Paper Group ANR 60
![Paper Group ANR 60](/2018/images/pwc/paper-arxiv_hu144ec288a26b3e360d673e256787de3e_28623_900x500_fit_q75_box.jpg)
A Learning-Based Visual Saliency Fusion Model for High Dynamic Range Video (LBVS-HDR). A Bayesian Approach for Inferring Local Causal Structure in Gene Regulatory Networks. Automatically Designing CNN Architectures for Medical Image Segmentation. Exact and Robust Conformal Inference Methods for Predictive Machine Learning With Dependent Data. A Cla …
A Learning-Based Visual Saliency Fusion Model for High Dynamic Range Video (LBVS-HDR)
Title | A Learning-Based Visual Saliency Fusion Model for High Dynamic Range Video (LBVS-HDR) |
Authors | Amin Banitalebi-Dehkordi, Yuanyuan Dong, Mahsa T. Pourazad, Panos Nasiopoulos |
Abstract | Saliency prediction for Standard Dynamic Range (SDR) videos has been well explored in the last decade. However, limited studies are available on High Dynamic Range (HDR) Visual Attention Models (VAMs). Considering that the characteristic of HDR content in terms of dynamic range and color gamut is quite different than those of SDR content, it is essential to identify the importance of different saliency attributes of HDR videos for designing a VAM and understand how to combine these features. To this end we propose a learning-based visual saliency fusion method for HDR content (LVBS-HDR) to combine various visual saliency features. In our approach various conspicuity maps are extracted from HDR data, and then for fusing conspicuity maps, a Random Forests algorithm is used to train a model based on the collected data from an eye-tracking experiment. Performance evaluations demonstrate the superiority of the proposed fusion method against other existing fusion methods. |
Tasks | Eye Tracking, Saliency Prediction |
Published | 2018-03-13 |
URL | http://arxiv.org/abs/1803.04827v1 |
http://arxiv.org/pdf/1803.04827v1.pdf | |
PWC | https://paperswithcode.com/paper/a-learning-based-visual-saliency-fusion-model |
Repo | |
Framework | |
A Bayesian Approach for Inferring Local Causal Structure in Gene Regulatory Networks
Title | A Bayesian Approach for Inferring Local Causal Structure in Gene Regulatory Networks |
Authors | Ioan Gabriel Bucur, Tom van Bussel, Tom Claassen, Tom Heskes |
Abstract | Gene regulatory networks play a crucial role in controlling an organism’s biological processes, which is why there is significant interest in developing computational methods that are able to extract their structure from high-throughput genetic data. A typical approach consists of a series of conditional independence tests on the covariance structure meant to progressively reduce the space of possible causal models. We propose a novel efficient Bayesian method for discovering the local causal relationships among triplets of (normally distributed) variables. In our approach, we score the patterns in the covariance matrix in one go and we incorporate the available background knowledge in the form of priors over causal structures. Our method is flexible in the sense that it allows for different types of causal structures and assumptions. We apply the approach to the task of inferring gene regulatory networks by learning regulatory relationships between gene expression levels. We show that our algorithm produces stable and conservative posterior probability estimates over local causal structures that can be used to derive an honest ranking of the most meaningful regulatory relationships. We demonstrate the stability and efficacy of our method both on simulated data and on real-world data from an experiment on yeast. |
Tasks | |
Published | 2018-09-18 |
URL | http://arxiv.org/abs/1809.06827v1 |
http://arxiv.org/pdf/1809.06827v1.pdf | |
PWC | https://paperswithcode.com/paper/a-bayesian-approach-for-inferring-local |
Repo | |
Framework | |
Automatically Designing CNN Architectures for Medical Image Segmentation
Title | Automatically Designing CNN Architectures for Medical Image Segmentation |
Authors | Aliasghar Mortazi, Ulas Bagci |
Abstract | Deep neural network architectures have traditionally been designed and explored with human expertise in a long-lasting trial-and-error process. This process requires huge amount of time, expertise, and resources. To address this tedious problem, we propose a novel algorithm to optimally find hyperparameters of a deep network architecture automatically. We specifically focus on designing neural architectures for medical image segmentation task. Our proposed method is based on a policy gradient reinforcement learning for which the reward function is assigned a segmentation evaluation utility (i.e., dice index). We show the efficacy of the proposed method with its low computational cost in comparison with the state-of-the-art medical image segmentation networks. We also present a new architecture design, a densely connected encoder-decoder CNN, as a strong baseline architecture to apply the proposed hyperparameter search algorithm. We apply the proposed algorithm to each layer of the baseline architectures. As an application, we train the proposed system on cine cardiac MR images from Automated Cardiac Diagnosis Challenge (ACDC) MICCAI 2017. Starting from a baseline segmentation architecture, the resulting network architecture obtains the state-of-the-art results in accuracy without performing any trial-and-error based architecture design approaches or close supervision of the hyperparameters changes. |
Tasks | Medical Image Segmentation, Semantic Segmentation |
Published | 2018-07-19 |
URL | http://arxiv.org/abs/1807.07663v1 |
http://arxiv.org/pdf/1807.07663v1.pdf | |
PWC | https://paperswithcode.com/paper/automatically-designing-cnn-architectures-for |
Repo | |
Framework | |
Exact and Robust Conformal Inference Methods for Predictive Machine Learning With Dependent Data
Title | Exact and Robust Conformal Inference Methods for Predictive Machine Learning With Dependent Data |
Authors | Victor Chernozhukov, Kaspar Wuthrich, Yinchu Zhu |
Abstract | We extend conformal inference to general settings that allow for time series data. Our proposal is developed as a randomization method and accounts for potential serial dependence by including block structures in the permutation scheme. As a result, the proposed method retains the exact, model-free validity when the data are i.i.d. or more generally exchangeable, similar to usual conformal inference methods. When exchangeability fails, as is the case for common time series data, the proposed approach is approximately valid under weak assumptions on the conformity score. |
Tasks | Time Series |
Published | 2018-02-17 |
URL | http://arxiv.org/abs/1802.06300v3 |
http://arxiv.org/pdf/1802.06300v3.pdf | |
PWC | https://paperswithcode.com/paper/exact-and-robust-conformal-inference-methods |
Repo | |
Framework | |
A Class-Incremental Learning Method Based on One Class Support Vector Machine
Title | A Class-Incremental Learning Method Based on One Class Support Vector Machine |
Authors | Chengfei Yao, Jie Zou, Yanan Luo, Tao Li, Gang Bai |
Abstract | A method based on one class support vector machine (OCSVM) is proposed for class incremental learning. Several OCSVM models divide the input space into several parts. Then, the 1VS1 classifiers are constructed for the confuse part by using the support vectors. During the class incremental learning process, the OCSVM of the new class is trained at first. Then the support vectors of the old classes and the support vectors of the new class are reused to train 1VS1 classifiers for the confuse part. In order to bring more information to the certain support vectors, the support vectors are at the boundary of the distribution of samples as much as possible when the OCSVM is built. Compared with the traditional methods, the proposed method retains the original model and thus reduces memory consumption and training time cost. Various experiments on different datasets also verify the efficiency of the proposed method. |
Tasks | |
Published | 2018-03-01 |
URL | http://arxiv.org/abs/1803.00159v1 |
http://arxiv.org/pdf/1803.00159v1.pdf | |
PWC | https://paperswithcode.com/paper/a-class-incremental-learning-method-based-on |
Repo | |
Framework | |
Learning formation energy of inorganic compounds using matrix variate deep Gaussian process
Title | Learning formation energy of inorganic compounds using matrix variate deep Gaussian process |
Authors | Saket Mishra, Piyush Tagade |
Abstract | Future advancement of engineering applications is dependent on design of novel materials with desired properties. Enormous size of known chemical space necessitates use of automated high throughput screening to search the desired material. The high throughput screening uses quantum chemistry calculations to predict material properties, however, computational complexity of these calculations often imposes prohibitively high cost on the search for desired material. This critical bottleneck is resolved by using deep machine learning to emulate the quantum computations. However, the deep learning algorithms require a large training dataset to ensure an acceptable generalization, which is often unavailable a-priory. In this paper, we propose a deep Gaussian process based approach to develop an emulator for quantum calculations. We further propose a novel molecular descriptor that enables implementation of the proposed approach. As demonstrated in this paper, the proposed approach can be implemented using a small dataset. We demonstrate efficacy of our approach for prediction of formation energy of inorganic molecules. |
Tasks | Formation Energy |
Published | 2018-12-22 |
URL | http://arxiv.org/abs/1901.06016v2 |
http://arxiv.org/pdf/1901.06016v2.pdf | |
PWC | https://paperswithcode.com/paper/learning-formation-energy-of-inorganic |
Repo | |
Framework | |
A Learning Framework for High Precision Industrial Assembly
Title | A Learning Framework for High Precision Industrial Assembly |
Authors | Yongxiang Fan, Jieliang Luo, Masayoshi Tomizuka |
Abstract | Automatic assembly has broad applications in industries. Traditional assembly tasks utilize predefined trajectories or tuned force control parameters, which make the automatic assembly time-consuming, difficult to generalize, and not robust to uncertainties. In this paper, we propose a learning framework for high precision industrial assembly. The framework combines both the supervised learning and the reinforcement learning. The supervised learning utilizes trajectory optimization to provide the initial guidance to the policy, while the reinforcement learning utilizes actor-critic algorithm to establish the evaluation system even the supervisor is not accurate. The proposed learning framework is more efficient compared with the reinforcement learning and achieves better stability performance than the supervised learning. The effectiveness of the method is verified by both the simulation and experiment. |
Tasks | |
Published | 2018-09-23 |
URL | http://arxiv.org/abs/1809.08548v3 |
http://arxiv.org/pdf/1809.08548v3.pdf | |
PWC | https://paperswithcode.com/paper/a-learning-framework-for-high-precision |
Repo | |
Framework | |
Steerable Wavelet Scattering for 3D Atomic Systems with Application to Li-Si Energy Prediction
Title | Steerable Wavelet Scattering for 3D Atomic Systems with Application to Li-Si Energy Prediction |
Authors | Xavier Brumwell, Paul Sinz, Kwang Jin Kim, Yue Qi, Matthew Hirn |
Abstract | A general machine learning architecture is introduced that uses wavelet scattering coefficients of an inputted three dimensional signal as features. Solid harmonic wavelet scattering transforms of three dimensional signals were previously introduced in a machine learning framework for the regression of properties of small organic molecules. Here this approach is extended for general steerable wavelets which are equivariant to translations and rotations, resulting in a sparse model of the target function. The scattering coefficients inherit from the wavelets invariance to translations and rotations. As an illustration of this approach a linear regression model is learned for the formation energy of amorphous lithium-silicon material states trained over a database generated using plane-wave Density Functional Theory methods. State-of-the-art results are produced as compared to other machine learning approaches over similarly generated databases. |
Tasks | Formation Energy |
Published | 2018-11-21 |
URL | http://arxiv.org/abs/1812.02320v2 |
http://arxiv.org/pdf/1812.02320v2.pdf | |
PWC | https://paperswithcode.com/paper/steerable-wavelet-scattering-for-3d-atomic |
Repo | |
Framework | |
Identifying High-Quality Chinese News Comments Based on Multi-Target Text Matching Model
Title | Identifying High-Quality Chinese News Comments Based on Multi-Target Text Matching Model |
Authors | Deli Chen, Shuming Ma, Pengcheng Yang, Xu Sun |
Abstract | With the development of information technology, there is an explosive growth in the number of online comment concerning news, blogs and so on. The massive comments are overloaded, and often contain some misleading and unwelcome information. Therefore, it is necessary to identify high-quality comments and filter out low-quality comments. In this work, we introduce a novel task: high-quality comment identification (HQCI), which aims to automatically assess the quality of online comments. First, we construct a news comment corpus, which consists of news, comments, and the corresponding quality label. Second, we analyze the dataset, and find the quality of comments can be measured in three aspects: informativeness, consistency, and novelty. Finally, we propose a novel multi-target text matching model, which can measure three aspects by referring to the news and surrounding comments. Experimental results show that our method can outperform various baselines by a large margin on the news dataset. |
Tasks | Text Matching |
Published | 2018-08-22 |
URL | http://arxiv.org/abs/1808.07191v1 |
http://arxiv.org/pdf/1808.07191v1.pdf | |
PWC | https://paperswithcode.com/paper/identifying-high-quality-chinese-news |
Repo | |
Framework | |
Deep Architectures and Ensembles for Semantic Video Classification
Title | Deep Architectures and Ensembles for Semantic Video Classification |
Authors | Eng-Jon Ong, Sameed Husain, Mikel Bober-Irizar, Miroslaw Bober |
Abstract | This work addresses the problem of accurate semantic labelling of short videos. To this end, a multitude of different deep nets, ranging from traditional recurrent neural networks (LSTM, GRU), temporal agnostic networks (FV,VLAD,BoW), fully connected neural networks mid-stage AV fusion and others. Additionally, we also propose a residual architecture-based DNN for video classification, with state-of-the art classification performance at significantly reduced complexity. Furthermore, we propose four new approaches to diversity-driven multi-net ensembling, one based on fast correlation measure and three incorporating a DNN-based combiner. We show that significant performance gains can be achieved by ensembling diverse nets and we investigate factors contributing to high diversity. Based on the extensive YouTube8M dataset, we provide an in-depth evaluation and analysis of their behaviour. We show that the performance of the ensemble is state-of-the-art achieving the highest accuracy on the YouTube-8M Kaggle test data. The performance of the ensemble of classifiers was also evaluated on the HMDB51 and UCF101 datasets, and show that the resulting method achieves comparable accuracy with state-of-the-art methods using similar input features. |
Tasks | Video Classification |
Published | 2018-07-03 |
URL | http://arxiv.org/abs/1807.01026v3 |
http://arxiv.org/pdf/1807.01026v3.pdf | |
PWC | https://paperswithcode.com/paper/deep-architectures-and-ensembles-for-semantic |
Repo | |
Framework | |
An ensemble based on a bi-objective evolutionary spectral algorithm for graph clustering
Title | An ensemble based on a bi-objective evolutionary spectral algorithm for graph clustering |
Authors | Camila P. S. Tautenhain, Mariá C. V. Nascimento |
Abstract | Graph clustering is a challenging pattern recognition problem whose goal is to identify vertex partitions with high intra-group connectivity. This paper investigates a bi-objective problem that maximizes the number of intra-cluster edges of a graph and minimizes the expected number of inter-cluster edges in a random graph with the same degree sequence as the original one. The difference between the two investigated objectives is the definition of the well-known measure of graph clustering quality: the modularity. We introduce a spectral decomposition hybridized with an evolutionary heuristic, called MOSpecG, to approach this bi-objective problem and an ensemble strategy to consolidate the solutions found by MOSpecG into a final robust partition. The results of computational experiments with real and artificial LFR networks demonstrated a significant improvement in the results and performance of the introduced method in regard to another bi-objective algorithm found in the literature. The crossover operator based on the geometric interpretation of the modularity maximization problem to match the communities of a pair of individuals was of utmost importance for the good performance of MOSpecG. Hybridizing spectral graph theory and intelligent systems allowed us to define significantly high-quality community structures. |
Tasks | Graph Clustering |
Published | 2018-10-08 |
URL | https://arxiv.org/abs/1810.03652v2 |
https://arxiv.org/pdf/1810.03652v2.pdf | |
PWC | https://paperswithcode.com/paper/an-ensemble-based-on-a-bi-objective |
Repo | |
Framework | |
Learning latent variable structured prediction models with Gaussian perturbations
Title | Learning latent variable structured prediction models with Gaussian perturbations |
Authors | Kevin Bello, Jean Honorio |
Abstract | The standard margin-based structured prediction commonly uses a maximum loss over all possible structured outputs. The large-margin formulation including latent variables not only results in a non-convex formulation but also increases the search space by a factor of the size of the latent space. Recent work has proposed the use of the maximum loss over random structured outputs sampled independently from some proposal distribution, with theoretical guarantees. We extend this work by including latent variables. We study a new family of loss functions under Gaussian perturbations and analyze the effect of the latent space on the generalization bounds. We show that the non-convexity of learning with latent variables originates naturally, as it relates to a tight upper bound of the Gibbs decoder distortion with respect to the latent space. Finally, we provide a formulation using random samples that produces a tighter upper bound of the Gibbs decoder distortion up to a statistical accuracy, which enables a faster evaluation of the objective function. We illustrate the method with synthetic experiments and a computer vision application. |
Tasks | Structured Prediction |
Published | 2018-05-23 |
URL | http://arxiv.org/abs/1805.09213v1 |
http://arxiv.org/pdf/1805.09213v1.pdf | |
PWC | https://paperswithcode.com/paper/learning-latent-variable-structured |
Repo | |
Framework | |
Gaussian Processes and Kernel Methods: A Review on Connections and Equivalences
Title | Gaussian Processes and Kernel Methods: A Review on Connections and Equivalences |
Authors | Motonobu Kanagawa, Philipp Hennig, Dino Sejdinovic, Bharath K Sriperumbudur |
Abstract | This paper is an attempt to bridge the conceptual gaps between researchers working on the two widely used approaches based on positive definite kernels: Bayesian learning or inference using Gaussian processes on the one side, and frequentist kernel methods based on reproducing kernel Hilbert spaces on the other. It is widely known in machine learning that these two formalisms are closely related; for instance, the estimator of kernel ridge regression is identical to the posterior mean of Gaussian process regression. However, they have been studied and developed almost independently by two essentially separate communities, and this makes it difficult to seamlessly transfer results between them. Our aim is to overcome this potential difficulty. To this end, we review several old and new results and concepts from either side, and juxtapose algorithmic quantities from each framework to highlight close similarities. We also provide discussions on subtle philosophical and theoretical differences between the two approaches. |
Tasks | Gaussian Processes |
Published | 2018-07-06 |
URL | http://arxiv.org/abs/1807.02582v1 |
http://arxiv.org/pdf/1807.02582v1.pdf | |
PWC | https://paperswithcode.com/paper/gaussian-processes-and-kernel-methods-a |
Repo | |
Framework | |
Learning Graph Representations by Dendrograms
Title | Learning Graph Representations by Dendrograms |
Authors | Thomas Bonald, Bertrand Charpentier |
Abstract | Hierarchical graph clustering is a common technique to reveal the multi-scale structure of complex networks. We propose a novel metric for assessing the quality of a hierarchical clustering. This metric reflects the ability to reconstruct the graph from the dendrogram, which encodes the hierarchy. The optimal representation of the graph defines a class of reducible linkages leading to regular dendrograms by greedy agglomerative clustering. |
Tasks | Graph Clustering |
Published | 2018-07-13 |
URL | http://arxiv.org/abs/1807.05087v1 |
http://arxiv.org/pdf/1807.05087v1.pdf | |
PWC | https://paperswithcode.com/paper/learning-graph-representations-by-dendrograms |
Repo | |
Framework | |
Morse Theory and an Impossibility Theorem for Graph Clustering
Title | Morse Theory and an Impossibility Theorem for Graph Clustering |
Authors | Fabio Strazzeri, Rubén J. Sánchez-García |
Abstract | Kleinberg introduced three natural clustering properties, or axioms, and showed they cannot be simultaneously satisfied by any clustering algorithm. We present a new clustering property, Monotonic Consistency, which avoids the well-known problematic behaviour of Kleinberg’s Consistency axiom, and the impossibility result. Namely, we describe a clustering algorithm, Morse Clustering, inspired by Morse Theory in Differential Topology, which satisfies Kleinberg’s original axioms with Consistency replaced by Monotonic Consistency. Morse clustering uncovers the underlying flow structure on a set or graph and returns a partition into trees representing basins of attraction of critical vertices. We also generalise Kleinberg’s axiomatic approach to sparse graphs, showing an impossibility result for Consistency, and a possibility result for Monotonic Consistency and Morse clustering. |
Tasks | Graph Clustering |
Published | 2018-06-15 |
URL | https://arxiv.org/abs/1806.06142v2 |
https://arxiv.org/pdf/1806.06142v2.pdf | |
PWC | https://paperswithcode.com/paper/morse-theory-and-an-impossibility-theorem-for |
Repo | |
Framework | |