Paper Group ANR 158
RGB-based 3D Hand Pose Estimation via Privileged Learning with Depth Images. XPCA: Extending PCA for a Combination of Discrete and Continuous Variables. Deep Reinforcement Learning in Ice Hockey for Context-Aware Player Evaluation. Unsupervised learning with contrastive latent variable models. Finding Frequent Entities in Continuous Data. Adversari …
RGB-based 3D Hand Pose Estimation via Privileged Learning with Depth Images
Title | RGB-based 3D Hand Pose Estimation via Privileged Learning with Depth Images |
Authors | Shanxin Yuan, Bjorn Stenger, Tae-Kyun Kim |
Abstract | This paper proposes a method for hand pose estimation from RGB images that uses both external large-scale depth image datasets and paired depth and RGB images as privileged information at training time. We show that providing depth information during training significantly improves performance of pose estimation from RGB images during testing. We explore different ways of using this privileged information: (1) using depth data to initially train a depth-based network, (2) using the features from the depth-based network of the paired depth images to constrain mid-level RGB network weights, and (3) using the foreground mask, obtained from the depth data, to suppress the responses from the background area. By using paired RGB and depth images, we are able to supervise the RGB-based network to learn middle layer features that mimic that of the corresponding depth-based network, which is trained on large-scale, accurately annotated depth data. During testing, when only an RGB image is available, our method produces accurate 3D hand pose predictions. Our method is also tested on 2D hand pose estimation. Experiments on three public datasets show that the method outperforms the state-of-the-art methods for hand pose estimation using RGB image input. |
Tasks | Hand Pose Estimation, Pose Estimation |
Published | 2018-11-18 |
URL | http://arxiv.org/abs/1811.07376v1 |
http://arxiv.org/pdf/1811.07376v1.pdf | |
PWC | https://paperswithcode.com/paper/rgb-based-3d-hand-pose-estimation-via |
Repo | |
Framework | |
XPCA: Extending PCA for a Combination of Discrete and Continuous Variables
Title | XPCA: Extending PCA for a Combination of Discrete and Continuous Variables |
Authors | Clifford Anderson-Bergman, Tamara G. Kolda, Kina Kincher-Winoto |
Abstract | Principal component analysis (PCA) is arguably the most popular tool in multivariate exploratory data analysis. In this paper, we consider the question of how to handle heterogeneous variables that include continuous, binary, and ordinal. In the probabilistic interpretation of low-rank PCA, the data has a normal multivariate distribution and, therefore, normal marginal distributions for each column. If some marginals are continuous but not normal, the semiparametric copula-based principal component analysis (COCA) method is an alternative to PCA that combines a Gaussian copula with nonparametric marginals. If some marginals are discrete or semi-continuous, we propose a new extended PCA (XPCA) method that also uses a Gaussian copula and nonparametric marginals and accounts for discrete variables in the likelihood calculation by integrating over appropriate intervals. Like PCA, the factors produced by XPCA can be used to find latent structure in data, build predictive models, and perform dimensionality reduction. We present the new model, its induced likelihood function, and a fitting algorithm which can be applied in the presence of missing data. We demonstrate how to use XPCA to produce an estimated full conditional distribution for each data point, and use this to produce to provide estimates for missing data that are automatically range respecting. We compare the methods as applied to simulated and real-world data sets that have a mixture of discrete and continuous variables. |
Tasks | Dimensionality Reduction |
Published | 2018-08-22 |
URL | http://arxiv.org/abs/1808.07510v1 |
http://arxiv.org/pdf/1808.07510v1.pdf | |
PWC | https://paperswithcode.com/paper/xpca-extending-pca-for-a-combination-of |
Repo | |
Framework | |
Deep Reinforcement Learning in Ice Hockey for Context-Aware Player Evaluation
Title | Deep Reinforcement Learning in Ice Hockey for Context-Aware Player Evaluation |
Authors | Guiliang Liu, Oliver Schulte |
Abstract | A variety of machine learning models have been proposed to assess the performance of players in professional sports. However, they have only a limited ability to model how player performance depends on the game context. This paper proposes a new approach to capturing game context: we apply Deep Reinforcement Learning (DRL) to learn an action-value Q function from 3M play-by-play events in the National Hockey League (NHL). The neural network representation integrates both continuous context signals and game history, using a possession-based LSTM. The learned Q-function is used to value players’ actions under different game contexts. To assess a player’s overall performance, we introduce a novel Game Impact Metric (GIM) that aggregates the values of the player’s actions. Empirical Evaluation shows GIM is consistent throughout a play season, and correlates highly with standard success measures and future salary. |
Tasks | |
Published | 2018-05-26 |
URL | http://arxiv.org/abs/1805.11088v3 |
http://arxiv.org/pdf/1805.11088v3.pdf | |
PWC | https://paperswithcode.com/paper/deep-reinforcement-learning-in-ice-hockey-for |
Repo | |
Framework | |
Unsupervised learning with contrastive latent variable models
Title | Unsupervised learning with contrastive latent variable models |
Authors | Kristen Severson, Soumya Ghosh, Kenney Ng |
Abstract | In unsupervised learning, dimensionality reduction is an important tool for data exploration and visualization. Because these aims are typically open-ended, it can be useful to frame the problem as looking for patterns that are enriched in one dataset relative to another. These pairs of datasets occur commonly, for instance a population of interest vs. control or signal vs. signal free recordings.However, there are few methods that work on sets of data as opposed to data points or sequences. Here, we present a probabilistic model for dimensionality reduction to discover signal that is enriched in the target dataset relative to the background dataset. The data in these sets do not need to be paired or grouped beyond set membership. By using a probabilistic model where some structure is shared amongst the two datasets and some is unique to the target dataset, we are able to recover interesting structure in the latent space of the target dataset. The method also has the advantages of a probabilistic model, namely that it allows for the incorporation of prior information, handles missing data, and can be generalized to different distributional assumptions. We describe several possible variations of the model and demonstrate the application of the technique to de-noising, feature selection, and subgroup discovery settings. |
Tasks | Dimensionality Reduction, Feature Selection, Latent Variable Models |
Published | 2018-11-14 |
URL | http://arxiv.org/abs/1811.06094v1 |
http://arxiv.org/pdf/1811.06094v1.pdf | |
PWC | https://paperswithcode.com/paper/unsupervised-learning-with-contrastive-latent |
Repo | |
Framework | |
Finding Frequent Entities in Continuous Data
Title | Finding Frequent Entities in Continuous Data |
Authors | Ferran Alet, Rohan Chitnis, Leslie P. Kaelbling, Tomas Lozano-Perez |
Abstract | In many applications that involve processing high-dimensional data, it is important to identify a small set of entities that account for a significant fraction of detections. Rather than formalize this as a clustering problem, in which all detections must be grouped into hard or soft categories, we formalize it as an instance of the frequent items or heavy hitters problem, which finds groups of tightly clustered objects that have a high density in the feature space. We show that the heavy hitters formulation generates solutions that are more accurate and effective than the clustering formulation. In addition, we present a novel online algorithm for heavy hitters, called HAC, which addresses problems in continuous space, and demonstrate its effectiveness on real video and household domains. |
Tasks | |
Published | 2018-05-08 |
URL | http://arxiv.org/abs/1805.02874v1 |
http://arxiv.org/pdf/1805.02874v1.pdf | |
PWC | https://paperswithcode.com/paper/finding-frequent-entities-in-continuous-data |
Repo | |
Framework | |
Adversarial Training for Adverse Conditions: Robust Metric Localisation using Appearance Transfer
Title | Adversarial Training for Adverse Conditions: Robust Metric Localisation using Appearance Transfer |
Authors | Horia Porav, Will Maddern, Paul Newman |
Abstract | We present a method of improving visual place recognition and metric localisation under very strong appear- ance change. We learn an invertable generator that can trans- form the conditions of images, e.g. from day to night, summer to winter etc. This image transforming filter is explicitly designed to aid and abet feature-matching using a new loss based on SURF detector and dense descriptor maps. A network is trained to output synthetic images optimised for feature matching given only an input RGB image, and these generated images are used to localize the robot against a previously built map using traditional sparse matching approaches. We benchmark our results using multiple traversals of the Oxford RobotCar Dataset over a year-long period, using one traversal as a map and the other to localise. We show that this method significantly improves place recognition and localisation under changing and adverse conditions, while reducing the number of mapping runs needed to successfully achieve reliable localisation. |
Tasks | Visual Place Recognition |
Published | 2018-03-09 |
URL | http://arxiv.org/abs/1803.03341v1 |
http://arxiv.org/pdf/1803.03341v1.pdf | |
PWC | https://paperswithcode.com/paper/adversarial-training-for-adverse-conditions |
Repo | |
Framework | |
Differentially-Private “Draw and Discard” Machine Learning
Title | Differentially-Private “Draw and Discard” Machine Learning |
Authors | Vasyl Pihur, Aleksandra Korolova, Frederick Liu, Subhash Sankuratripati, Moti Yung, Dachuan Huang, Ruogu Zeng |
Abstract | In this work, we propose a novel framework for privacy-preserving client-distributed machine learning. It is motivated by the desire to achieve differential privacy guarantees in the local model of privacy in a way that satisfies all systems constraints using asynchronous client-server communication and provides attractive model learning properties. We call it “Draw and Discard” because it relies on random sampling of models for load distribution (scalability), which also provides additional server-side privacy protections and improved model quality through averaging. We present the mechanics of client and server components of “Draw and Discard” and demonstrate how the framework can be applied to learning Generalized Linear models. We then analyze the privacy guarantees provided by our approach against several types of adversaries and showcase experimental results that provide evidence for the framework’s viability in practical deployments. |
Tasks | |
Published | 2018-07-11 |
URL | http://arxiv.org/abs/1807.04369v2 |
http://arxiv.org/pdf/1807.04369v2.pdf | |
PWC | https://paperswithcode.com/paper/differentially-private-draw-and-discard |
Repo | |
Framework | |
Assessment of Deep Convolutional Neural Networks for Road Surface Classification
Title | Assessment of Deep Convolutional Neural Networks for Road Surface Classification |
Authors | Marcus Nolte, Nikita Kister, Markus Maurer |
Abstract | When parameterizing vehicle control algorithms for stability or trajectory control, the road-tire friction coefficient is an essential model parameter when it comes to control performance. One major impact on the friction coefficient is the condition of the road surface. A camera-based, forward-looking classification of the road-surface helps enabling an early parametrization of vehicle control algorithms. In this paper, we train and compare two different Deep Convolutional Neural Network models, regarding their application for road friction estimation and describe the challenges for training the classifier in terms of available training data and the construction of suitable datasets. |
Tasks | |
Published | 2018-04-24 |
URL | http://arxiv.org/abs/1804.08872v2 |
http://arxiv.org/pdf/1804.08872v2.pdf | |
PWC | https://paperswithcode.com/paper/assessment-of-deep-convolutional-neural |
Repo | |
Framework | |
ABACUS: Unsupervised Multivariate Change Detection via Bayesian Source Separation
Title | ABACUS: Unsupervised Multivariate Change Detection via Bayesian Source Separation |
Authors | Wenyu Zhang, Daniel Gilbert, David Matteson |
Abstract | Change detection involves segmenting sequential data such that observations in the same segment share some desired properties. Multivariate change detection continues to be a challenging problem due to the variety of ways change points can be correlated across channels and the potentially poor signal-to-noise ratio on individual channels. In this paper, we are interested in locating additive outliers (AO) and level shifts (LS) in the unsupervised setting. We propose ABACUS, Automatic BAyesian Changepoints Under Sparsity, a Bayesian source separation technique to recover latent signals while also detecting changes in model parameters. Multi-level sparsity achieves both dimension reduction and modeling of signal changes. We show ABACUS has competitive or superior performance in simulation studies against state-of-the-art change detection methods and established latent variable models. We also illustrate ABACUS on two real application, modeling genomic profiles and analyzing household electricity consumption. |
Tasks | Dimensionality Reduction, Latent Variable Models |
Published | 2018-10-15 |
URL | http://arxiv.org/abs/1810.06167v1 |
http://arxiv.org/pdf/1810.06167v1.pdf | |
PWC | https://paperswithcode.com/paper/abacus-unsupervised-multivariate-change |
Repo | |
Framework | |
Using Apple Machine Learning Algorithms to Detect and Subclassify Non-Small Cell Lung Cancer
Title | Using Apple Machine Learning Algorithms to Detect and Subclassify Non-Small Cell Lung Cancer |
Authors | Andrew A. Borkowski, Catherine P. Wilson, Steven A. Borkowski, Lauren A. Deland, Stephen M. Mastorides |
Abstract | Lung cancer continues to be a major healthcare challenge with high morbidity and mortality rates among both men and women worldwide. The majority of lung cancer cases are of non-small cell lung cancer type. With the advent of targeted cancer therapy, it is imperative not only to properly diagnose but also sub-classify non-small cell lung cancer. In our study, we evaluated the utility of using Apple Create ML module to detect and sub-classify non-small cell carcinomas based on histopathological images. After module optimization, the program detected 100% of non-small cell lung cancer images and successfully subclassified the majority of the images. Trained modules, such as ours, can be utilized in diagnostic smartphone-based applications, augmenting diagnostic services in understaffed areas of the world. |
Tasks | |
Published | 2018-08-24 |
URL | http://arxiv.org/abs/1808.08230v2 |
http://arxiv.org/pdf/1808.08230v2.pdf | |
PWC | https://paperswithcode.com/paper/using-apple-machine-learning-algorithms-to |
Repo | |
Framework | |
Learning to Detect Instantaneous Changes with Retrospective Convolution and Static Sample Synthesis
Title | Learning to Detect Instantaneous Changes with Retrospective Convolution and Static Sample Synthesis |
Authors | Chao Chen, Sheng Zhang, Cuibing Du |
Abstract | Change detection has been a challenging visual task due to the dynamic nature of real-world scenes. Good performance of existing methods depends largely on prior background images or a long-term observation. These methods, however, suffer severe degradation when they are applied to detection of instantaneously occurred changes with only a few preceding frames provided. In this paper, we exploit spatio-temporal convolutional networks to address this challenge, and propose a novel retrospective convolution, which features efficient change information extraction between the current frame and frames from historical observation. To address the problem of foreground-specific over-fitting in learning-based methods, we further propose a data augmentation method, named static sample synthesis, to guide the network to focus on learning change-cued information rather than specific spatial features of foreground. Trained end-to-end with complex scenarios, our framework proves to be accurate in detecting instantaneous changes and robust in combating diverse noises. Extensive experiments demonstrate that our proposed method significantly outperforms existing methods. |
Tasks | Data Augmentation |
Published | 2018-11-20 |
URL | http://arxiv.org/abs/1811.08138v1 |
http://arxiv.org/pdf/1811.08138v1.pdf | |
PWC | https://paperswithcode.com/paper/learning-to-detect-instantaneous-changes-with |
Repo | |
Framework | |
Improving Context-Aware Semantic Relationships in Sparse Mobile Datasets
Title | Improving Context-Aware Semantic Relationships in Sparse Mobile Datasets |
Authors | Peter Hansel, Nik Marda, William Yin |
Abstract | Traditional semantic similarity models often fail to encapsulate the external context in which texts are situated. However, textual datasets generated on mobile platforms can help us build a truer representation of semantic similarity by introducing multimodal data. This is especially important in sparse datasets, making solely text-driven interpretation of context more difficult. In this paper, we develop new algorithms for building external features into sentence embeddings and semantic similarity scores. Then, we test them on embedding spaces on data from Twitter, using each tweet’s time and geolocation to better understand its context. Ultimately, we show that applying PCA with eight components to the embedding space and appending multimodal features yields the best outcomes. This yields a considerable improvement over pure text-based approaches for discovering similar tweets. Our results suggest that our new algorithm can help improve semantic understanding in various settings. |
Tasks | Semantic Similarity, Semantic Textual Similarity, Sentence Embeddings |
Published | 2018-12-23 |
URL | http://arxiv.org/abs/1812.09650v1 |
http://arxiv.org/pdf/1812.09650v1.pdf | |
PWC | https://paperswithcode.com/paper/improving-context-aware-semantic |
Repo | |
Framework | |
Segmentation hiérarchique faiblement supervisée
Title | Segmentation hiérarchique faiblement supervisée |
Authors | Amin Fehri, Santiago Velasco-Forero, Fernand Meyer |
Abstract | Image segmentation is the process of partitioning an image into a set of meaningful regions according to some criteria. Hierarchical segmentation has emerged as a major trend in this regard as it favors the emergence of important regions at different scales. On the other hand, many methods allow us to have prior information on the position of structures of interest in the images. In this paper, we present a versatile hierarchical segmentation method that takes into account any prior spatial information and outputs a hierarchical segmentation that emphasizes the contours or regions of interest while preserving the important structures in the image. An application of this method to the weakly-supervised segmentation problem is presented. |
Tasks | Semantic Segmentation |
Published | 2018-02-20 |
URL | http://arxiv.org/abs/1802.07008v1 |
http://arxiv.org/pdf/1802.07008v1.pdf | |
PWC | https://paperswithcode.com/paper/segmentation-hierarchique-faiblement |
Repo | |
Framework | |
Mixed-Integer Convex Nonlinear Optimization with Gradient-Boosted Trees Embedded
Title | Mixed-Integer Convex Nonlinear Optimization with Gradient-Boosted Trees Embedded |
Authors | Miten Mistry, Dimitrios Letsios, Gerhard Krennrich, Robert M. Lee, Ruth Misener |
Abstract | Decision trees usefully represent sparse, high dimensional and noisy data. Having learned a function from this data, we may want to thereafter integrate the function into a larger decision-making problem, e.g., for picking the best chemical process catalyst. We study a large-scale, industrially-relevant mixed-integer nonlinear nonconvex optimization problem involving both gradient-boosted trees and penalty functions mitigating risk. This mixed-integer optimization problem with convex penalty terms broadly applies to optimizing pre-trained regression tree models. Decision makers may wish to optimize discrete models to repurpose legacy predictive models, or they may wish to optimize a discrete model that particularly well-represents a data set. We develop several heuristic methods to find feasible solutions, and an exact, branch-and-bound algorithm leveraging structural properties of the gradient-boosted trees and penalty functions. We computationally test our methods on concrete mixture design instance and a chemical catalysis industrial instance. |
Tasks | Decision Making |
Published | 2018-03-02 |
URL | https://arxiv.org/abs/1803.00952v3 |
https://arxiv.org/pdf/1803.00952v3.pdf | |
PWC | https://paperswithcode.com/paper/mixed-integer-convex-nonlinear-optimization |
Repo | |
Framework | |
Typhoon track prediction using satellite images in a Generative Adversarial Network
Title | Typhoon track prediction using satellite images in a Generative Adversarial Network |
Authors | Mario Rüttgers, Sangseung Lee, Donghyun You |
Abstract | Tracks of typhoons are predicted using satellite images as input for a Generative Adversarial Network (GAN). The satellite images have time gaps of 6 hours and are marked with a red square at the location of the typhoon center. The GAN uses images from the past to generate an image one time step ahead. The generated image shows the future location of the typhoon center, as well as the future cloud structures. The errors between predicted and real typhoon centers are measured quantitatively in kilometers. 42.4% of all typhoon center predictions have absolute errors of less than 80 km, 32.1% lie within a range of 80 - 120 km and the remaining 25.5% have accuracies above 120 km. The relative error sets the above mentioned absolute error in relation to the distance that has been traveled by a typhoon over the past 6 hours. High relative errors are found in three types of situations, when a typhoon moves on the open sea far away from land, when a typhoon changes its course suddenly and when a typhoon is about to hit the mainland. The cloud structure prediction is evaluated qualitatively. It is shown that the GAN is able to predict trends in cloud motion. In order to improve both, the typhoon center and cloud motion prediction, the present study suggests to add information about the sea surface temperature, surface pressure and velocity fields to the input data. |
Tasks | motion prediction |
Published | 2018-08-16 |
URL | http://arxiv.org/abs/1808.05382v1 |
http://arxiv.org/pdf/1808.05382v1.pdf | |
PWC | https://paperswithcode.com/paper/typhoon-track-prediction-using-satellite |
Repo | |
Framework | |