Paper Group ANR 352
Computationally and statistically efficient learning of causal Bayes nets using path queries. Sky detection and log illumination refinement for PDE-based hazy image contrast enhancement. Planar Object Tracking in the Wild: A Benchmark. X-View: Graph-Based Semantic Multi-View Localization. LSTM Networks for Data-Aware Remaining Time Prediction of Bu …
Computationally and statistically efficient learning of causal Bayes nets using path queries
| Title | Computationally and statistically efficient learning of causal Bayes nets using path queries |
| Authors | Kevin Bello, Jean Honorio |
| Abstract | Causal discovery from empirical data is a fundamental problem in many scientific domains. Observational data allows for identifiability only up to Markov equivalence class. In this paper we first propose a polynomial time algorithm for learning the exact correctly-oriented structure of the transitive reduction of any causal Bayesian network with high probability, by using interventional path queries. Each path query takes as input an origin node and a target node, and answers whether there is a directed path from the origin to the target. This is done by intervening on the origin node and observing samples from the target node. We theoretically show the logarithmic sample complexity for the size of interventional data per path query, for continuous and discrete networks. We then show how to learn the transitive edges using also logarithmic sample complexity (albeit in time exponential in the maximum number of parents for discrete networks), which allows us to learn the full network. We further extend our work by reducing the number of interventional path queries for learning rooted trees. We also provide an analysis of imperfect interventions. |
| Tasks | Causal Discovery |
| Published | 2017-06-02 |
| URL | https://arxiv.org/abs/1706.00754v4 |
| https://arxiv.org/pdf/1706.00754v4.pdf | |
| PWC | https://paperswithcode.com/paper/learning-causal-bayes-networks-using |
| Repo | |
| Framework | |
Sky detection and log illumination refinement for PDE-based hazy image contrast enhancement
| Title | Sky detection and log illumination refinement for PDE-based hazy image contrast enhancement |
| Authors | Uche A. Nnolim |
| Abstract | This report presents the results of a sky detection technique used to improve the performance of a previously developed partial differential equation (PDE)-based hazy image enhancement algorithm. Additionally, a proposed alternative method utilizes a function for log illumination refinement to improve de-hazing results while avoiding over-enhancement of sky or homogeneous regions. The algorithms were tested with several benchmark and calibration images and compared with several standard algorithms from the literature. Results indicate that the algorithms yield mostly consistent results and surpasses several of the other algorithms in terms of colour and contrast enhancement in addition to improved edge visibility. |
| Tasks | Calibration, Image Enhancement |
| Published | 2017-12-28 |
| URL | http://arxiv.org/abs/1712.09775v2 |
| http://arxiv.org/pdf/1712.09775v2.pdf | |
| PWC | https://paperswithcode.com/paper/sky-detection-and-log-illumination-refinement |
| Repo | |
| Framework | |
Planar Object Tracking in the Wild: A Benchmark
| Title | Planar Object Tracking in the Wild: A Benchmark |
| Authors | Pengpeng Liang, Yifan Wu, Hu Lu, Liming Wang, Chunyuan Liao, Haibin Ling |
| Abstract | Planar object tracking is an actively studied problem in vision-based robotic applications. While several benchmarks have been constructed for evaluating state-of-the-art algorithms, there is a lack of video sequences captured in the wild rather than in constrained laboratory environment. In this paper, we present a carefully designed planar object tracking benchmark containing 210 videos of 30 planar objects sampled in the natural environment. In particular, for each object, we shoot seven videos involving various challenging factors, namely scale change, rotation, perspective distortion, motion blur, occlusion, out-of-view, and unconstrained. The ground truth is carefully annotated semi-manually to ensure the quality. Moreover, eleven state-of-the-art algorithms are evaluated on the benchmark using two evaluation metrics, with detailed analysis provided for the evaluation results. We expect the proposed benchmark to benefit future studies on planar object tracking. |
| Tasks | Object Tracking |
| Published | 2017-03-23 |
| URL | http://arxiv.org/abs/1703.07938v2 |
| http://arxiv.org/pdf/1703.07938v2.pdf | |
| PWC | https://paperswithcode.com/paper/planar-object-tracking-in-the-wild-a |
| Repo | |
| Framework | |
X-View: Graph-Based Semantic Multi-View Localization
| Title | X-View: Graph-Based Semantic Multi-View Localization |
| Authors | Abel Gawel, Carlo Del Don, Roland Siegwart, Juan Nieto, Cesar Cadena |
| Abstract | Global registration of multi-view robot data is a challenging task. Appearance-based global localization approaches often fail under drastic view-point changes, as representations have limited view-point invariance. This work is based on the idea that human-made environments contain rich semantics which can be used to disambiguate global localization. Here, we present X-View, a Multi-View Semantic Global Localization system. X-View leverages semantic graph descriptor matching for global localization, enabling localization under drastically different view-points. While the approach is general in terms of the semantic input data, we present and evaluate an implementation on visual data. We demonstrate the system in experiments on the publicly available SYNTHIA dataset, on a realistic urban dataset recorded with a simulator, and on real-world StreetView data. Our findings show that X-View is able to globally localize aerial-to-ground, and ground-to-ground robot data of drastically different view-points. Our approach achieves an accuracy of up to 85 % on global localizations in the multi-view case, while the benchmarked baseline appearance-based methods reach up to 75 %. |
| Tasks | |
| Published | 2017-09-28 |
| URL | http://arxiv.org/abs/1709.09905v3 |
| http://arxiv.org/pdf/1709.09905v3.pdf | |
| PWC | https://paperswithcode.com/paper/x-view-graph-based-semantic-multi-view |
| Repo | |
| Framework | |
LSTM Networks for Data-Aware Remaining Time Prediction of Business Process Instances
| Title | LSTM Networks for Data-Aware Remaining Time Prediction of Business Process Instances |
| Authors | Nicolò Navarin, Beatrice Vincenzi, Mirko Polato, Alessandro Sperduti |
| Abstract | Predicting the completion time of business process instances would be a very helpful aid when managing processes under service level agreement constraints. The ability to know in advance the trend of running process instances would allow business managers to react in time, in order to prevent delays or undesirable situations. However, making such accurate forecasts is not easy: many factors may influence the required time to complete a process instance. In this paper, we propose an approach based on deep Recurrent Neural Networks (specifically LSTMs) that is able to exploit arbitrary information associated to single events, in order to produce an as-accurate-as-possible prediction of the completion time of running instances. Experiments on real-world datasets confirm the quality of our proposal. |
| Tasks | |
| Published | 2017-11-10 |
| URL | http://arxiv.org/abs/1711.03822v1 |
| http://arxiv.org/pdf/1711.03822v1.pdf | |
| PWC | https://paperswithcode.com/paper/lstm-networks-for-data-aware-remaining-time |
| Repo | |
| Framework | |
Graphical Models: An Extension to Random Graphs, Trees, and Other Objects
| Title | Graphical Models: An Extension to Random Graphs, Trees, and Other Objects |
| Authors | Neil Hallonquist |
| Abstract | In this work, we consider an extension of graphical models to random graphs, trees, and other objects. To do this, many fundamental concepts for multivariate random variables (e.g., marginal variables, Gibbs distribution, Markov properties) must be extended to other mathematical objects; it turns out that this extension is possible, as we will discuss, if we have a consistent, complete system of projections on a given object. Each projection defines a marginal random variable, allowing one to specify independence assumptions between them. Furthermore, these independencies can be specified in terms of a small subset of these marginal variables (which we call the atomic variables), allowing the compact representation of independencies by a directed graph. Projections also define factors, functions on the projected object space, and hence a projection family defines a set of possible factorizations for a distribution; these can be compactly represented by an undirected graph. The invariances used in graphical models are essential for learning distributions, not just on multivariate random variables, but also on other objects. When they are applied to random graphs and random trees, the result is a general class of models that is applicable to a broad range of problems, including those in which the graphs and trees have complicated edge structures. These models need not be conditioned on a fixed number of vertices, as is often the case in the literature for random graphs, and can be used for problems in which attributes are associated with vertices and edges. For graphs, applications include the modeling of molecules, neural networks, and relational real-world scenes; for trees, applications include the modeling of infectious diseases, cell fusion, the structure of language, and the structure of objects in visual scenes. Many classic models are particular instances of this framework. |
| Tasks | |
| Published | 2017-04-14 |
| URL | http://arxiv.org/abs/1704.04478v2 |
| http://arxiv.org/pdf/1704.04478v2.pdf | |
| PWC | https://paperswithcode.com/paper/graphical-models-an-extension-to-random |
| Repo | |
| Framework | |
Differential Generative Adversarial Networks: Synthesizing Non-linear Facial Variations with Limited Number of Training Data
| Title | Differential Generative Adversarial Networks: Synthesizing Non-linear Facial Variations with Limited Number of Training Data |
| Authors | Geonmo Gu, Seong Tae Kim, Kihyun Kim, Wissam J. Baddar, Yong Man Ro |
| Abstract | In face-related applications with a public available dataset, synthesizing non-linear facial variations (e.g., facial expression, head-pose, illumination, etc.) through a generative model is helpful in addressing the lack of training data. In reality, however, there is insufficient data to even train the generative model for face synthesis. In this paper, we propose Differential Generative Adversarial Networks (D-GAN) that can perform photo-realistic face synthesis even when training data is small. Two discriminators are devised to ensure the generator to approximate a face manifold, which can express face changes as it wants. Experimental results demonstrate that the proposed method is robust to the amount of training data and synthesized images are useful to improve the performance of a face expression classifier. |
| Tasks | Face Generation |
| Published | 2017-11-28 |
| URL | http://arxiv.org/abs/1711.10267v4 |
| http://arxiv.org/pdf/1711.10267v4.pdf | |
| PWC | https://paperswithcode.com/paper/differential-generative-adversarial-networks |
| Repo | |
| Framework | |
DesnowNet: Context-Aware Deep Network for Snow Removal
| Title | DesnowNet: Context-Aware Deep Network for Snow Removal |
| Authors | Yun-Fu Liu, Da-Wei Jaw, Shih-Chia Huang, Jenq-Neng Hwang |
| Abstract | Existing learning-based atmospheric particle-removal approaches such as those used for rainy and hazy images are designed with strong assumptions regarding spatial frequency, trajectory, and translucency. However, the removal of snow particles is more complicated because it possess the additional attributes of particle size and shape, and these attributes may vary within a single image. Currently, hand-crafted features are still the mainstream for snow removal, making significant generalization difficult to achieve. In response, we have designed a multistage network codenamed DesnowNet to in turn deal with the removal of translucent and opaque snow particles. We also differentiate snow into attributes of translucency and chromatic aberration for accurate estimation. Moreover, our approach individually estimates residual complements of the snow-free images to recover details obscured by opaque snow. Additionally, a multi-scale design is utilized throughout the entire network to model the diversity of snow. As demonstrated in experimental results, our approach outperforms state-of-the-art learning-based atmospheric phenomena removal methods and one semantic segmentation baseline on the proposed Snow100K dataset in both qualitative and quantitative comparisons. The results indicate our network would benefit applications involving computer vision and graphics. |
| Tasks | Semantic Segmentation |
| Published | 2017-08-15 |
| URL | http://arxiv.org/abs/1708.04512v1 |
| http://arxiv.org/pdf/1708.04512v1.pdf | |
| PWC | https://paperswithcode.com/paper/desnownet-context-aware-deep-network-for-snow |
| Repo | |
| Framework | |
Just an Update on PMING Distance for Web-based Semantic Similarity in Artificial Intelligence and Data Mining
| Title | Just an Update on PMING Distance for Web-based Semantic Similarity in Artificial Intelligence and Data Mining |
| Authors | Valentina Franzoni |
| Abstract | One of the main problems that emerges in the classic approach to semantics is the difficulty in acquisition and maintenance of ontologies and semantic annotations. On the other hand, the Internet explosion and the massive diffusion of mobile smart devices lead to the creation of a worldwide system, which information is daily checked and fueled by the contribution of millions of users who interacts in a collaborative way. Search engines, continually exploring the Web, are a natural source of information on which to base a modern approach to semantic annotation. A promising idea is that it is possible to generalize the semantic similarity, under the assumption that semantically similar terms behave similarly, and define collaborative proximity measures based on the indexing information returned by search engines. The PMING Distance is a proximity measure used in data mining and information retrieval, which collaborative information express the degree of relationship between two terms, using only the number of documents returned as result for a query on a search engine. In this work, the PMINIG Distance is updated, providing a novel formal algebraic definition, which corrects previous works. The novel point of view underlines the features of the PMING to be a locally normalized linear combination of the Pointwise Mutual Information and Normalized Google Distance. The analyzed measure dynamically reflects the collaborative change made on the web resources. |
| Tasks | Information Retrieval, Semantic Similarity, Semantic Textual Similarity |
| Published | 2017-01-09 |
| URL | http://arxiv.org/abs/1701.02163v1 |
| http://arxiv.org/pdf/1701.02163v1.pdf | |
| PWC | https://paperswithcode.com/paper/just-an-update-on-pming-distance-for-web |
| Repo | |
| Framework | |
An Improved Residual LSTM Architecture for Acoustic Modeling
| Title | An Improved Residual LSTM Architecture for Acoustic Modeling |
| Authors | Lu Huang, Jiasong Sun, Ji Xu, Yi Yang |
| Abstract | Long Short-Term Memory (LSTM) is the primary recurrent neural networks architecture for acoustic modeling in automatic speech recognition systems. Residual learning is an efficient method to help neural networks converge easier and faster. In this paper, we propose several types of residual LSTM methods for our acoustic modeling. Our experiments indicate that, compared with classic LSTM, our architecture shows more than 8% relative reduction in Phone Error Rate (PER) on TIMIT tasks. At the same time, our residual fast LSTM approach shows 4% relative reduction in PER on the same task. Besides, we find that all this architecture could have good results on THCHS-30, Librispeech and Switchboard corpora. |
| Tasks | Speech Recognition |
| Published | 2017-08-17 |
| URL | http://arxiv.org/abs/1708.05682v1 |
| http://arxiv.org/pdf/1708.05682v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-improved-residual-lstm-architecture-for |
| Repo | |
| Framework | |
Combinatorial Semi-Bandits with Knapsacks
| Title | Combinatorial Semi-Bandits with Knapsacks |
| Authors | Karthik Abinav Sankararaman, Aleksandrs Slivkins |
| Abstract | We unify two prominent lines of work on multi-armed bandits: bandits with knapsacks (BwK) and combinatorial semi-bandits. The former concerns limited “resources” consumed by the algorithm, e.g., limited supply in dynamic pricing. The latter allows a huge number of actions but assumes combinatorial structure and additional feedback to make the problem tractable. We define a common generalization, support it with several motivating examples, and design an algorithm for it. Our regret bounds are comparable with those for BwK and combinatorial semi- bandits. |
| Tasks | Multi-Armed Bandits |
| Published | 2017-05-23 |
| URL | http://arxiv.org/abs/1705.08110v3 |
| http://arxiv.org/pdf/1705.08110v3.pdf | |
| PWC | https://paperswithcode.com/paper/combinatorial-semi-bandits-with-knapsacks |
| Repo | |
| Framework | |
Semantic Evolutionary Concept Distances for Effective Information Retrieval in Query Expansion
| Title | Semantic Evolutionary Concept Distances for Effective Information Retrieval in Query Expansion |
| Authors | Valentina Franzoni, Yuanxi Li, Clement H. C. Leung, Alfredo Milani |
| Abstract | In this work several semantic approaches to concept-based query expansion and reranking schemes are studied and compared with different ontology-based expansion methods in web document search and retrieval. In particular, we focus on concept-based query expansion schemes, where, in order to effectively increase the precision of web document retrieval and to decrease the users browsing time, the main goal is to quickly provide users with the most suitable query expansion. Two key tasks for query expansion in web document retrieval are to find the expansion candidates, as the closest concepts in web document domain, and to rank the expanded queries properly. The approach we propose aims at improving the expansion phase for better web document retrieval and precision. The basic idea is to measure the distance between candidate concepts using the PMING distance, a collaborative semantic proximity measure, i.e. a measure which can be computed by using statistical results from web search engine. Experiments show that the proposed technique can provide users with more satisfying expansion results and improve the quality of web document retrieval. |
| Tasks | Information Retrieval |
| Published | 2017-01-19 |
| URL | http://arxiv.org/abs/1701.05311v1 |
| http://arxiv.org/pdf/1701.05311v1.pdf | |
| PWC | https://paperswithcode.com/paper/semantic-evolutionary-concept-distances-for |
| Repo | |
| Framework | |
Human Uncertainty and Ranking Error – The Secret of Successful Evaluation in Predictive Data Mining
| Title | Human Uncertainty and Ranking Error – The Secret of Successful Evaluation in Predictive Data Mining |
| Authors | Kevin Jasberg, Sergej Sizov |
| Abstract | One of the most crucial issues in data mining is to model human behaviour in order to provide personalisation, adaptation and recommendation. This usually involves implicit or explicit knowledge, either by observing user interactions, or by asking users directly. But these sources of information are always subject to the volatility of human decisions, making utilised data uncertain to a particular extent. In this contribution, we elaborate on the impact of this human uncertainty when it comes to comparative assessments of different data mining approaches. In particular, we reveal two problems: (1) biasing effects on various metrics of model-based prediction and (2) the propagation of uncertainty and its thus induced error probabilities for algorithm rankings. For this purpose, we introduce a probabilistic view and prove the existence of those problems mathematically, as well as provide possible solution strategies. We exemplify our theory mainly in the context of recommender systems along with the metric RMSE as a prominent example of precision quality measures. |
| Tasks | Recommendation Systems |
| Published | 2017-08-17 |
| URL | http://arxiv.org/abs/1708.05688v1 |
| http://arxiv.org/pdf/1708.05688v1.pdf | |
| PWC | https://paperswithcode.com/paper/human-uncertainty-and-ranking-error-the |
| Repo | |
| Framework | |
Single image super-resolution using self-optimizing mask via fractional-order gradient interpolation and reconstruction
| Title | Single image super-resolution using self-optimizing mask via fractional-order gradient interpolation and reconstruction |
| Authors | Qi Yang, Yanzhu Zhang, Tiebiao Zhao, YangQuan Chen |
| Abstract | Image super-resolution using self-optimizing mask via fractional-order gradient interpolation and reconstruction aims to recover detailed information from low-resolution images and reconstruct them into high-resolution images. Due to the limited amount of data and information retrieved from low-resolution images, it is difficult to restore clear, artifact-free images, while still preserving enough structure of the image such as the texture. This paper presents a new single image super-resolution method which is based on adaptive fractional-order gradient interpolation and reconstruction. The interpolated image gradient via optimal fractional-order gradient is first constructed according to the image similarity and afterwards the minimum energy function is employed to reconstruct the final high-resolution image. Fractional-order gradient based interpolation methods provide an additional degree of freedom which helps optimize the implementation quality due to the fact that an extra free parameter $\alpha$-order is being used. The proposed method is able to produce a rich texture detail while still being able to maintain structural similarity even under large zoom conditions. Experimental results show that the proposed method performs better than current single image super-resolution techniques. |
| Tasks | Image Super-Resolution, Super-Resolution |
| Published | 2017-03-18 |
| URL | http://arxiv.org/abs/1703.06260v1 |
| http://arxiv.org/pdf/1703.06260v1.pdf | |
| PWC | https://paperswithcode.com/paper/single-image-super-resolution-using-self |
| Repo | |
| Framework | |
Linear Stochastic Approximation: Constant Step-Size and Iterate Averaging
| Title | Linear Stochastic Approximation: Constant Step-Size and Iterate Averaging |
| Authors | Chandrashekar Lakshminarayanan, Csaba Szepesvári |
| Abstract | We consider $d$-dimensional linear stochastic approximation algorithms (LSAs) with a constant step-size and the so called Polyak-Ruppert (PR) averaging of iterates. LSAs are widely applied in machine learning and reinforcement learning (RL), where the aim is to compute an appropriate $\theta_{*} \in \mathbb{R}^d$ (that is an optimum or a fixed point) using noisy data and $O(d)$ updates per iteration. In this paper, we are motivated by the problem (in RL) of policy evaluation from experience replay using the \emph{temporal difference} (TD) class of learning algorithms that are also LSAs. For LSAs with a constant step-size, and PR averaging, we provide bounds for the mean squared error (MSE) after $t$ iterations. We assume that data is \iid with finite variance (underlying distribution being $P$) and that the expected dynamics is Hurwitz. For a given LSA with PR averaging, and data distribution $P$ satisfying the said assumptions, we show that there exists a range of constant step-sizes such that its MSE decays as $O(\frac{1}{t})$. We examine the conditions under which a constant step-size can be chosen uniformly for a class of data distributions $\mathcal{P}$, and show that not all data distributions `admit’ such a uniform constant step-size. We also suggest a heuristic step-size tuning algorithm to choose a constant step-size of a given LSA for a given data distribution $P$. We compare our results with related work and also discuss the implication of our results in the context of TD algorithms that are LSAs. | |
| Tasks | |
| Published | 2017-09-12 |
| URL | http://arxiv.org/abs/1709.04073v1 |
| http://arxiv.org/pdf/1709.04073v1.pdf | |
| PWC | https://paperswithcode.com/paper/linear-stochastic-approximation-constant-step |
| Repo | |
| Framework | |
