Paper Group ANR 1525
Conditional Neural Style Transfer with Peer-Regularized Feature Transform. Simultaneous Identification of Tweet Purpose and Position. Towards more effective consumer steering via network analysis. Impact of Narrow Lanes on Arterial Road Vehicle Crashes: A Machine Learning Approach. PerceptNet: Learning Perceptual Similarity of Haptic Textures in Pr …
Conditional Neural Style Transfer with Peer-Regularized Feature Transform
| Title | Conditional Neural Style Transfer with Peer-Regularized Feature Transform |
| Authors | Jan Svoboda, Asha Anoosheh, Christian Osendorfer, Jonathan Masci |
| Abstract | This paper introduces a neural style transfer model to conditionally generate a stylized image using only a set of examples describing the desired style. The proposed solution produces high-quality images even in the zero-shot setting and allows for greater freedom in changing the content geometry. This is thanks to the introduction of a novel Peer-Regularization Layer that recomposes style in latent space by means of a custom graph convolutional layer aiming at separating style and content. Contrary to the vast majority of existing solutions our model does not require any pre-trained network for computing perceptual losses and can be trained fully end-to-end with a new set of cyclic losses that operate directly in latent space. An extensive ablation study confirms the usefulness of the proposed losses and of the Peer-Regularization Layer, with qualitative results that are competitive with respect to the current state-of-the-art even in the challenging zero-shot setting. This opens the door to more abstract and artistic neural image generation scenarios and easier deployment of the model in. production |
| Tasks | Image Generation, Style Transfer |
| Published | 2019-06-07 |
| URL | https://arxiv.org/abs/1906.02913v2 |
| https://arxiv.org/pdf/1906.02913v2.pdf | |
| PWC | https://paperswithcode.com/paper/conditional-neural-style-transfer-with-peer |
| Repo | |
| Framework | |
Simultaneous Identification of Tweet Purpose and Position
| Title | Simultaneous Identification of Tweet Purpose and Position |
| Authors | Rahul Radhakrishnan Iyer, Yulong Pei, Katia Sycara |
| Abstract | Tweet classification has attracted considerable attention recently. Most of the existing work on tweet classification focuses on topic classification, which classifies tweets into several predefined categories, and sentiment classification, which classifies tweets into positive, negative and neutral. Since tweets are different from conventional text in that they generally are of limited length and contain informal, irregular or new words, so it is difficult to determine user intention to publish a tweet and user attitude towards certain topic. In this paper, we aim to simultaneously classify tweet purpose, i.e., the intention for user to publish a tweet, and position, i.e., supporting, opposing or being neutral to a given topic. By transforming this problem to a multi-label classification problem, a multi-label classification method with post-processing is proposed. Experiments on real-world data sets demonstrate the effectiveness of this method and the results outperform the individual classification methods. |
| Tasks | Multi-Label Classification, Sentiment Analysis |
| Published | 2019-12-24 |
| URL | https://arxiv.org/abs/2001.00051v1 |
| https://arxiv.org/pdf/2001.00051v1.pdf | |
| PWC | https://paperswithcode.com/paper/simultaneous-identification-of-tweet-purpose |
| Repo | |
| Framework | |
Towards more effective consumer steering via network analysis
| Title | Towards more effective consumer steering via network analysis |
| Authors | Jacopo Arpetti, Antonio Iovanella |
| Abstract | Increased data gathering capacity, together with the spread of data analytics techniques, has prompted an unprecedented concentration of information related to the individuals’ preferences in the hands of a few gatekeepers. In the present paper, we show how platforms’ performances still appear astonishing in relation to some unexplored data and networks properties, capable to enhance the platforms’ capacity to implement steering practices by means of an increased ability to estimate individuals’ preferences. To this end, we rely on network science whose analytical tools allow data representations capable of highlighting relationships between subjects and/or items, extracting a great amount of information. We therefore propose a measure called Network Information Patrimony, considering the amount of information available within the system and we look into how platforms could exploit data stemming from connected profiles within a network, with a view to obtaining competitive advantages. Our measure takes into account the quality of the connections among nodes as the one of a hypothetical user in relation to its neighbourhood, detecting how users with a good neighbourhood – hence of a superior connections set – obtain better information. We tested our measures on Amazons’ instances, obtaining evidence which confirm the relevance of information extracted from nodes’ neighbourhood in order to steer targeted users. |
| Tasks | |
| Published | 2019-03-27 |
| URL | https://arxiv.org/abs/1903.11469v2 |
| https://arxiv.org/pdf/1903.11469v2.pdf | |
| PWC | https://paperswithcode.com/paper/towards-more-effective-consumer-steering-via |
| Repo | |
| Framework | |
Impact of Narrow Lanes on Arterial Road Vehicle Crashes: A Machine Learning Approach
| Title | Impact of Narrow Lanes on Arterial Road Vehicle Crashes: A Machine Learning Approach |
| Authors | Mohammed Elhenawy, Arash Jahangiri, Hesham Rakha |
| Abstract | In this paper we adopted state-of-the-art machine learning algorithms, namely: random forest (RF) and least squares boosting, to model crash data and identify the optimum model to study the impact of narrow lanes on the safety of arterial roads. Using a ten-year crash dataset in four cities in Nebraska, two machine learning models were assessed based on the prediction error. The RF model was identified as the best model. The RF was used to compute the importance of the lane width predictors in our regression model based on two different measures. Subsequently, the RF model was used to simulate the crash rate for different lane widths. The Kruskal-Wallis test, was then conducted to determine if simulated values from the four lane width groups have equal means. The test null hypothesis of equal means for simulated values from the four lane width groups was rejected. Consequently, it was concluded that the crash rates from at least one lane width group was statistically different from the others. Finally, the results from the pairwise comparisons using the Tukey and Kramer test showed that the changes in crash rates between any two lane width conditions were statistically significant. |
| Tasks | |
| Published | 2019-11-07 |
| URL | https://arxiv.org/abs/1911.04954v1 |
| https://arxiv.org/pdf/1911.04954v1.pdf | |
| PWC | https://paperswithcode.com/paper/impact-of-narrow-lanes-on-arterial-road |
| Repo | |
| Framework | |
PerceptNet: Learning Perceptual Similarity of Haptic Textures in Presence of Unorderable Triplets
| Title | PerceptNet: Learning Perceptual Similarity of Haptic Textures in Presence of Unorderable Triplets |
| Authors | Priyadarshini K, Siddhartha Chaudhuri, Subhasis Chaudhuri |
| Abstract | In order to design haptic icons or build a haptic vocabulary, we require a set of easily distinguishable haptic signals to avoid perceptual ambiguity, which in turn requires a way to accurately estimate the perceptual (dis)similarity of such signals. In this work, we present a novel method to learn such a perceptual metric based on data from human studies. Our method is based on a deep neural network that projects signals to an embedding space where the natural Euclidean distance accurately models the degree of dissimilarity between two signals. The network is trained only on non-numerical comparisons of triplets of signals, using a novel triplet loss that considers both types of triplets that are easy to order (inequality constraints), as well as those that are unorderable/ambiguous (equality constraints). Unlike prior MDS-based non-parametric approaches, our method can be trained on a partial set of comparisons and can embed new haptic signals without retraining the model from scratch. Extensive experimental evaluations show that our method is significantly more effective at modeling perceptual dissimilarity than alternatives. |
| Tasks | |
| Published | 2019-05-08 |
| URL | https://arxiv.org/abs/1905.03302v1 |
| https://arxiv.org/pdf/1905.03302v1.pdf | |
| PWC | https://paperswithcode.com/paper/190503302 |
| Repo | |
| Framework | |
Baidu-UTS Submission to the EPIC-Kitchens Action Recognition Challenge 2019
| Title | Baidu-UTS Submission to the EPIC-Kitchens Action Recognition Challenge 2019 |
| Authors | Xiaohan Wang, Yu Wu, Linchao Zhu, Yi Yang |
| Abstract | In this report, we present the Baidu-UTS submission to the EPIC-Kitchens Action Recognition Challenge in CVPR 2019. This is the winning solution to this challenge. In this task, the goal is to predict verbs, nouns, and actions from the vocabulary for each video segment. The EPIC-Kitchens dataset contains various small objects, intense motion blur, and occlusions. It is challenging to locate and recognize the object that an actor interacts with. To address these problems, we utilize object detection features to guide the training of 3D Convolutional Neural Networks (CNN), which can significantly improve the accuracy of noun prediction. Specifically, we introduce a Gated Feature Aggregator module to learn from the clip feature and the object feature. This module can strengthen the interaction between the two kinds of activations and avoid gradient exploding. Experimental results demonstrate our approach outperforms other methods on both seen and unseen test set. |
| Tasks | Object Detection |
| Published | 2019-06-22 |
| URL | https://arxiv.org/abs/1906.09383v1 |
| https://arxiv.org/pdf/1906.09383v1.pdf | |
| PWC | https://paperswithcode.com/paper/baidu-uts-submission-to-the-epic-kitchens |
| Repo | |
| Framework | |
Simultaneous Detection of Multiple Appliances from Smart-meter Measurements via Multi-Label Consistent Deep Dictionary Learning and Deep Transform Learning
| Title | Simultaneous Detection of Multiple Appliances from Smart-meter Measurements via Multi-Label Consistent Deep Dictionary Learning and Deep Transform Learning |
| Authors | Vanika Singhal, Jyoti Maggu, Angshul Majumdar |
| Abstract | Currently there are several well-known approaches to non-intrusive appliance load monitoring rule based, stochastic finite state machines, neural networks and sparse coding. Recently several studies have proposed a new approach based on multi label classification. Different appliances are treated as separate classes, and the task is to identify the classes given the aggregate smart-meter reading. Prior studies in this area have used off the shelf algorithms like MLKNN and RAKEL to address this problem. In this work, we propose a deep learning based technique. There are hardly any studies in deep learning based multi label classification; two new deep learning techniques to solve the said problem are fundamental contributions of this work. These are deep dictionary learning and deep transform learning. Thorough experimental results on benchmark datasets show marked improvement over existing studies. |
| Tasks | Dictionary Learning, Multi-Label Classification |
| Published | 2019-12-11 |
| URL | https://arxiv.org/abs/1912.07568v1 |
| https://arxiv.org/pdf/1912.07568v1.pdf | |
| PWC | https://paperswithcode.com/paper/simultaneous-detection-of-multiple-appliances |
| Repo | |
| Framework | |
Re-Weighted $\ell_1$ Algorithms within the Lagrange Duality Framework: Bringing Interpretability to Weights
| Title | Re-Weighted $\ell_1$ Algorithms within the Lagrange Duality Framework: Bringing Interpretability to Weights |
| Authors | Matías Valdés, Marcelo Fiori |
| Abstract | We consider an important problem in signal processing, which consists in finding the sparsest solution of a linear system $\Phi x=b$. This problem has applications in several areas, but is NP-hard in general. Usually an alternative convex problem is considered, based on minimizing the (weighted) $\ell_{1}$ norm. For this alternative to be useful, weights should be chosen as to obtain a solution of the original NP-hard problem. A well known algorithm for this is the Re-Weighted $\ell_{1}$, proposed by Cand`es, Wakin and Boyd. In this article we introduce a new methodology for updating the weights of a Re-Weighted $\ell_{1}$ algorithm, based on identifying these weights as Lagrange multipliers. This is then translated into an algorithm with performance comparable to the usual methodology, but allowing an interpretation of the weights as Lagrange multipliers. The methodology may also be used for a noisy linear system, obtaining in this case a Re-Weighted LASSO algorithm, with a promising performance according to the experimental results. |
| Tasks | |
| Published | 2019-06-21 |
| URL | https://arxiv.org/abs/1906.09329v1 |
| https://arxiv.org/pdf/1906.09329v1.pdf | |
| PWC | https://paperswithcode.com/paper/re-weighted-ell_1-algorithms-within-the |
| Repo | |
| Framework | |
Density estimation in representation space to predict model uncertainty
| Title | Density estimation in representation space to predict model uncertainty |
| Authors | Tiago Ramalho, Miguel Miranda |
| Abstract | Deep learning models frequently make incorrect predictions with high confidence when presented with test examples that are not well represented in their training dataset. We propose a novel and straightforward approach to estimate prediction uncertainty in a pre-trained neural network model. Our method estimates the training data density in representation space for a novel input. A neural network model then uses this information to determine whether we expect the pre-trained model to make a correct prediction. This uncertainty model is trained by predicting in-distribution errors, but can detect out-of-distribution data without having seen any such example. We test our method for a state-of-the art image classification model in the settings of both in-distribution uncertainty estimation as well as out-of-distribution detection. |
| Tasks | Density Estimation, Image Classification, Out-of-Distribution Detection |
| Published | 2019-08-20 |
| URL | https://arxiv.org/abs/1908.07235v2 |
| https://arxiv.org/pdf/1908.07235v2.pdf | |
| PWC | https://paperswithcode.com/paper/density-estimation-in-representation-space-to |
| Repo | |
| Framework | |
Filling Gender & Number Gaps in Neural Machine Translation with Black-box Context Injection
| Title | Filling Gender & Number Gaps in Neural Machine Translation with Black-box Context Injection |
| Authors | Amit Moryossef, Roee Aharoni, Yoav Goldberg |
| Abstract | When translating from a language that does not morphologically mark information such as gender and number into a language that does, translation systems must “guess” this missing information, often leading to incorrect translations in the given context. We propose a black-box approach for injecting the missing information to a pre-trained neural machine translation system, allowing to control the morphological variations in the generated translations without changing the underlying model or training data. We evaluate our method on an English to Hebrew translation task, and show that it is effective in injecting the gender and number information and that supplying the correct information improves the translation accuracy in up to 2.3 BLEU on a female-speaker test set for a state-of-the-art online black-box system. Finally, we perform a fine-grained syntactic analysis of the generated translations that shows the effectiveness of our method. |
| Tasks | Machine Translation |
| Published | 2019-03-08 |
| URL | http://arxiv.org/abs/1903.03467v1 |
| http://arxiv.org/pdf/1903.03467v1.pdf | |
| PWC | https://paperswithcode.com/paper/filling-gender-number-gaps-in-neural-machine |
| Repo | |
| Framework | |
BoLTVOS: Box-Level Tracking for Video Object Segmentation
| Title | BoLTVOS: Box-Level Tracking for Video Object Segmentation |
| Authors | Paul Voigtlaender, Jonathon Luiten, Bastian Leibe |
| Abstract | We approach video object segmentation (VOS) by splitting the task into two sub-tasks: bounding box level tracking, followed by bounding box segmentation. Following this paradigm, we present BoLTVOS (Box-Level Tracking for VOS), which consists of an R-CNN detector conditioned on the first-frame bounding box to detect the object of interest, a temporal consistency rescoring algorithm, and a Box2Seg network that converts bounding boxes to segmentation masks. BoLTVOS performs VOS using only the firstframe bounding box without the mask. We evaluate our approach on DAVIS 2017 and YouTube-VOS, and show that it outperforms all methods that do not perform first-frame fine-tuning. We further present BoLTVOS-ft, which learns to segment the object in question using the first-frame mask while it is being tracked, without increasing the runtime. BoLTVOS-ft outperforms PReMVOS, the previously best performing VOS method on DAVIS 2016 and YouTube-VOS, while running up to 45 times faster. Our bounding box tracker also outperforms all previous short-term and longterm trackers on the bounding box level tracking datasets OTB 2015 and LTB35. A newer version of this work can be found at arXiv:1911.12836. |
| Tasks | Semantic Segmentation, Video Object Segmentation, Video Semantic Segmentation |
| Published | 2019-04-09 |
| URL | https://arxiv.org/abs/1904.04552v2 |
| https://arxiv.org/pdf/1904.04552v2.pdf | |
| PWC | https://paperswithcode.com/paper/boltvos-box-level-tracking-for-video-object |
| Repo | |
| Framework | |
Zermelo’s problem: Optimal point-to-point navigation in 2D turbulent flows using Reinforcement Learning
| Title | Zermelo’s problem: Optimal point-to-point navigation in 2D turbulent flows using Reinforcement Learning |
| Authors | Luca Biferale, Fabio Bonaccorso, Michele Buzzicotti, Patricio Clark Di Leoni, Kristian Gustavsson |
| Abstract | To find the path that minimizes the time to navigate between two given points in a fluid flow is known as Zermelo’s problem. Here, we investigate it by using a Reinforcement Learning (RL) approach for the case of a vessel which has a slip velocity with fixed intensity, Vs , but variable direction and navigating in a 2D turbulent sea. We show that an Actor-Critic RL algorithm is able to find quasi-optimal solutions for both time-independent and chaotically evolving flow configurations. For the frozen case, we also compared the results with strategies obtained analytically from continuous Optimal Navigation (ON) protocols. We show that for our application, ON solutions are unstable for the typical duration of the navigation process, and are therefore not useful in practice. On the other hand, RL solutions are much more robust with respect to small changes in the initial conditions and to external noise, even when V s is much smaller than the maximum flow velocity. Furthermore, we show how the RL approach is able to take advantage of the flow properties in order to reach the target, especially when the steering speed is small. |
| Tasks | |
| Published | 2019-07-17 |
| URL | https://arxiv.org/abs/1907.08591v2 |
| https://arxiv.org/pdf/1907.08591v2.pdf | |
| PWC | https://paperswithcode.com/paper/zermelos-problem-optimal-point-to-point |
| Repo | |
| Framework | |
An Optimal Transport Formulation of the Ensemble Kalman Filter
| Title | An Optimal Transport Formulation of the Ensemble Kalman Filter |
| Authors | Amirhossein Taghvaei, Prashant G. Mehta |
| Abstract | Controlled interacting particle systems such as the ensemble Kalman filter (EnKF) and the feedback particle filter (FPF) are numerical algorithms to approximate the solution of the nonlinear filtering problem in continuous time. The distinguishing feature of these algorithms is that the Bayesian update step is implemented using a feedback control law. It has been noted in the literature that the control law is not unique. This is the main problem addressed in this paper. To obtain a unique control law, the filtering problem is formulated here as an optimal transportation problem. An explicit formula for the (mean-field type) optimal control law is derived in the linear Gaussian setting. Comparisons are made with the control laws for different types of EnKF algorithms described in the literature. Via empirical approximation of the mean-field control law, a finite-$N$ controlled interacting particle algorithm is obtained. For this algorithm, the equations for empirical mean and covariance are derived and shown to be identical to the Kalman filter. This allows strong conclusions on convergence and error properties based on the classical filter stability theory for the Kalman filter. It is shown that, under certain technical conditions, the mean squared error (m.s.e.) converges to zero even with a finite number of particles. A detailed propagation of chaos analysis is carried out for the finite-$N$ algorithm. The analysis is used to prove weak convergence of the empirical distribution as $N\rightarrow\infty$. For a certain simplified filtering problem, analytical comparison of the m.s.e. with the importance sampling-based algorithms is described. The analysis helps explain the favorable scaling properties of the control-based algorithms reported in several numerical studies in recent literature. |
| Tasks | |
| Published | 2019-10-05 |
| URL | https://arxiv.org/abs/1910.02338v1 |
| https://arxiv.org/pdf/1910.02338v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-optimal-transport-formulation-of-the |
| Repo | |
| Framework | |
Analysis of Evolutionary Behavior in Self-Learning Media Search Engines
| Title | Analysis of Evolutionary Behavior in Self-Learning Media Search Engines |
| Authors | Nikki Lijing Kuang, Clement H. C. Leung |
| Abstract | The diversity of intrinsic qualities of multimedia entities tends to impede their effective retrieval. In a SelfLearning Search Engine architecture, the subtle nuances of human perceptions and deep knowledge are taught and captured through unsupervised reinforcement learning, where the degree of reinforcement may be suitably calibrated. Such architectural paradigm enables indexes to evolve naturally while accommodating the dynamic changes of user interests. It operates by continuously constructing indexes over time, while injecting progressive improvement in search performance. For search operations to be effective, convergence of index learning is of crucial importance to ensure efficiency and robustness. In this paper, we develop a Self-Learning Search Engine architecture based on reinforcement learning using a Markov Decision Process framework. The balance between exploration and exploitation is achieved through evolutionary exploration Strategies. The evolutionary index learning behavior is then studied and formulated using stochastic analysis. Experimental results are presented which corroborate the steady convergence of the index evolution mechanism. Index Term |
| Tasks | |
| Published | 2019-11-22 |
| URL | https://arxiv.org/abs/1911.09882v1 |
| https://arxiv.org/pdf/1911.09882v1.pdf | |
| PWC | https://paperswithcode.com/paper/analysis-of-evolutionary-behavior-in-self |
| Repo | |
| Framework | |
Bayesian Network Based Risk and Sensitivity Analysis for Production Process Stability Control
| Title | Bayesian Network Based Risk and Sensitivity Analysis for Production Process Stability Control |
| Authors | Wei Xie, Bo Wang, Cheng Li, Jared Auclair, Peter Baker |
| Abstract | The biomanufacturing industry is growing rapidly and becoming one of the key drivers of personalized medicine and life science. However, biopharmaceutical production faces critical challenges, including complexity, high variability, long lead time and rapid changes in technologies, processes, and regulatory environment. Driven by these challenges, we explore the bio-technology domain knowledge and propose a rigorous risk and sensitivity analysis framework for biomanufacturing innovation. Built on the causal relationships of raw material quality attributes, production process, and bio-drug properties in safety and efficacy, we develop a Bayesian Network (BN) to model the complex probabilistic interdependence between process parameters and quality attributes of raw materials/in-process materials/drug substance. It integrates various sources of data and leads to an interpretable probabilistic knowledge graph of the end-to-end production process. Then, we introduce a systematic risk analysis to assess the criticality of process parameters and quality attributes. The complex production processes often involve many process parameters and quality attributes impacting the product quality variability. However, the real-world (batch) data are often limited, especially for customized and personalized bio-drugs. We propose uncertainty quantification and sensitivity analysis to analyze the impact of model risk. Given very limited process data, the empirical results show that we can provide reliable and interpretable risk and sensitivity analysis. Thus, the proposed framework can provide the science- and risk-based guidance on the process monitoring, data collection, and process parameters specifications to facilitate the production process learning and stability control. |
| Tasks | |
| Published | 2019-09-10 |
| URL | https://arxiv.org/abs/1909.04261v1 |
| https://arxiv.org/pdf/1909.04261v1.pdf | |
| PWC | https://paperswithcode.com/paper/bayesian-network-based-risk-and-sensitivity |
| Repo | |
| Framework | |
