Paper Group ANR 322
Deep Learning the City : Quantifying Urban Perception At A Global Scale. Learning of Generalized Low-Rank Models: A Greedy Approach. End-to-end Learning of Cost-Volume Aggregation for Real-time Dense Stereo. Operator Variational Inference. Improving analytical tomographic reconstructions through consistency conditions. Embedding based on function a …
Deep Learning the City : Quantifying Urban Perception At A Global Scale
| Title | Deep Learning the City : Quantifying Urban Perception At A Global Scale |
| Authors | Abhimanyu Dubey, Nikhil Naik, Devi Parikh, Ramesh Raskar, César A. Hidalgo |
| Abstract | Computer vision methods that quantify the perception of urban environment are increasingly being used to study the relationship between a city’s physical appearance and the behavior and health of its residents. Yet, the throughput of current methods is too limited to quantify the perception of cities across the world. To tackle this challenge, we introduce a new crowdsourced dataset containing 110,988 images from 56 cities, and 1,170,000 pairwise comparisons provided by 81,630 online volunteers along six perceptual attributes: safe, lively, boring, wealthy, depressing, and beautiful. Using this data, we train a Siamese-like convolutional neural architecture, which learns from a joint classification and ranking loss, to predict human judgments of pairwise image comparisons. Our results show that crowdsourcing combined with neural networks can produce urban perception data at the global scale. |
| Tasks | |
| Published | 2016-08-05 |
| URL | http://arxiv.org/abs/1608.01769v2 |
| http://arxiv.org/pdf/1608.01769v2.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-the-city-quantifying-urban |
| Repo | |
| Framework | |
Learning of Generalized Low-Rank Models: A Greedy Approach
| Title | Learning of Generalized Low-Rank Models: A Greedy Approach |
| Authors | Quanming Yao, James T. Kwok |
| Abstract | Learning of low-rank matrices is fundamental to many machine learning applications. A state-of-the-art algorithm is the rank-one matrix pursuit (R1MP). However, it can only be used in matrix completion problems with the square loss. In this paper, we develop a more flexible greedy algorithm for generalized low-rank models whose optimization objective can be smooth or nonsmooth, general convex or strongly convex. The proposed algorithm has low per-iteration time complexity and fast convergence rate. Experimental results show that it is much faster than the state-of-the-art, with comparable or even better prediction performance. |
| Tasks | Matrix Completion |
| Published | 2016-07-27 |
| URL | http://arxiv.org/abs/1607.08012v1 |
| http://arxiv.org/pdf/1607.08012v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-of-generalized-low-rank-models-a |
| Repo | |
| Framework | |
End-to-end Learning of Cost-Volume Aggregation for Real-time Dense Stereo
| Title | End-to-end Learning of Cost-Volume Aggregation for Real-time Dense Stereo |
| Authors | Andrey Kuzmin, Dmitry Mikushin, Victor Lempitsky |
| Abstract | We present a new deep learning-based approach for dense stereo matching. Compared to previous works, our approach does not use deep learning of pixel appearance descriptors, employing very fast classical matching scores instead. At the same time, our approach uses a deep convolutional network to predict the local parameters of cost volume aggregation process, which in this paper we implement using differentiable domain transform. By treating such transform as a recurrent neural network, we are able to train our whole system that includes cost volume computation, cost-volume aggregation (smoothing), and winner-takes-all disparity selection end-to-end. The resulting method is highly efficient at test time, while achieving good matching accuracy. On the KITTI 2015 benchmark, it achieves a result of 6.34% error rate while running at 29 frames per second rate on a modern GPU. |
| Tasks | Stereo Matching, Stereo Matching Hand |
| Published | 2016-11-17 |
| URL | http://arxiv.org/abs/1611.05689v1 |
| http://arxiv.org/pdf/1611.05689v1.pdf | |
| PWC | https://paperswithcode.com/paper/end-to-end-learning-of-cost-volume |
| Repo | |
| Framework | |
Operator Variational Inference
| Title | Operator Variational Inference |
| Authors | Rajesh Ranganath, Jaan Altosaar, Dustin Tran, David M. Blei |
| Abstract | Variational inference is an umbrella term for algorithms which cast Bayesian inference as optimization. Classically, variational inference uses the Kullback-Leibler divergence to define the optimization. Though this divergence has been widely used, the resultant posterior approximation can suffer from undesirable statistical properties. To address this, we reexamine variational inference from its roots as an optimization problem. We use operators, or functions of functions, to design variational objectives. As one example, we design a variational objective with a Langevin-Stein operator. We develop a black box algorithm, operator variational inference (OPVI), for optimizing any operator objective. Importantly, operators enable us to make explicit the statistical and computational tradeoffs for variational inference. We can characterize different properties of variational objectives, such as objectives that admit data subsampling—allowing inference to scale to massive data—as well as objectives that admit variational programs—a rich class of posterior approximations that does not require a tractable density. We illustrate the benefits of OPVI on a mixture model and a generative model of images. |
| Tasks | Bayesian Inference |
| Published | 2016-10-27 |
| URL | http://arxiv.org/abs/1610.09033v3 |
| http://arxiv.org/pdf/1610.09033v3.pdf | |
| PWC | https://paperswithcode.com/paper/operator-variational-inference |
| Repo | |
| Framework | |
Improving analytical tomographic reconstructions through consistency conditions
| Title | Improving analytical tomographic reconstructions through consistency conditions |
| Authors | Filippo Arcadu, Jakob Vogel, Marco Stampanoni, Federica Marone |
| Abstract | This work introduces and characterizes a fast parameterless filter based on the Helgason-Ludwig consistency conditions, used to improve the accuracy of analytical reconstructions of tomographic undersampled datasets. The filter, acting in the Radon domain, extrapolates intermediate projections between those existing. The resulting sinogram, doubled in views, is then reconstructed by a standard analytical method. Experiments with simulated data prove that the peak-signal-to-noise ratio of the results computed by filtered backprojection is improved up to 5-6 dB, if the filter is used prior to reconstruction. |
| Tasks | Tomographic Reconstructions |
| Published | 2016-09-21 |
| URL | http://arxiv.org/abs/1609.06604v1 |
| http://arxiv.org/pdf/1609.06604v1.pdf | |
| PWC | https://paperswithcode.com/paper/improving-analytical-tomographic |
| Repo | |
| Framework | |
Embedding based on function approximation for large scale image search
| Title | Embedding based on function approximation for large scale image search |
| Authors | Thanh-Toan Do, Ngai-Man Cheung |
| Abstract | The objective of this paper is to design an embedding method that maps local features describing an image (e.g. SIFT) to a higher dimensional representation useful for the image retrieval problem. First, motivated by the relationship between the linear approximation of a nonlinear function in high dimensional space and the stateof-the-art feature representation used in image retrieval, i.e., VLAD, we propose a new approach for the approximation. The embedded vectors resulted by the function approximation process are then aggregated to form a single representation for image retrieval. Second, in order to make the proposed embedding method applicable to large scale problem, we further derive its fast version in which the embedded vectors can be efficiently computed, i.e., in the closed-form. We compare the proposed embedding methods with the state of the art in the context of image search under various settings: when the images are represented by medium length vectors, short vectors, or binary vectors. The experimental results show that the proposed embedding methods outperform existing the state of the art on the standard public image retrieval benchmarks. |
| Tasks | Image Retrieval |
| Published | 2016-05-23 |
| URL | http://arxiv.org/abs/1605.06914v3 |
| http://arxiv.org/pdf/1605.06914v3.pdf | |
| PWC | https://paperswithcode.com/paper/embedding-based-on-function-approximation-for |
| Repo | |
| Framework | |
Network-Guided Biomarker Discovery
| Title | Network-Guided Biomarker Discovery |
| Authors | Chloé-Agathe Azencott |
| Abstract | Identifying measurable genetic indicators (or biomarkers) of a specific condition of a biological system is a key element of precision medicine. Indeed it allows to tailor diagnostic, prognostic and treatment choice to individual characteristics of a patient. In machine learning terms, biomarker discovery can be framed as a feature selection problem on whole-genome data sets. However, classical feature selection methods are usually underpowered to process these data sets, which contain orders of magnitude more features than samples. This can be addressed by making the assumption that genetic features that are linked on a biological network are more likely to work jointly towards explaining the phenotype of interest. We review here three families of methods for feature selection that integrate prior knowledge in the form of networks. |
| Tasks | Feature Selection |
| Published | 2016-07-27 |
| URL | http://arxiv.org/abs/1607.08161v2 |
| http://arxiv.org/pdf/1607.08161v2.pdf | |
| PWC | https://paperswithcode.com/paper/network-guided-biomarker-discovery |
| Repo | |
| Framework | |
3D Hand Pose Tracking and Estimation Using Stereo Matching
| Title | 3D Hand Pose Tracking and Estimation Using Stereo Matching |
| Authors | Jiawei Zhang, Jianbo Jiao, Mingliang Chen, Liangqiong Qu, Xiaobin Xu, Qingxiong Yang |
| Abstract | 3D hand pose tracking/estimation will be very important in the next generation of human-computer interaction. Most of the currently available algorithms rely on low-cost active depth sensors. However, these sensors can be easily interfered by other active sources and require relatively high power consumption. As a result, they are currently not suitable for outdoor environments and mobile devices. This paper aims at tracking/estimating hand poses using passive stereo which avoids these limitations. A benchmark with 18,000 stereo image pairs and 18,000 depth images captured from different scenarios and the ground-truth 3D positions of palm and finger joints (obtained from the manual label) is thus proposed. This paper demonstrates that the performance of the state-of-the art tracking/estimation algorithms can be maintained with most stereo matching algorithms on the proposed benchmark, as long as the hand segmentation is correct. As a result, a novel stereo-based hand segmentation algorithm specially designed for hand tracking/estimation is proposed. The quantitative evaluation demonstrates that the proposed algorithm is suitable for the state-of-the-art hand pose tracking/estimation algorithms and the tracking quality is comparable to the use of active depth sensors under different challenging scenarios. |
| Tasks | Hand Segmentation, Pose Tracking, Stereo Matching, Stereo Matching Hand |
| Published | 2016-10-23 |
| URL | http://arxiv.org/abs/1610.07214v1 |
| http://arxiv.org/pdf/1610.07214v1.pdf | |
| PWC | https://paperswithcode.com/paper/3d-hand-pose-tracking-and-estimation-using |
| Repo | |
| Framework | |
A Permutation-based Model for Crowd Labeling: Optimal Estimation and Robustness
| Title | A Permutation-based Model for Crowd Labeling: Optimal Estimation and Robustness |
| Authors | Nihar B. Shah, Sivaraman Balakrishnan, Martin J. Wainwright |
| Abstract | The aggregation and denoising of crowd-labeled data is a task that has gained increased significance with the advent of crowdsourcing platforms and massive datasets. In this paper, we propose a permutation-based model for crowd labeled data that is a significant generalization of the common Dawid-Skene model, and introduce a new error metric by which to compare different estimators. Working in a high-dimensional non-asymptotic framework that allows both the number of workers and tasks to scale, we derive minimax rates of convergence for the permutation-based model that are optimal (up to logarithmic factors). We show that the permutation-based model offers significant robustness in estimation due to its richness, while surprisingly incurring only a small additional statistical penalty as compared to the Dawid-Skene model. We then design a computationally-efficient method, called the OBI-WAN estimator, that is optimal over a class intermediate between the permutation-based and the Dawid-Skene models (up to logarithmic factors), and also simultaneously achieves non-trivial guarantees over the entire permutation-based model class. Finally, we conduct synthetic simulations and experiments on real-world crowdsourcing data, and these corroborate our theoretical findings. |
| Tasks | Denoising |
| Published | 2016-06-30 |
| URL | https://arxiv.org/abs/1606.09632v2 |
| https://arxiv.org/pdf/1606.09632v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-permutation-based-model-for-crowd-labeling |
| Repo | |
| Framework | |
BliStrTune: Hierarchical Invention of Theorem Proving Strategies
| Title | BliStrTune: Hierarchical Invention of Theorem Proving Strategies |
| Authors | Jan Jakubuv, Josef Urban |
| Abstract | Inventing targeted proof search strategies for specific problem sets is a difficult task. State-of-the-art automated theorem provers (ATPs) such as E allow a large number of user-specified proof search strategies described in a rich domain specific language. Several machine learning methods that invent strategies automatically for ATPs were proposed previously. One of them is the Blind Strategymaker (BliStr), a system for automated invention of ATP strategies. In this paper we introduce BliStrTune – a hierarchical extension of BliStr. BliStrTune allows exploring much larger space of E strategies by interleaving search for high-level parameters with their fine-tuning. We use BliStrTune to invent new strategies based also on new clause weight functions targeted at problems from large ITP libraries. We show that the new strategies significantly improve E’s performance in solving problems from the Mizar Mathematical Library. |
| Tasks | Automated Theorem Proving |
| Published | 2016-11-26 |
| URL | http://arxiv.org/abs/1611.08733v1 |
| http://arxiv.org/pdf/1611.08733v1.pdf | |
| PWC | https://paperswithcode.com/paper/blistrtune-hierarchical-invention-of-theorem |
| Repo | |
| Framework | |
Balotage in Argentina 2015, a sentiment analysis of tweets
| Title | Balotage in Argentina 2015, a sentiment analysis of tweets |
| Authors | Daniel Robins, Fernando Emmanuel Frati, Jonatan Alvarez, Jose Texier |
| Abstract | Twitter social network contains a large amount of information generated by its users. That information is composed of opinions and comments that may reflect trends in social behavior. There is talk of trend when it is possible to identify opinions and comments geared towards the same shared by a lot of people direction. To determine if two or more written opinions share the same address, techniques Natural Language Processing (NLP) are used. This paper proposes a methodology for predicting reflected in Twitter from the use of sentiment analysis functions NLP based on social behaviors. The case study was selected the 2015 Presidential in Argentina, and a software architecture Big Data composed Vertica data base with the component called Pulse was used. Through the analysis it was possible to detect trends in voting intentions with regard to the presidential candidates, achieving greater accuracy in predicting that achieved with traditional systems surveys. |
| Tasks | Sentiment Analysis |
| Published | 2016-11-07 |
| URL | http://arxiv.org/abs/1611.02337v1 |
| http://arxiv.org/pdf/1611.02337v1.pdf | |
| PWC | https://paperswithcode.com/paper/balotage-in-argentina-2015-a-sentiment |
| Repo | |
| Framework | |
DeepAlgebra - an outline of a program
| Title | DeepAlgebra - an outline of a program |
| Authors | Przemyslaw Chojecki |
| Abstract | We outline a program in the area of formalization of mathematics to automate theorem proving in algebra and algebraic geometry. We propose a construction of a dictionary between automated theorem provers and (La)TeX exploiting syntactic parsers. We describe its application to a repository of human-written facts and definitions in algebraic geometry (The Stacks Project). We use deep learning techniques. |
| Tasks | Automated Theorem Proving |
| Published | 2016-10-04 |
| URL | http://arxiv.org/abs/1610.01044v1 |
| http://arxiv.org/pdf/1610.01044v1.pdf | |
| PWC | https://paperswithcode.com/paper/deepalgebra-an-outline-of-a-program |
| Repo | |
| Framework | |
Deep Roots: Improving CNN Efficiency with Hierarchical Filter Groups
| Title | Deep Roots: Improving CNN Efficiency with Hierarchical Filter Groups |
| Authors | Yani Ioannou, Duncan Robertson, Roberto Cipolla, Antonio Criminisi |
| Abstract | We propose a new method for creating computationally efficient and compact convolutional neural networks (CNNs) using a novel sparse connection structure that resembles a tree root. This allows a significant reduction in computational cost and number of parameters compared to state-of-the-art deep CNNs, without compromising accuracy, by exploiting the sparsity of inter-layer filter dependencies. We validate our approach by using it to train more efficient variants of state-of-the-art CNN architectures, evaluated on the CIFAR10 and ILSVRC datasets. Our results show similar or higher accuracy than the baseline architectures with much less computation, as measured by CPU and GPU timings. For example, for ResNet 50, our model has 40% fewer parameters, 45% fewer floating point operations, and is 31% (12%) faster on a CPU (GPU). For the deeper ResNet 200 our model has 25% fewer floating point operations and 44% fewer parameters, while maintaining state-of-the-art accuracy. For GoogLeNet, our model has 7% fewer parameters and is 21% (16%) faster on a CPU (GPU). |
| Tasks | |
| Published | 2016-05-20 |
| URL | http://arxiv.org/abs/1605.06489v3 |
| http://arxiv.org/pdf/1605.06489v3.pdf | |
| PWC | https://paperswithcode.com/paper/deep-roots-improving-cnn-efficiency-with |
| Repo | |
| Framework | |
Accelerating the BSM interpretation of LHC data with machine learning
| Title | Accelerating the BSM interpretation of LHC data with machine learning |
| Authors | Gianfranco Bertone, Marc Peter Deisenroth, Jong Soo Kim, Sebastian Liem, Roberto Ruiz de Austri, Max Welling |
| Abstract | The interpretation of Large Hadron Collider (LHC) data in the framework of Beyond the Standard Model (BSM) theories is hampered by the need to run computationally expensive event generators and detector simulators. Performing statistically convergent scans of high-dimensional BSM theories is consequently challenging, and in practice unfeasible for very high-dimensional BSM theories. We present here a new machine learning method that accelerates the interpretation of LHC data, by learning the relationship between BSM theory parameters and data. As a proof-of-concept, we demonstrate that this technique accurately predicts natural SUSY signal events in two signal regions at the High Luminosity LHC, up to four orders of magnitude faster than standard techniques. The new approach makes it possible to rapidly and accurately reconstruct the theory parameters of complex BSM theories, should an excess in the data be discovered at the LHC. |
| Tasks | |
| Published | 2016-11-08 |
| URL | http://arxiv.org/abs/1611.02704v1 |
| http://arxiv.org/pdf/1611.02704v1.pdf | |
| PWC | https://paperswithcode.com/paper/accelerating-the-bsm-interpretation-of-lhc |
| Repo | |
| Framework | |
A modified Physarum-inspired model for the user equilibrium traffic assignment problem
| Title | A modified Physarum-inspired model for the user equilibrium traffic assignment problem |
| Authors | Shuai Xu, Wen Jiang, Yehang Shou |
| Abstract | The user equilibrium traffic assignment principle is very important in the traffic assignment problem. Mathematical programming models are designed to solve the user equilibrium problem in traditional algorithms. Recently, the Physarum shows the ability to address the user equilibrium and system optimization traffic assignment problems. However, the Physarum model are not efficient in real traffic networks with two-way traffic characteristics and multiple origin-destination pairs. In this article, a modified Physarum-inspired model for the user equilibrium problem is proposed. By decomposing traffic flux based on origin nodes, the traffic flux from different origin-destination pairs can be distinguished in the proposed model. The Physarum can obtain the equilibrium traffic flux when no shorter path can be discovered between each origin-destination pair. Finally, numerical examples use the Sioux Falls network to demonstrate the rationality and convergence properties of the proposed model. |
| Tasks | |
| Published | 2016-12-19 |
| URL | http://arxiv.org/abs/1612.06174v1 |
| http://arxiv.org/pdf/1612.06174v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-modified-physarum-inspired-model-for-the |
| Repo | |
| Framework | |
