Paper Group ANR 308
Semi-supervised Learning based on Distributionally Robust Optimization. Sensing Urban Land-Use Patterns By Integrating Google Tensorflow And Scene-Classification Models. Traffic scene recognition based on deep cnn and vlad spatial pyramids. Traffic Flow Forecasting Using a Spatio-Temporal Bayesian Network Predictor. A Computational Approach to Rela …
Semi-supervised Learning based on Distributionally Robust Optimization
| Title | Semi-supervised Learning based on Distributionally Robust Optimization |
| Authors | Jose Blanchet, Yang Kang |
| Abstract | We propose a novel method for semi-supervised learning (SSL) based on data-driven distributionally robust optimization (DRO) using optimal transport metrics. Our proposed method enhances generalization error by using the unlabeled data to restrict the support of the worst case distribution in our DRO formulation. We enable the implementation of our DRO formulation by proposing a stochastic gradient descent algorithm which allows to easily implement the training procedure. We demonstrate that our Semi-supervised DRO method is able to improve the generalization error over natural supervised procedures and state-of-the-art SSL estimators. Finally, we include a discussion on the large sample behavior of the optimal uncertainty region in the DRO formulation. Our discussion exposes important aspects such as the role of dimension reduction in SSL. |
| Tasks | Dimensionality Reduction |
| Published | 2017-02-28 |
| URL | http://arxiv.org/abs/1702.08848v4 |
| http://arxiv.org/pdf/1702.08848v4.pdf | |
| PWC | https://paperswithcode.com/paper/semi-supervised-learning-based-on |
| Repo | |
| Framework | |
Sensing Urban Land-Use Patterns By Integrating Google Tensorflow And Scene-Classification Models
| Title | Sensing Urban Land-Use Patterns By Integrating Google Tensorflow And Scene-Classification Models |
| Authors | Yao Yao, Haolin Liang, Xia Li, Jinbao Zhang, Jialv He |
| Abstract | With the rapid progress of China’s urbanization, research on the automatic detection of land-use patterns in Chinese cities is of substantial importance. Deep learning is an effective method to extract image features. To take advantage of the deep-learning method in detecting urban land-use patterns, we applied a transfer-learning-based remote-sensing image approach to extract and classify features. Using the Google Tensorflow framework, a powerful convolution neural network (CNN) library was created. First, the transferred model was previously trained on ImageNet, one of the largest object-image data sets, to fully develop the model’s ability to generate feature vectors of standard remote-sensing land-cover data sets (UC Merced and WHU-SIRI). Then, a random-forest-based classifier was constructed and trained on these generated vectors to classify the actual urban land-use pattern on the scale of traffic analysis zones (TAZs). To avoid the multi-scale effect of remote-sensing imagery, a large random patch (LRP) method was used. The proposed method could efficiently obtain acceptable accuracy (OA = 0.794, Kappa = 0.737) for the study area. In addition, the results show that the proposed method can effectively overcome the multi-scale effect that occurs in urban land-use classification at the irregular land-parcel level. The proposed method can help planners monitor dynamic urban land use and evaluate the impact of urban-planning schemes. |
| Tasks | Scene Classification, Transfer Learning |
| Published | 2017-08-04 |
| URL | http://arxiv.org/abs/1708.01580v1 |
| http://arxiv.org/pdf/1708.01580v1.pdf | |
| PWC | https://paperswithcode.com/paper/sensing-urban-land-use-patterns-by |
| Repo | |
| Framework | |
Traffic scene recognition based on deep cnn and vlad spatial pyramids
| Title | Traffic scene recognition based on deep cnn and vlad spatial pyramids |
| Authors | Fang-Yu Wu, Shi-Yang Yan, Jeremy S. Smith, Bai-Ling Zhang |
| Abstract | Traffic scene recognition is an important and challenging issue in Intelligent Transportation Systems (ITS). Recently, Convolutional Neural Network (CNN) models have achieved great success in many applications, including scene classification. The remarkable representational learning capability of CNN remains to be further explored for solving real-world problems. Vector of Locally Aggregated Descriptors (VLAD) encoding has also proved to be a powerful method in catching global contextual information. In this paper, we attempted to solve the traffic scene recognition problem by combining the features representational capabilities of CNN with the VLAD encoding scheme. More specifically, the CNN features of image patches generated by a region proposal algorithm are encoded by applying VLAD, which subsequently represent an image in a compact representation. To catch the spatial information, spatial pyramids are exploited to encode CNN features. We experimented with a dataset of 10 categories of traffic scenes, with satisfactory categorization performances. |
| Tasks | Scene Classification, Scene Recognition |
| Published | 2017-07-24 |
| URL | http://arxiv.org/abs/1707.07411v1 |
| http://arxiv.org/pdf/1707.07411v1.pdf | |
| PWC | https://paperswithcode.com/paper/traffic-scene-recognition-based-on-deep-cnn |
| Repo | |
| Framework | |
Traffic Flow Forecasting Using a Spatio-Temporal Bayesian Network Predictor
| Title | Traffic Flow Forecasting Using a Spatio-Temporal Bayesian Network Predictor |
| Authors | Shiliang Sun, Changshui Zhang, Yi Zhang |
| Abstract | A novel predictor for traffic flow forecasting, namely spatio-temporal Bayesian network predictor, is proposed. Unlike existing methods, our approach incorporates all the spatial and temporal information available in a transportation network to carry our traffic flow forecasting of the current site. The Pearson correlation coefficient is adopted to rank the input variables (traffic flows) for prediction, and the best-first strategy is employed to select a subset as the cause nodes of a Bayesian network. Given the derived cause nodes and the corresponding effect node in the spatio-temporal Bayesian network, a Gaussian Mixture Model is applied to describe the statistical relationship between the input and output. Finally, traffic flow forecasting is performed under the criterion of Minimum Mean Square Error (M.M.S.E.). Experimental results with the urban vehicular flow data of Beijing demonstrate the effectiveness of our presented spatio-temporal Bayesian network predictor. |
| Tasks | |
| Published | 2017-12-24 |
| URL | http://arxiv.org/abs/1712.08883v1 |
| http://arxiv.org/pdf/1712.08883v1.pdf | |
| PWC | https://paperswithcode.com/paper/traffic-flow-forecasting-using-a-spatio |
| Repo | |
| Framework | |
A Computational Approach to Relative Aesthetics
| Title | A Computational Approach to Relative Aesthetics |
| Authors | Parag S. Chandakkar, Vijetha Gattupalli, Baoxin Li |
| Abstract | Computational visual aesthetics has recently become an active research area. Existing state-of-art methods formulate this as a binary classification task where a given image is predicted to be beautiful or not. In many applications such as image retrieval and enhancement, it is more important to rank images based on their aesthetic quality instead of binary-categorizing them. Furthermore, in such applications, it may be possible that all images belong to the same category. Hence determining the aesthetic ranking of the images is more appropriate. To this end, we formulate a novel problem of ranking images with respect to their aesthetic quality. We construct a new dataset of image pairs with relative labels by carefully selecting images from the popular AVA dataset. Unlike in aesthetics classification, there is no single threshold which would determine the ranking order of the images across our entire dataset. We propose a deep neural network based approach that is trained on image pairs by incorporating principles from relative learning. Results show that such relative training procedure allows our network to rank the images with a higher accuracy than a state-of-art network trained on the same set of images using binary labels. |
| Tasks | Image Retrieval |
| Published | 2017-04-05 |
| URL | http://arxiv.org/abs/1704.01248v1 |
| http://arxiv.org/pdf/1704.01248v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-computational-approach-to-relative |
| Repo | |
| Framework | |
Efficient Multitask Feature and Relationship Learning
| Title | Efficient Multitask Feature and Relationship Learning |
| Authors | Han Zhao, Otilia Stretcu, Alex Smola, Geoff Gordon |
| Abstract | We consider a multitask learning problem, in which several predictors are learned jointly. Prior research has shown that learning the relations between tasks, and between the input features, together with the predictor, can lead to better generalization and interpretability, which proved to be useful for applications in many domains. In this paper, we consider a formulation of multitask learning that learns the relationships both between tasks and between features, represented through a task covariance and a feature covariance matrix, respectively. First, we demonstrate that existing methods proposed for this problem present an issue that may lead to ill-posed optimization. We then propose an alternative formulation, as well as an efficient algorithm to optimize it. Using ideas from optimization and graph theory, we propose an efficient coordinate-wise minimization algorithm that has a closed form solution for each block subproblem. Our experiments show that the proposed optimization method is orders of magnitude faster than its competitors. We also provide a nonlinear extension that is able to achieve better generalization than existing methods. |
| Tasks | |
| Published | 2017-02-14 |
| URL | https://arxiv.org/abs/1702.04423v3 |
| https://arxiv.org/pdf/1702.04423v3.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-multitask-feature-and-relationship |
| Repo | |
| Framework | |
Unsupervised learning of phase transitions: from principal component analysis to variational autoencoders
| Title | Unsupervised learning of phase transitions: from principal component analysis to variational autoencoders |
| Authors | Sebastian Johann Wetzel |
| Abstract | We employ unsupervised machine learning techniques to learn latent parameters which best describe states of the two-dimensional Ising model and the three-dimensional XY model. These methods range from principal component analysis to artificial neural network based variational autoencoders. The states are sampled using a Monte-Carlo simulation above and below the critical temperature. We find that the predicted latent parameters correspond to the known order parameters. The latent representation of the states of the models in question are clustered, which makes it possible to identify phases without prior knowledge of their existence or the underlying Hamiltonian. Furthermore, we find that the reconstruction loss function can be used as a universal identifier for phase transitions. |
| Tasks | |
| Published | 2017-03-07 |
| URL | http://arxiv.org/abs/1703.02435v2 |
| http://arxiv.org/pdf/1703.02435v2.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-learning-of-phase-transitions |
| Repo | |
| Framework | |
Deep Investigation of Cross-Language Plagiarism Detection Methods
| Title | Deep Investigation of Cross-Language Plagiarism Detection Methods |
| Authors | Jeremy Ferrero, Laurent Besacier, Didier Schwab, Frederic Agnes |
| Abstract | This paper is a deep investigation of cross-language plagiarism detection methods on a new recently introduced open dataset, which contains parallel and comparable collections of documents with multiple characteristics (different genres, languages and sizes of texts). We investigate cross-language plagiarism detection methods for 6 language pairs on 2 granularities of text units in order to draw robust conclusions on the best methods while deeply analyzing correlations across document styles and languages. |
| Tasks | |
| Published | 2017-05-24 |
| URL | http://arxiv.org/abs/1705.08828v1 |
| http://arxiv.org/pdf/1705.08828v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-investigation-of-cross-language |
| Repo | |
| Framework | |
Feature functional theory - binding predictor (FFT-BP) for the blind prediction of binding free energies
| Title | Feature functional theory - binding predictor (FFT-BP) for the blind prediction of binding free energies |
| Authors | Bao Wang, Zhixiong Zhao, Duc D. Nguyen, Guo-Wei Wei |
| Abstract | We present a feature functional theory - binding predictor (FFT-BP) for the protein-ligand binding affinity prediction. The underpinning assumptions of FFT-BP are as follows: i) representability: there exists a microscopic feature vector that can uniquely characterize and distinguish one protein-ligand complex from another; ii) feature-function relationship: the macroscopic features, including binding free energy, of a complex is a functional of microscopic feature vectors; and iii) similarity: molecules with similar microscopic features have similar macroscopic features, such as binding affinity. Physical models, such as implicit solvent models and quantum theory, are utilized to extract microscopic features, while machine learning algorithms are employed to rank the similarity among protein-ligand complexes. A large variety of numerical validations and tests confirms the accuracy and robustness of the proposed FFT-BP model. The root mean square errors (RMSEs) of FFT-BP blind predictions of a benchmark set of 100 complexes, the PDBBind v2007 core set of 195 complexes and the PDBBind v2015 core set of 195 complexes are 1.99, 2.02 and 1.92 kcal/mol, respectively. Their corresponding Pearson correlation coefficients are 0.75, 0.80, and 0.78, respectively. |
| Tasks | |
| Published | 2017-03-31 |
| URL | http://arxiv.org/abs/1703.10927v1 |
| http://arxiv.org/pdf/1703.10927v1.pdf | |
| PWC | https://paperswithcode.com/paper/feature-functional-theory-binding-predictor |
| Repo | |
| Framework | |
Polynomial Time Algorithms for Dual Volume Sampling
| Title | Polynomial Time Algorithms for Dual Volume Sampling |
| Authors | Chengtao Li, Stefanie Jegelka, Suvrit Sra |
| Abstract | We study dual volume sampling, a method for selecting k columns from an n x m short and wide matrix (n <= k <= m) such that the probability of selection is proportional to the volume spanned by the rows of the induced submatrix. This method was proposed by Avron and Boutsidis (2013), who showed it to be a promising method for column subset selection and its multiple applications. However, its wider adoption has been hampered by the lack of polynomial time sampling algorithms. We remove this hindrance by developing an exact (randomized) polynomial time sampling algorithm as well as its derandomization. Thereafter, we study dual volume sampling via the theory of real stable polynomials and prove that its distribution satisfies the “Strong Rayleigh” property. This result has numerous consequences, including a provably fast-mixing Markov chain sampler that makes dual volume sampling much more attractive to practitioners. This sampler is closely related to classical algorithms for popular experimental design methods that are to date lacking theoretical analysis but are known to empirically work well. |
| Tasks | |
| Published | 2017-03-08 |
| URL | http://arxiv.org/abs/1703.02674v3 |
| http://arxiv.org/pdf/1703.02674v3.pdf | |
| PWC | https://paperswithcode.com/paper/polynomial-time-algorithms-for-dual-volume |
| Repo | |
| Framework | |
The Local Dimension of Deep Manifold
| Title | The Local Dimension of Deep Manifold |
| Authors | Mengxiao Zhang, Wangquan Wu, Yanren Zhang, Kun He, Tao Yu, Huan Long, John E. Hopcroft |
| Abstract | Based on our observation that there exists a dramatic drop for the singular values of the fully connected layers or a single feature map of the convolutional layer, and that the dimension of the concatenated feature vector almost equals the summation of the dimension on each feature map, we propose a singular value decomposition (SVD) based approach to estimate the dimension of the deep manifolds for a typical convolutional neural network VGG19. We choose three categories from the ImageNet, namely Persian Cat, Container Ship and Volcano, and determine the local dimension of the deep manifolds of the deep layers through the tangent space of a target image. Through several augmentation methods, we found that the Gaussian noise method is closer to the intrinsic dimension, as by adding random noise to an image we are moving in an arbitrary dimension, and when the rank of the feature matrix of the augmented images does not increase we are very close to the local dimension of the manifold. We also estimate the dimension of the deep manifold based on the tangent space for each of the maxpooling layers. Our results show that the dimensions of different categories are close to each other and decline quickly along the convolutional layers and fully connected layers. Furthermore, we show that the dimensions decline quickly inside the Conv5 layer. Our work provides new insights for the intrinsic structure of deep neural networks and helps unveiling the inner organization of the black box of deep neural networks. |
| Tasks | |
| Published | 2017-11-05 |
| URL | http://arxiv.org/abs/1711.01573v1 |
| http://arxiv.org/pdf/1711.01573v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-local-dimension-of-deep-manifold |
| Repo | |
| Framework | |
Software engineering and the SP Theory of Intelligence
| Title | Software engineering and the SP Theory of Intelligence |
| Authors | J Gerard Wolff |
| Abstract | This paper describes a novel approach to software engineering derived from the “SP Theory of Intelligence” and its realisation in the “SP Computer Model”. Despite superficial appearances, it is shown that many of the key ideas in software engineering have counterparts in the structure and workings of the SP system. Potential benefits of this new approach to software engineering include: the automation or semi-automation of software development, with support for programming of the SP system where necessary; allowing programmers to concentrate on ‘world-oriented’ parallelism, without worries about parallelism to speed up processing; support for the long-term goal of programming the SP system via written or spoken natural language; reducing or eliminating the distinction between ‘design’ and ‘implementation’; reducing or eliminating operations like compiling or interpretation; reducing or eliminating the need for verification of software; reducing the need for validation of software; no formal distinction between program and database; the potential for substantial reductions in the number of types of data file and the number of computer languages; benefits for version control; and reducing technical debt. |
| Tasks | |
| Published | 2017-08-18 |
| URL | http://arxiv.org/abs/1708.06665v2 |
| http://arxiv.org/pdf/1708.06665v2.pdf | |
| PWC | https://paperswithcode.com/paper/software-engineering-and-the-sp-theory-of |
| Repo | |
| Framework | |
Locally Smoothed Neural Networks
| Title | Locally Smoothed Neural Networks |
| Authors | Liang Pang, Yanyan Lan, Jun Xu, Jiafeng Guo, Xueqi Cheng |
| Abstract | Convolutional Neural Networks (CNN) and the locally connected layer are limited in capturing the importance and relations of different local receptive fields, which are often crucial for tasks such as face verification, visual question answering, and word sequence prediction. To tackle the issue, we propose a novel locally smoothed neural network (LSNN) in this paper. The main idea is to represent the weight matrix of the locally connected layer as the product of the kernel and the smoother, where the kernel is shared over different local receptive fields, and the smoother is for determining the importance and relations of different local receptive fields. Specifically, a multi-variate Gaussian function is utilized to generate the smoother, for modeling the location relations among different local receptive fields. Furthermore, the content information can also be leveraged by setting the mean and precision of the Gaussian function according to the content. Experiments on some variant of MNIST clearly show our advantages over CNN and locally connected layer. |
| Tasks | Face Verification, Question Answering, Visual Question Answering |
| Published | 2017-11-22 |
| URL | http://arxiv.org/abs/1711.08132v1 |
| http://arxiv.org/pdf/1711.08132v1.pdf | |
| PWC | https://paperswithcode.com/paper/locally-smoothed-neural-networks |
| Repo | |
| Framework | |
Unsupervised Learning of Geometry with Edge-aware Depth-Normal Consistency
| Title | Unsupervised Learning of Geometry with Edge-aware Depth-Normal Consistency |
| Authors | Zhenheng Yang, Peng Wang, Wei Xu, Liang Zhao, Ramakant Nevatia |
| Abstract | Learning to reconstruct depths in a single image by watching unlabeled videos via deep convolutional network (DCN) is attracting significant attention in recent years. In this paper, we introduce a surface normal representation for unsupervised depth estimation framework. Our estimated depths are constrained to be compatible with predicted normals, yielding more robust geometry results. Specifically, we formulate an edge-aware depth-normal consistency term, and solve it by constructing a depth-to-normal layer and a normal-to-depth layer inside of the DCN. The depth-to-normal layer takes estimated depths as input, and computes normal directions using cross production based on neighboring pixels. Then given the estimated normals, the normal-to-depth layer outputs a regularized depth map through local planar smoothness. Both layers are computed with awareness of edges inside the image to help address the issue of depth/normal discontinuity and preserve sharp edges. Finally, to train the network, we apply the photometric error and gradient smoothness for both depth and normal predictions. We conducted experiments on both outdoor (KITTI) and indoor (NYUv2) datasets, and show that our algorithm vastly outperforms state of the art, which demonstrates the benefits from our approach. |
| Tasks | Depth Estimation |
| Published | 2017-11-10 |
| URL | http://arxiv.org/abs/1711.03665v1 |
| http://arxiv.org/pdf/1711.03665v1.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-learning-of-geometry-with-edge |
| Repo | |
| Framework | |
Summarized Network Behavior Prediction
| Title | Summarized Network Behavior Prediction |
| Authors | Shih-Chieh Su |
| Abstract | This work studies the entity-wise topical behavior from massive network logs. Both the temporal and the spatial relationships of the behavior are explored with the learning architectures combing the recurrent neural network (RNN) and the convolutional neural network (CNN). To make the behavioral data appropriate for the spatial learning in CNN, several reduction steps are taken to form the topical metrics and place them homogeneously like pixels in the images. The experimental result shows both the temporal- and the spatial- gains when compared to a multilayer perceptron (MLP) network. A new learning framework called spatially connected convolutional networks (SCCN) is introduced to more efficiently predict the behavior. |
| Tasks | |
| Published | 2017-05-02 |
| URL | http://arxiv.org/abs/1705.01143v1 |
| http://arxiv.org/pdf/1705.01143v1.pdf | |
| PWC | https://paperswithcode.com/paper/summarized-network-behavior-prediction |
| Repo | |
| Framework | |
