Paper Group ANR 523
Spoofing 2D Face Detection: Machines See People Who Aren’t There. Training Neural Networks Without Gradients: A Scalable ADMM Approach. Model-Free Trajectory-based Policy Optimization with Monotonic Improvement. A Neural Architecture Mimicking Humans End-to-End for Natural Language Inference. Automatic TM Cleaning through MT and POS Tagging: Autode …
Spoofing 2D Face Detection: Machines See People Who Aren’t There
| Title | Spoofing 2D Face Detection: Machines See People Who Aren’t There |
| Authors | Michael McCoyd, David Wagner |
| Abstract | Machine learning is increasingly used to make sense of the physical world yet may suffer from adversarial manipulation. We examine the Viola-Jones 2D face detection algorithm to study whether images can be created that humans do not notice as faces yet the algorithm detects as faces. We show that it is possible to construct images that Viola-Jones recognizes as containing faces yet no human would consider a face. Moreover, we show that it is possible to construct images that fool facial detection even when they are printed and then photographed. |
| Tasks | Face Detection |
| Published | 2016-08-06 |
| URL | http://arxiv.org/abs/1608.02128v1 |
| http://arxiv.org/pdf/1608.02128v1.pdf | |
| PWC | https://paperswithcode.com/paper/spoofing-2d-face-detection-machines-see |
| Repo | |
| Framework | |
Training Neural Networks Without Gradients: A Scalable ADMM Approach
| Title | Training Neural Networks Without Gradients: A Scalable ADMM Approach |
| Authors | Gavin Taylor, Ryan Burmeister, Zheng Xu, Bharat Singh, Ankit Patel, Tom Goldstein |
| Abstract | With the growing importance of large network models and enormous training datasets, GPUs have become increasingly necessary to train neural networks. This is largely because conventional optimization algorithms rely on stochastic gradient methods that don’t scale well to large numbers of cores in a cluster setting. Furthermore, the convergence of all gradient methods, including batch methods, suffers from common problems like saturation effects, poor conditioning, and saddle points. This paper explores an unconventional training method that uses alternating direction methods and Bregman iteration to train networks without gradient descent steps. The proposed method reduces the network training problem to a sequence of minimization sub-steps that can each be solved globally in closed form. The proposed method is advantageous because it avoids many of the caveats that make gradient methods slow on highly non-convex problems. The method exhibits strong scaling in the distributed setting, yielding linear speedups even when split over thousands of cores. |
| Tasks | |
| Published | 2016-05-06 |
| URL | http://arxiv.org/abs/1605.02026v1 |
| http://arxiv.org/pdf/1605.02026v1.pdf | |
| PWC | https://paperswithcode.com/paper/training-neural-networks-without-gradients-a |
| Repo | |
| Framework | |
Model-Free Trajectory-based Policy Optimization with Monotonic Improvement
| Title | Model-Free Trajectory-based Policy Optimization with Monotonic Improvement |
| Authors | Riad Akrour, Abbas Abdolmaleki, Hany Abdulsamad, Jan Peters, Gerhard Neumann |
| Abstract | Many of the recent trajectory optimization algorithms alternate between linear approximation of the system dynamics around the mean trajectory and conservative policy update. One way of constraining the policy change is by bounding the Kullback-Leibler (KL) divergence between successive policies. These approaches already demonstrated great experimental success in challenging problems such as end-to-end control of physical systems. However, the linear approximation of the system dynamics can introduce a bias in the policy update and prevent convergence to the optimal policy. In this article, we propose a new model-free trajectory-based policy optimization algorithm with guaranteed monotonic improvement. The algorithm backpropagates a local, quadratic and time-dependent \qfunc~learned from trajectory data instead of a model of the system dynamics. Our policy update ensures exact KL-constraint satisfaction without simplifying assumptions on the system dynamics. We experimentally demonstrate on highly non-linear control tasks the improvement in performance of our algorithm in comparison to approaches linearizing the system dynamics. In order to show the monotonic improvement of our algorithm, we additionally conduct a theoretical analysis of our policy update scheme to derive a lower bound of the change in policy return between successive iterations. |
| Tasks | |
| Published | 2016-06-29 |
| URL | http://arxiv.org/abs/1606.09197v4 |
| http://arxiv.org/pdf/1606.09197v4.pdf | |
| PWC | https://paperswithcode.com/paper/model-free-trajectory-based-policy |
| Repo | |
| Framework | |
A Neural Architecture Mimicking Humans End-to-End for Natural Language Inference
| Title | A Neural Architecture Mimicking Humans End-to-End for Natural Language Inference |
| Authors | Biswajit Paria, K. M. Annervaz, Ambedkar Dukkipati, Ankush Chatterjee, Sanjay Podder |
| Abstract | In this work we use the recent advances in representation learning to propose a neural architecture for the problem of natural language inference. Our approach is aligned to mimic how a human does the natural language inference process given two statements. The model uses variants of Long Short Term Memory (LSTM), attention mechanism and composable neural networks, to carry out the task. Each part of our model can be mapped to a clear functionality humans do for carrying out the overall task of natural language inference. The model is end-to-end differentiable enabling training by stochastic gradient descent. On Stanford Natural Language Inference(SNLI) dataset, the proposed model achieves better accuracy numbers than all published models in literature. |
| Tasks | Natural Language Inference, Representation Learning |
| Published | 2016-11-15 |
| URL | http://arxiv.org/abs/1611.04741v2 |
| http://arxiv.org/pdf/1611.04741v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-neural-architecture-mimicking-humans-end-to |
| Repo | |
| Framework | |
Automatic TM Cleaning through MT and POS Tagging: Autodesk’s Submission to the NLP4TM 2016 Shared Task
| Title | Automatic TM Cleaning through MT and POS Tagging: Autodesk’s Submission to the NLP4TM 2016 Shared Task |
| Authors | Alena Zwahlen, Olivier Carnal, Samuel Läubli |
| Abstract | We describe a machine learning based method to identify incorrect entries in translation memories. It extends previous work by Barbu (2015) through incorporating recall-based machine translation and part-of-speech-tagging features. Our system ranked first in the Binary Classification (II) task for two out of three language pairs: English-Italian and English-Spanish. |
| Tasks | Machine Translation, Part-Of-Speech Tagging |
| Published | 2016-05-19 |
| URL | http://arxiv.org/abs/1605.05906v1 |
| http://arxiv.org/pdf/1605.05906v1.pdf | |
| PWC | https://paperswithcode.com/paper/automatic-tm-cleaning-through-mt-and-pos |
| Repo | |
| Framework | |
Optimization of Convolutional Neural Network using Microcanonical Annealing Algorithm
| Title | Optimization of Convolutional Neural Network using Microcanonical Annealing Algorithm |
| Authors | Vina Ayumi, L. M. Rasdi Rere, Mohamad Ivan Fanany, Aniati Murni Arymurthy |
| Abstract | Convolutional neural network (CNN) is one of the most prominent architectures and algorithm in Deep Learning. It shows a remarkable improvement in the recognition and classification of objects. This method has also been proven to be very effective in a variety of computer vision and machine learning problems. As in other deep learning, however, training the CNN is interesting yet challenging. Recently, some metaheuristic algorithms have been used to optimize CNN using Genetic Algorithm, Particle Swarm Optimization, Simulated Annealing and Harmony Search. In this paper, another type of metaheuristic algorithms with different strategy has been proposed, i.e. Microcanonical Annealing to optimize Convolutional Neural Network. The performance of the proposed method is tested using the MNIST and CIFAR-10 datasets. Although experiment results of MNIST dataset indicate the increase in computation time (1.02x - 1.38x), nevertheless this proposed method can considerably enhance the performance of the original CNN (up to 4.60%). On the CIFAR10 dataset, currently, state of the art is 96.53% using fractional pooling, while this proposed method achieves 99.14%. |
| Tasks | |
| Published | 2016-10-07 |
| URL | http://arxiv.org/abs/1610.02306v1 |
| http://arxiv.org/pdf/1610.02306v1.pdf | |
| PWC | https://paperswithcode.com/paper/optimization-of-convolutional-neural-network |
| Repo | |
| Framework | |
Distributed Estimation of the Operating State of a Single-Bus DC MicroGrid without an External Communication Interface
| Title | Distributed Estimation of the Operating State of a Single-Bus DC MicroGrid without an External Communication Interface |
| Authors | Marko Angjelichinoski, Anna Scaglione, Petar Popovski, Cedomir Stefanovic |
| Abstract | We propose a decentralized Maximum Likelihood solution for estimating the stochastic renewable power generation and demand in single bus Direct Current (DC) MicroGrids (MGs), with high penetration of droop controlled power electronic converters. The solution relies on the fact that the primary control parameters are set in accordance with the local power generation status of the generators. Therefore, the steady state voltage is inherently dependent on the generation capacities and the load, through a non-linear parametric model, which can be estimated. To have a well conditioned estimation problem, our solution avoids the use of an external communication interface and utilizes controlled voltage disturbances to perform distributed training. Using this tool, we develop an efficient, decentralized Maximum Likelihood Estimator (MLE) and formulate the sufficient condition for the existence of the globally optimal solution. The numerical results illustrate the promising performance of our MLE algorithm. |
| Tasks | |
| Published | 2016-09-14 |
| URL | http://arxiv.org/abs/1609.04623v1 |
| http://arxiv.org/pdf/1609.04623v1.pdf | |
| PWC | https://paperswithcode.com/paper/distributed-estimation-of-the-operating-state |
| Repo | |
| Framework | |
Robust Structure from Motion in the Presence of Outliers and Missing Data
| Title | Robust Structure from Motion in the Presence of Outliers and Missing Data |
| Authors | Guanghui Wang |
| Abstract | Structure from motion is an import theme in computer vision. Although great progress has been made both in theory and applications, most of the algorithms only work for static scenes and rigid objects. In recent years, structure and motion recovery of non-rigid objects and dynamic scenes have received a lot of attention. In this paper, the state-of-the-art techniques for structure and motion factorization of non-rigid objects are reviewed and discussed. First, an introduction of the structure from motion problem is presented, followed by a general formulation of non-rigid structure from motion. Second, an augmented affined factorization framework, by using homogeneous representation, is presented to solve the registration issue in the presence of outlying and missing data. Third, based on the observation that the reprojection residuals of outliers are significantly larger than those of inliers, a robust factorization strategy with outlier rejection is proposed by means of the reprojection residuals, followed by some comparative experimental evaluations. Finally, some future research topics in non-rigid structure from motion are discussed. |
| Tasks | |
| Published | 2016-09-09 |
| URL | http://arxiv.org/abs/1609.02638v2 |
| http://arxiv.org/pdf/1609.02638v2.pdf | |
| PWC | https://paperswithcode.com/paper/robust-structure-from-motion-in-the-presence |
| Repo | |
| Framework | |
A New Type-II Fuzzy Logic Based Controller for Non-linear Dynamical Systems with Application to a 3-PSP Parallel Robot
| Title | A New Type-II Fuzzy Logic Based Controller for Non-linear Dynamical Systems with Application to a 3-PSP Parallel Robot |
| Authors | Hamid Reza Hassanzadeh |
| Abstract | The concept of uncertainty is posed in almost any complex system including parallel robots as an outstanding instance of dynamical robotics systems. As suggested by the name, uncertainty, is some missing information that is beyond the knowledge of human thus we may tend to handle it properly to minimize the side-effects through the control process. Type-II fuzzy logic has shown its superiority over traditional fuzzy logic when dealing with uncertainty. Type-II fuzzy logic controllers are however newer and more promising approaches that have been recently applied to various fields due to their significant contribution especially when noise (as an important instance of uncertainty) emerges. During the design of Type-I fuzzy logic systems, we presume that we are almost certain about the fuzzy membership functions which is not true in many cases. Thus T2FLS as a more realistic approach dealing with practical applications might have a lot to offer. Type-II fuzzy logic takes into account a higher level of uncertainty, in other words, the membership grade for a type-II fuzzy variable is no longer a crisp number but rather is itself a type-I linguistic term. In this thesis the effects of uncertainty in dynamic control of a parallel robot is considered. More specifically, it is intended to incorporate the Type-II Fuzzy Logic paradigm into a model based controller, the so-called computed torque control method, and apply the result to a 3 degrees of freedom parallel manipulator. … |
| Tasks | |
| Published | 2016-12-05 |
| URL | http://arxiv.org/abs/1612.01399v1 |
| http://arxiv.org/pdf/1612.01399v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-new-type-ii-fuzzy-logic-based-controller |
| Repo | |
| Framework | |
Subspace Clustering Based Tag Sharing for Inductive Tag Matrix Refinement with Complex Errors
| Title | Subspace Clustering Based Tag Sharing for Inductive Tag Matrix Refinement with Complex Errors |
| Authors | Yuqing Hou, Zhouchen Lin, Jin-ge Yao |
| Abstract | Annotating images with tags is useful for indexing and retrieving images. However, many available annotation data include missing or inaccurate annotations. In this paper, we propose an image annotation framework which sequentially performs tag completion and refinement. We utilize the subspace property of data via sparse subspace clustering for tag completion. Then we propose a novel matrix completion model for tag refinement, integrating visual correlation, semantic correlation and the novelly studied property of complex errors. The proposed method outperforms the state-of-the-art approaches on multiple benchmark datasets even when they contain certain levels of annotation noise. |
| Tasks | Matrix Completion |
| Published | 2016-01-12 |
| URL | http://arxiv.org/abs/1601.03055v3 |
| http://arxiv.org/pdf/1601.03055v3.pdf | |
| PWC | https://paperswithcode.com/paper/subspace-clustering-based-tag-sharing-for |
| Repo | |
| Framework | |
Utilizing High-level Visual Feature for Indoor Shopping Mall Navigation
| Title | Utilizing High-level Visual Feature for Indoor Shopping Mall Navigation |
| Authors | Ziwei Xu, Haitian Zheng, Minjian Pang, Yangchun Zhu, Xiongfei Su, Guyue Zhou, Lu Fang |
| Abstract | Towards robust and convenient indoor shopping mall navigation, we propose a novel learning-based scheme to utilize the high-level visual information from the storefront images captured by personal devices of users. Specifically, we decompose the visual navigation problem into localization and map generation respectively. Given a storefront input image, a novel feature fusion scheme (denoted as FusionNet) is proposed by fusing the distinguishing DNN-based appearance feature and text feature for robust recognition of store brands, which serves for accurate localization. Regarding the map generation, we convert the user-captured indicator map of the shopping mall into a topological map by parsing the stores and their connectivity. Experimental results conducted on the real shopping malls demonstrate that the proposed system achieves robust localization and precise map generation, enabling accurate navigation. |
| Tasks | Visual Navigation |
| Published | 2016-10-06 |
| URL | http://arxiv.org/abs/1610.01906v4 |
| http://arxiv.org/pdf/1610.01906v4.pdf | |
| PWC | https://paperswithcode.com/paper/utilizing-high-level-visual-feature-for |
| Repo | |
| Framework | |
Causal inference for data-driven debugging and decision making in cloud computing
| Title | Causal inference for data-driven debugging and decision making in cloud computing |
| Authors | Philipp Geiger, Lucian Carata, Bernhard Schoelkopf |
| Abstract | Cloud computing involves complex technical and economical systems and interactions. This brings about various challenges, two of which are: (1) debugging and control to optimize the performance of computing systems, with the help of sandbox experiments, and (2) privacy-preserving prediction of the cost of spot'' resources for decision making of cloud clients. In this paper, we formalize debugging by counterfactual probabilities and control by post-(soft-)interventional probabilities. We prove that counterfactuals can approximately be calculated from a stochastic’’ graphical causal model (while they are originally defined only for deterministic'' functional causal models), and based on this sketch a data-driven approach to address problem (1). To address problem (2), we formalize bidding by post-(soft-)interventional probabilities and present a simple mathematical result on approximate integration of incomplete’’ conditional probability distributions. We show how this can be used by cloud clients to trade off privacy against predictability of the outcome of their bidding actions in a toy scenario. We report experiments on simulated and real data. |
| Tasks | Causal Inference, Decision Making |
| Published | 2016-03-04 |
| URL | https://arxiv.org/abs/1603.01581v8 |
| https://arxiv.org/pdf/1603.01581v8.pdf | |
| PWC | https://paperswithcode.com/paper/causal-inference-for-cloud-computing |
| Repo | |
| Framework | |
Optimizing Gaze Direction in a Visual Navigation Task
| Title | Optimizing Gaze Direction in a Visual Navigation Task |
| Authors | Tuomas Välimäki, Risto Ritala |
| Abstract | Navigation in an unknown environment consists of multiple separable subtasks, such as collecting information about the surroundings and navigating to the current goal. In the case of pure visual navigation, all these subtasks need to utilize the same vision system, and therefore a way to optimally control the direction of focus is needed. We present a case study, where we model the active sensing problem of directing the gaze of a mobile robot with three machine vision cameras as a partially observable Markov decision process (POMDP) using a mutual information (MI) based reward function. The key aspect of the solution is that the cameras are dynamically used either in monocular or stereo configuration. The benefits of using the proposed active sensing implementation are demonstrated with simulations and experiments on a real robot. |
| Tasks | Visual Navigation |
| Published | 2016-02-16 |
| URL | http://arxiv.org/abs/1602.04981v1 |
| http://arxiv.org/pdf/1602.04981v1.pdf | |
| PWC | https://paperswithcode.com/paper/optimizing-gaze-direction-in-a-visual |
| Repo | |
| Framework | |
Small-Variance Nonparametric Clustering on the Hypersphere
| Title | Small-Variance Nonparametric Clustering on the Hypersphere |
| Authors | Julian Straub, Trevor Campbell, Jonathan P. How, John W. Fisher III |
| Abstract | Structural regularities in man-made environments reflect in the distribution of their surface normals. Describing these surface normal distributions is important in many computer vision applications, such as scene understanding, plane segmentation, and regularization of 3D reconstructions. Based on the small-variance limit of Bayesian nonparametric von-Mises-Fisher (vMF) mixture distributions, we propose two new flexible and efficient k-means-like clustering algorithms for directional data such as surface normals. The first, DP-vMF-means, is a batch clustering algorithm derived from the Dirichlet process (DP) vMF mixture. Recognizing the sequential nature of data collection in many applications, we extend this algorithm to DDP-vMF-means, which infers temporally evolving cluster structure from streaming data. Both algorithms naturally respect the geometry of directional data, which lies on the unit sphere. We demonstrate their performance on synthetic directional data and real 3D surface normals from RGB-D sensors. While our experiments focus on 3D data, both algorithms generalize to high dimensional directional data such as protein backbone configurations and semantic word vectors. |
| Tasks | Scene Understanding |
| Published | 2016-07-21 |
| URL | http://arxiv.org/abs/1607.06407v1 |
| http://arxiv.org/pdf/1607.06407v1.pdf | |
| PWC | https://paperswithcode.com/paper/small-variance-nonparametric-clustering-on |
| Repo | |
| Framework | |
Persistent Homology on Grassmann Manifolds for Analysis of Hyperspectral Movies
| Title | Persistent Homology on Grassmann Manifolds for Analysis of Hyperspectral Movies |
| Authors | Sofya Chepushtanova, Michael Kirby, Chris Peterson, Lori Ziegelmeier |
| Abstract | The existence of characteristic structure, or shape, in complex data sets has been recognized as increasingly important for mathematical data analysis. This realization has motivated the development of new tools such as persistent homology for exploring topological invariants, or features, in large data sets. In this paper we apply persistent homology to the characterization of gas plumes in time dependent sequences of hyperspectral cubes, i.e. the analysis of 4-way arrays. We investigate hyperspectral movies of Long-Wavelength Infrared data monitoring an experimental release of chemical simulant into the air. Our approach models regions of interest within the hyperspectral data cubes as points on the real Grassmann manifold $G(k, n)$ (whose points parameterize the $k$-dimensional subspaces of $\mathbb{R}^n$), contrasting our approach with the more standard framework in Euclidean space. An advantage of this approach is that it allows a sequence of time slices in a hyperspectral movie to be collapsed to a sequence of points in such a way that some of the key structure within and between the slices is encoded by the points on the Grassmann manifold. This motivates the search for topological features, associated with the evolution of the frames of a hyperspectral movie, within the corresponding points on the Grassmann manifold. The proposed mathematical model affords the processing of large data sets while retaining valuable discriminatory information. In this paper, we discuss how embedding our data in the Grassmann manifold, together with topological data analysis, captures dynamical events that occur as the chemical plume is released and evolves. |
| Tasks | Topological Data Analysis |
| Published | 2016-07-07 |
| URL | http://arxiv.org/abs/1607.02196v2 |
| http://arxiv.org/pdf/1607.02196v2.pdf | |
| PWC | https://paperswithcode.com/paper/persistent-homology-on-grassmann-manifolds |
| Repo | |
| Framework | |
