen |
| Abstract | Automatic color enhancement is aimed to adaptively adjust photos to expected styles and tones. For current learned methods in this field, global harmonious perception and local details are hard to be well-considered in a single model simultaneously. To address this problem, we propose a coarse-to-fine framework with non-local attention for color enhancement in this paper. Within our framework, we propose to divide enhancement process into channel-wise enhancement and pixel-wise refinement performed by two cascaded Convolutional Neural Networks (CNNs). In channel-wise enhancement, our model predicts a global linear mapping for RGB channels of input images to perform global style adjustment. In pixel-wise refinement, we learn a refining mapping using residual learning for local adjustment. Further, we adopt a non-local attention block to capture the long-range dependencies from global information for subsequent fine-grained local refinement. We evaluate our proposed framework on the commonly using benchmark and conduct sufficient experiments to demonstrate each technical component within it. |
| Tasks | |
| Published | 2019-06-08 |
| URL | https://arxiv.org/abs/1906.03404v2 |
| https://arxiv.org/pdf/1906.03404v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-coarse-to-fine-framework-for-learned-color |
| Repo | |
| Framework | |
Depth Separations in Neural Networks: What is Actually Being Separated?
| Title | Depth Separations in Neural Networks: What is Actually Being Separated? |
| Authors | Itay Safran, Ronen Eldan, Ohad Shamir |
| Abstract | Existing depth separation results for constant-depth networks essentially show that certain radial functions in $\mathbb{R}^d$, which can be easily approximated with depth $3$ networks, cannot be approximated by depth $2$ networks, even up to constant accuracy, unless their size is exponential in $d$. However, the functions used to demonstrate this are rapidly oscillating, with a Lipschitz parameter scaling polynomially with the dimension $d$ (or equivalently, by scaling the function, the hardness result applies to $\mathcal{O}(1)$-Lipschitz functions only when the target accuracy $\epsilon$ is at most $\text{poly}(1/d)$). In this paper, we study whether such depth separations might still hold in the natural setting of $\mathcal{O}(1)$-Lipschitz radial functions, when $\epsilon$ does not scale with $d$. Perhaps surprisingly, we show that the answer is negative: In contrast to the intuition suggested by previous work, it \emph{is} possible to approximate $\mathcal{O}(1)$-Lipschitz radial functions with depth $2$, size $\text{poly}(d)$ networks, for every constant $\epsilon$. We complement it by showing that approximating such functions is also possible with depth $2$, size $\text{poly}(1/\epsilon)$ networks, for every constant $d$. Finally, we show that it is not possible to have polynomial dependence in both $d,1/\epsilon$ simultaneously. Overall, our results indicate that in order to show depth separations for expressing $\mathcal{O}(1)$-Lipschitz functions with constant accuracy – if at all possible – one would need fundamentally different techniques than existing ones in the literature. |
| Tasks | |
| Published | 2019-04-15 |
| URL | https://arxiv.org/abs/1904.06984v2 |
| https://arxiv.org/pdf/1904.06984v2.pdf | |
| PWC | https://paperswithcode.com/paper/depth-separations-in-neural-networks-what-is |
| Repo | |
| Framework | |
Building an Effective Intrusion Detection System using Unsupervised Feature Selection in Multi-objective Optimization Framework
| Title | Building an Effective Intrusion Detection System using Unsupervised Feature Selection in Multi-objective Optimization Framework |
| Authors | Chanchal Suman, Somanath Tripathy, Sriparna Saha |
| Abstract | Intrusion Detection Systems (IDS) are developed to protect the network by detecting the attack. The current paper proposes an unsupervised feature selection technique for analyzing the network data. The search capability of the non-dominated sorting genetic algorithm (NSGA-II) has been employed for optimizing three different objective functions utilizing different information theoretic measures including mutual information, standard deviation, and information gain to identify mutually exclusive and a high variant subset of features. Finally, the Pareto optimal front of the different optimal feature subsets are obtained and these feature subsets are utilized for developing classification systems using different popular machine learning models like support vector machines, decision trees and k-nearest neighbour (k=5) classifier etc. We have evaluated the results of the algorithm on KDD-99, NSL-KDD and Kyoto 2006+ datasets. The experimental results on KDD-99 dataset show that decision tree provides better results than other available classifiers. The proposed system obtains the best results of 99.78% accuracy, 99.27% detection rate and false alarm rate of 0.2%, which are better than all the previous results for KDD dataset. We achieved an accuracy of 99.83% for 20% testing data of NSL-KDD dataset and 99.65% accuracy for 10-fold cross-validation on Kyoto dataset. The most attractive characteristic of the proposed scheme is that during the selection of appropriate feature subset, no labeled information is utilized and different feature quality measures are optimized simultaneously using the multi-objective optimization framework. |
| Tasks | Feature Selection, Intrusion Detection |
| Published | 2019-05-16 |
| URL | https://arxiv.org/abs/1905.06562v1 |
| https://arxiv.org/pdf/1905.06562v1.pdf | |
| PWC | https://paperswithcode.com/paper/building-an-effective-intrusion-detection |
| Repo | |
| Framework | |
Estimation of Linear Motion in Dense Crowd Videos using Langevin Model
| Title | Estimation of Linear Motion in Dense Crowd Videos using Langevin Model |
| Authors | Shreetam Behera, Debi Prosad Dogra, Malay Kumar Bandyopadhyay, Partha Pratim Roy |
| Abstract | Crowd gatherings at social and cultural events are increasing in leaps and bounds with the increase in population. Surveillance through computer vision and expert decision making systems can help to understand the crowd phenomena at large gatherings. Understanding crowd phenomena can be helpful in early identification of unwanted incidents and their prevention. Motion flow is one of the important crowd phenomena that can be instrumental in describing the crowd behavior. Flows can be useful in understanding instabilities in the crowd. However, extracting motion flows is a challenging task due to randomness in crowd movement and limitations of the sensing device. Moreover, low-level features such as optical flow can be misleading if the randomness is high. In this paper, we propose a new model based on Langevin equation to analyze the linear dominant flows in videos of densely crowded scenarios. We assume a force model with three components, namely external force, confinement/drift force, and disturbance force. These forces are found to be sufficient to describe the linear or near-linear motion in dense crowd videos. The method is significantly faster as compared to existing popular crowd segmentation methods. The evaluation of the proposed model has been carried out on publicly available datasets as well as using our dataset. It has been observed that the proposed method is able to estimate and segment the linear flows in the dense crowd with better accuracy as compared to state-of-the-art techniques with substantial decrease in the computational overhead. |
| Tasks | Decision Making, Optical Flow Estimation |
| Published | 2019-04-15 |
| URL | http://arxiv.org/abs/1904.07233v1 |
| http://arxiv.org/pdf/1904.07233v1.pdf | |
| PWC | https://paperswithcode.com/paper/estimation-of-linear-motion-in-dense-crowd |
| Repo | |
| Framework | |
Rank3DGAN: Semantic mesh generation using relative attributes
| Title | Rank3DGAN: Semantic mesh generation using relative attributes |
| Authors | Yassir Saquil, Qun-Ce Xu, Yong-Liang Yang, Peter Hall |
| Abstract | In this paper, we investigate a novel problem of using generative adversarial networks in the task of 3D shape generation according to semantic attributes. Recent works map 3D shapes into 2D parameter domain, which enables training Generative Adversarial Networks (GANs) for 3D shape generation task. We extend these architectures to the conditional setting, where we generate 3D shapes with respect to subjective attributes defined by the user. Given pairwise comparisons of 3D shapes, our model performs two tasks: it learns a generative model with a controlled latent space, and a ranking function for the 3D shapes based on their multi-chart representation in 2D. The capability of the model is demonstrated with experiments on HumanShape, Basel Face Model and reconstructed 3D CUB datasets. We also present various applications that benefit from our model, such as multi-attribute exploration, mesh editing, and mesh attribute transfer. |
| Tasks | 3D Shape Generation |
| Published | 2019-05-24 |
| URL | https://arxiv.org/abs/1905.10257v2 |
| https://arxiv.org/pdf/1905.10257v2.pdf | |
| PWC | https://paperswithcode.com/paper/rank3dgan-semantic-mesh-generation-using |
| Repo | |
| Framework | |
Robust Encoder-Decoder Learning Framework towards Offline Handwritten Mathematical Expression Recognition Based on Multi-Scale Deep Neural Network
| Title | Robust Encoder-Decoder Learning Framework towards Offline Handwritten Mathematical Expression Recognition Based on Multi-Scale Deep Neural Network |
| Authors | Guangcun Shan, Hongyu Wang, Wei Liang |
| Abstract | Offline handwritten mathematical expression recognition is a challenging task, because handwritten mathematical expressions mainly have two problems in the process of recognition. On one hand, it is how to correctly recognize different mathematical symbols. On the other hand, it is how to correctly recognize the two-dimensional structure existing in mathematical expressions. Inspired by recent work in deep learning, a new neural network model that combines a Multi-Scale convolutional neural network (CNN) with an Attention recurrent neural network (RNN) is proposed to identify two-dimensional handwritten mathematical expressions as one-dimensional LaTeX sequences. As a result, the model proposed in the present work has achieved a WER error of 25.715% and ExpRate of 28.216%. |
| Tasks | |
| Published | 2019-02-08 |
| URL | http://arxiv.org/abs/1902.05376v2 |
| http://arxiv.org/pdf/1902.05376v2.pdf | |
| PWC | https://paperswithcode.com/paper/robust-encoder-decoder-learning-framework |
| Repo | |
| Framework | |
Fusing location and text features for sentiment classification
| Title | Fusing location and text features for sentiment classification |
| Authors | Wei Lun Lim, Chiung Ching Ho, Choo-Yee Ting |
| Abstract | Geo-tagged Twitter data has been used recently to infer insights on the human aspects of social media. Insights related to demographics, spatial distribution of cultural activities, space-time travel trajectories for humans as well as happiness has been mined from geo-tagged twitter data in recent studies. To date, not much study has been done on the impact of the geolocation features of a Tweet on its sentiment. This observation has inspired us to propose the usage of geo-location features as a method to perform sentiment classification. In this method, the sentiment classification of geo-tagged tweets is performed by concatenating geo-location features and one-hot encoded word vectors as inputs for convolutional neural networks (CNN) and long short-term memory (LSTM) networks. The addition of language-independent features in the form of geo-location features has helped to enrich the tweet representation in order to combat the sparse nature of short tweet message. The results achieved has demonstrated that concatenating geo-location features to one-hot encoded word vectors can achieve higher accuracy as compared to the usage of word vectors alone for the purpose of sentiment classification. |
| Tasks | Sentiment Analysis |
| Published | 2019-07-28 |
| URL | https://arxiv.org/abs/1907.12008v1 |
| https://arxiv.org/pdf/1907.12008v1.pdf | |
| PWC | https://paperswithcode.com/paper/fusing-location-and-text-features-for |
| Repo | |
| Framework | |
Diversity-Sensitive Conditional Generative Adversarial Networks
| Title | Diversity-Sensitive Conditional Generative Adversarial Networks |
| Authors | Dingdong Yang, Seunghoon Hong, Yunseok Jang, Tianchen Zhao, Honglak Lee |
| Abstract | We propose a simple yet highly effective method that addresses the mode-collapse problem in the Conditional Generative Adversarial Network (cGAN). Although conditional distributions are multi-modal (i.e., having many modes) in practice, most cGAN approaches tend to learn an overly simplified distribution where an input is always mapped to a single output regardless of variations in latent code. To address such issue, we propose to explicitly regularize the generator to produce diverse outputs depending on latent codes. The proposed regularization is simple, general, and can be easily integrated into most conditional GAN objectives. Additionally, explicit regularization on generator allows our method to control a balance between visual quality and diversity. We demonstrate the effectiveness of our method on three conditional generation tasks: image-to-image translation, image inpainting, and future video prediction. We show that simple addition of our regularization to existing models leads to surprisingly diverse generations, substantially outperforming the previous approaches for multi-modal conditional generation specifically designed in each individual task. |
| Tasks | Image Inpainting, Image-to-Image Translation, Video Prediction |
| Published | 2019-01-25 |
| URL | http://arxiv.org/abs/1901.09024v1 |
| http://arxiv.org/pdf/1901.09024v1.pdf | |
| PWC | https://paperswithcode.com/paper/diversity-sensitive-conditional-generative |
| Repo | |
| Framework | |
Adversarial Attack with Pattern Replacement
| Title | Adversarial Attack with Pattern Replacement |
| Authors | Ziang Dong, Liang Mao, Shiliang Sun |
| Abstract | We propose a generative model for adversarial attack. The model generates subtle but predictive patterns from the input. To perform an attack, it replaces the patterns of the input with those generated based on examples from some other class. We demonstrate our model by attacking CNN on MNIST. |
| Tasks | Adversarial Attack |
| Published | 2019-11-25 |
| URL | https://arxiv.org/abs/1911.10875v1 |
| https://arxiv.org/pdf/1911.10875v1.pdf | |
| PWC | https://paperswithcode.com/paper/adversarial-attack-with-pattern-replacement |
| Repo | |
| Framework | |
