Paper Group ANR 17
On Face Segmentation, Face Swapping, and Face Perception. Belief Propagation, Bethe Approximation and Polynomials. High Accuracy Classification of Parkinson’s Disease through Shape Analysis and Surface Fitting in $^{123}$I-Ioflupane SPECT Imaging. A Multi-Armed Bandit to Smartly Select a Training Set from Big Medical Data. Interpreting Convolutiona …
On Face Segmentation, Face Swapping, and Face Perception
| Title | On Face Segmentation, Face Swapping, and Face Perception |
| Authors | Yuval Nirkin, Iacopo Masi, Anh Tuan Tran, Tal Hassner, Gerard Medioni |
| Abstract | We show that even when face images are unconstrained and arbitrarily paired, face swapping between them is actually quite simple. To this end, we make the following contributions. (a) Instead of tailoring systems for face segmentation, as others previously proposed, we show that a standard fully convolutional network (FCN) can achieve remarkably fast and accurate segmentations, provided that it is trained on a rich enough example set. For this purpose, we describe novel data collection and generation routines which provide challenging segmented face examples. (b) We use our segmentations to enable robust face swapping under unprecedented conditions. (c) Unlike previous work, our swapping is robust enough to allow for extensive quantitative tests. To this end, we use the Labeled Faces in the Wild (LFW) benchmark and measure the effect of intra- and inter-subject face swapping on recognition. We show that our intra-subject swapped faces remain as recognizable as their sources, testifying to the effectiveness of our method. In line with well known perceptual studies, we show that better face swapping produces less recognizable inter-subject results. This is the first time this effect was quantitatively demonstrated for machine vision systems. |
| Tasks | Face Swapping |
| Published | 2017-04-22 |
| URL | http://arxiv.org/abs/1704.06729v1 |
| http://arxiv.org/pdf/1704.06729v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-face-segmentation-face-swapping-and-face |
| Repo | |
| Framework | |
Belief Propagation, Bethe Approximation and Polynomials
| Title | Belief Propagation, Bethe Approximation and Polynomials |
| Authors | Damian Straszak, Nisheeth K. Vishnoi |
| Abstract | Factor graphs are important models for succinctly representing probability distributions in machine learning, coding theory, and statistical physics. Several computational problems, such as computing marginals and partition functions, arise naturally when working with factor graphs. Belief propagation is a widely deployed iterative method for solving these problems. However, despite its significant empirical success, not much is known about the correctness and efficiency of belief propagation. Bethe approximation is an optimization-based framework for approximating partition functions. While it is known that the stationary points of the Bethe approximation coincide with the fixed points of belief propagation, in general, the relation between the Bethe approximation and the partition function is not well understood. It has been observed that for a few classes of factor graphs, the Bethe approximation always gives a lower bound to the partition function, which distinguishes them from the general case, where neither a lower bound, nor an upper bound holds universally. This has been rigorously proved for permanents and for attractive graphical models. Here we consider bipartite normal factor graphs and show that if the local constraints satisfy a certain analytic property, the Bethe approximation is a lower bound to the partition function. We arrive at this result by viewing factor graphs through the lens of polynomials. In this process, we reformulate the Bethe approximation as a polynomial optimization problem. Our sufficient condition for the lower bound property to hold is inspired by recent developments in the theory of real stable polynomials. We believe that this way of viewing factor graphs and its connection to real stability might lead to a better understanding of belief propagation and factor graphs in general. |
| Tasks | |
| Published | 2017-08-08 |
| URL | http://arxiv.org/abs/1708.02581v1 |
| http://arxiv.org/pdf/1708.02581v1.pdf | |
| PWC | https://paperswithcode.com/paper/belief-propagation-bethe-approximation-and |
| Repo | |
| Framework | |
High Accuracy Classification of Parkinson’s Disease through Shape Analysis and Surface Fitting in $^{123}$I-Ioflupane SPECT Imaging
| Title | High Accuracy Classification of Parkinson’s Disease through Shape Analysis and Surface Fitting in $^{123}$I-Ioflupane SPECT Imaging |
| Authors | R. Prashanth, Sumantra Dutta Roy, Pravat K. Mandal, Shantanu Ghosh |
| Abstract | Early and accurate identification of parkinsonian syndromes (PS) involving presynaptic degeneration from non-degenerative variants such as Scans Without Evidence of Dopaminergic Deficit (SWEDD) and tremor disorders, is important for effective patient management as the course, therapy and prognosis differ substantially between the two groups. In this study, we use Single Photon Emission Computed Tomography (SPECT) images from healthy normal, early PD and SWEDD subjects, as obtained from the Parkinson’s Progression Markers Initiative (PPMI) database, and process them to compute shape- and surface fitting-based features for the three groups. We use these features to develop and compare various classification models that can discriminate between scans showing dopaminergic deficit, as in PD, from scans without the deficit, as in healthy normal or SWEDD. Along with it, we also compare these features with Striatal Binding Ratio (SBR)-based features, which are well-established and clinically used, by computing a feature importance score using Random forests technique. We observe that the Support Vector Machine (SVM) classifier gave the best performance with an accuracy of 97.29%. These features also showed higher importance than the SBR-based features. We infer from the study that shape analysis and surface fitting are useful and promising methods for extracting discriminatory features that can be used to develop diagnostic models that might have the potential to help clinicians in the diagnostic process. |
| Tasks | Feature Importance |
| Published | 2017-03-04 |
| URL | http://arxiv.org/abs/1703.01526v1 |
| http://arxiv.org/pdf/1703.01526v1.pdf | |
| PWC | https://paperswithcode.com/paper/high-accuracy-classification-of-parkinsons |
| Repo | |
| Framework | |
A Multi-Armed Bandit to Smartly Select a Training Set from Big Medical Data
| Title | A Multi-Armed Bandit to Smartly Select a Training Set from Big Medical Data |
| Authors | Benjamín Gutiérrez, Loïc Peter, Tassilo Klein, Christian Wachinger |
| Abstract | With the availability of big medical image data, the selection of an adequate training set is becoming more important to address the heterogeneity of different datasets. Simply including all the data does not only incur high processing costs but can even harm the prediction. We formulate the smart and efficient selection of a training dataset from big medical image data as a multi-armed bandit problem, solved by Thompson sampling. Our method assumes that image features are not available at the time of the selection of the samples, and therefore relies only on meta information associated with the images. Our strategy simultaneously exploits data sources with high chances of yielding useful samples and explores new data regions. For our evaluation, we focus on the application of estimating the age from a brain MRI. Our results on 7,250 subjects from 10 datasets show that our approach leads to higher accuracy while only requiring a fraction of the training data. |
| Tasks | |
| Published | 2017-05-23 |
| URL | http://arxiv.org/abs/1705.08111v2 |
| http://arxiv.org/pdf/1705.08111v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-multi-armed-bandit-to-smartly-select-a |
| Repo | |
| Framework | |
Interpreting Convolutional Neural Networks Through Compression
| Title | Interpreting Convolutional Neural Networks Through Compression |
| Authors | Reza Abbasi-Asl, Bin Yu |
| Abstract | Convolutional neural networks (CNNs) achieve state-of-the-art performance in a wide variety of tasks in computer vision. However, interpreting CNNs still remains a challenge. This is mainly due to the large number of parameters in these networks. Here, we investigate the role of compression and particularly pruning filters in the interpretation of CNNs. We exploit our recently-proposed greedy structural compression scheme that prunes filters in a trained CNN. In our compression, the filter importance index is defined as the classification accuracy reduction (CAR) of the network after pruning that filter. The filters are then iteratively pruned based on the CAR index. We demonstrate the interpretability of CAR-compressed CNNs by showing that our algorithm prunes filters with visually redundant pattern selectivity. Specifically, we show the importance of shape-selective filters for object recognition, as opposed to color-selective filters. Out of top 20 CAR-pruned filters in AlexNet, 17 of them in the first layer and 14 of them in the second layer are color-selective filters. Finally, we introduce a variant of our CAR importance index that quantifies the importance of each image class to each CNN filter. We show that the most and the least important class labels present a meaningful interpretation of each filter that is consistent with the visualized pattern selectivity of that filter. |
| Tasks | Object Recognition |
| Published | 2017-11-07 |
| URL | http://arxiv.org/abs/1711.02329v1 |
| http://arxiv.org/pdf/1711.02329v1.pdf | |
| PWC | https://paperswithcode.com/paper/interpreting-convolutional-neural-networks |
| Repo | |
| Framework | |
Semi-supervised cross-entropy clustering with information bottleneck constraint
| Title | Semi-supervised cross-entropy clustering with information bottleneck constraint |
| Authors | Marek Śmieja, Bernhard C. Geiger |
| Abstract | In this paper, we propose a semi-supervised clustering method, CEC-IB, that models data with a set of Gaussian distributions and that retrieves clusters based on a partial labeling provided by the user (partition-level side information). By combining the ideas from cross-entropy clustering (CEC) with those from the information bottleneck method (IB), our method trades between three conflicting goals: the accuracy with which the data set is modeled, the simplicity of the model, and the consistency of the clustering with side information. Experiments demonstrate that CEC-IB has a performance comparable to Gaussian mixture models (GMM) in a classical semi-supervised scenario, but is faster, more robust to noisy labels, automatically determines the optimal number of clusters, and performs well when not all classes are present in the side information. Moreover, in contrast to other semi-supervised models, it can be successfully applied in discovering natural subgroups if the partition-level side information is derived from the top levels of a hierarchical clustering. |
| Tasks | |
| Published | 2017-05-03 |
| URL | http://arxiv.org/abs/1705.01601v1 |
| http://arxiv.org/pdf/1705.01601v1.pdf | |
| PWC | https://paperswithcode.com/paper/semi-supervised-cross-entropy-clustering-with |
| Repo | |
| Framework | |
Online Factorization and Partition of Complex Networks From Random Walks
| Title | Online Factorization and Partition of Complex Networks From Random Walks |
| Authors | Lin F. Yang, Vladimir Braverman, Tuo Zhao, Mengdi Wang |
| Abstract | Finding the reduced-dimensional structure is critical to understanding complex networks. Existing approaches such as spectral clustering are applicable only when the full network is explicitly observed. In this paper, we focus on the online factorization and partition of implicit large-scale networks based on observations from an associated random walk. We formulate this into a nonconvex stochastic factorization problem and propose an efficient and scalable stochastic generalized Hebbian algorithm. The algorithm is able to process dependent state-transition data dynamically generated by the underlying network and learn a low-dimensional representation for each vertex. By applying a diffusion approximation analysis, we show that the continuous-time limiting process of the stochastic algorithm converges globally to the “principal components” of the Markov chain and achieves a nearly optimal sample complexity. Once given the learned low-dimensional representations, we further apply clustering techniques to recover the network partition. We show that when the associated Markov process is lumpable, one can recover the partition exactly with high probability. We apply the proposed approach to model the traffic flow of Manhattan as city-wide random walks. By using our algorithm to analyze the taxi trip data, we discover a latent partition of the Manhattan city that closely matches the traffic dynamics. |
| Tasks | |
| Published | 2017-05-22 |
| URL | http://arxiv.org/abs/1705.07881v4 |
| http://arxiv.org/pdf/1705.07881v4.pdf | |
| PWC | https://paperswithcode.com/paper/online-factorization-and-partition-of-complex |
| Repo | |
| Framework | |
Learning a Repression Network for Precise Vehicle Search
| Title | Learning a Repression Network for Precise Vehicle Search |
| Authors | Qiantong Xu, Ke Yan, Yonghong Tian |
| Abstract | The growing explosion in the use of surveillance cameras in public security highlights the importance of vehicle search from large-scale image databases. Precise vehicle search, aiming at finding out all instances for a given query vehicle image, is a challenging task as different vehicles will look very similar to each other if they share same visual attributes. To address this problem, we propose the Repression Network (RepNet), a novel multi-task learning framework, to learn discriminative features for each vehicle image from both coarse-grained and detailed level simultaneously. Besides, benefited from the satisfactory accuracy of attribute classification, a bucket search method is proposed to reduce the retrieval time while still maintaining competitive performance. We conduct extensive experiments on the revised VehcileID dataset. Experimental results show that our RepNet achieves the state-of-the-art performance and the bucket search method can reduce the retrieval time by about 24 times. |
| Tasks | Multi-Task Learning |
| Published | 2017-08-08 |
| URL | http://arxiv.org/abs/1708.02386v1 |
| http://arxiv.org/pdf/1708.02386v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-a-repression-network-for-precise |
| Repo | |
| Framework | |
Best-Choice Edge Grafting for Efficient Structure Learning of Markov Random Fields
| Title | Best-Choice Edge Grafting for Efficient Structure Learning of Markov Random Fields |
| Authors | Walid Chaabene, Bert Huang |
| Abstract | Incremental methods for structure learning of pairwise Markov random fields (MRFs), such as grafting, improve scalability by avoiding inference over the entire feature space in each optimization step. Instead, inference is performed over an incrementally grown active set of features. In this paper, we address key computational bottlenecks that current incremental techniques still suffer by introducing best-choice edge grafting, an incremental, structured method that activates edges as groups of features in a streaming setting. The method uses a reservoir of edges that satisfy an activation condition, approximating the search for the optimal edge to activate. It also reorganizes the search space using search-history and structure heuristics. Experiments show a significant speedup for structure learning and a controllable trade-off between the speed and quality of learning. |
| Tasks | |
| Published | 2017-05-25 |
| URL | http://arxiv.org/abs/1705.09026v2 |
| http://arxiv.org/pdf/1705.09026v2.pdf | |
| PWC | https://paperswithcode.com/paper/best-choice-edge-grafting-for-efficient |
| Repo | |
| Framework | |
Critical Contours: An Invariant Linking Image Flow with Salient Surface Organization
| Title | Critical Contours: An Invariant Linking Image Flow with Salient Surface Organization |
| Authors | Benjamin S. Kunsberg, Steven W. Zucker |
| Abstract | We exploit a key result from visual psychophysics—that individuals perceive shape qualitatively—to develop the use of a geometrical/topological “invariant’’ (the Morse–Smale complex) relating image structure with surface structure. Differences across individuals are minimal near certain configurations such as ridges and boundaries, and it is these configurations that are often represented in line drawings. In particular, we introduce a method for inferring a qualitative three-dimensional shape from shading patterns that link the shape-from-shading inference with shape-from-contour inference. For a given shape, certain shading patches approach “line drawings’’ in a well-defined limit. Under this limit, and invariably with respect to rendering choices, these shading patterns provide a qualitative description of the surface. We further show that, under this model, the contours partition the surface into meaningful parts using the Morse–Smale complex. These critical contours are the (perceptually) stable parts of this complex and are invariant over a wide class of rendering models. Intuitively, our main result shows that critical contours partition smooth surfaces into bumps and valleys, in effect providing a scaffold on the image from which a full surface can be interpolated. |
| Tasks | |
| Published | 2017-05-20 |
| URL | http://arxiv.org/abs/1705.07329v2 |
| http://arxiv.org/pdf/1705.07329v2.pdf | |
| PWC | https://paperswithcode.com/paper/critical-contours-an-invariant-linking-image |
| Repo | |
| Framework | |
A Deep Learning Approach to Drone Monitoring
| Title | A Deep Learning Approach to Drone Monitoring |
| Authors | Yueru Chen, Pranav Aggarwal, Jongmoo Choi, C. -C. Jay Kuo |
| Abstract | A drone monitoring system that integrates deep-learning-based detection and tracking modules is proposed in this work. The biggest challenge in adopting deep learning methods for drone detection is the limited amount of training drone images. To address this issue, we develop a model-based drone augmentation technique that automatically generates drone images with a bounding box label on drone’s location. To track a small flying drone, we utilize the residual information between consecutive image frames. Finally, we present an integrated detection and tracking system that outperforms the performance of each individual module containing detection or tracking only. The experiments show that, even being trained on synthetic data, the proposed system performs well on real world drone images with complex background. The USC drone detection and tracking dataset with user labeled bounding boxes is available to the public. |
| Tasks | |
| Published | 2017-12-04 |
| URL | http://arxiv.org/abs/1712.00863v1 |
| http://arxiv.org/pdf/1712.00863v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-deep-learning-approach-to-drone-monitoring |
| Repo | |
| Framework | |
A Multi-Horizon Quantile Recurrent Forecaster
| Title | A Multi-Horizon Quantile Recurrent Forecaster |
| Authors | Ruofeng Wen, Kari Torkkola, Balakrishnan Narayanaswamy, Dhruv Madeka |
| Abstract | We propose a framework for general probabilistic multi-step time series regression. Specifically, we exploit the expressiveness and temporal nature of Sequence-to-Sequence Neural Networks (e.g. recurrent and convolutional structures), the nonparametric nature of Quantile Regression and the efficiency of Direct Multi-Horizon Forecasting. A new training scheme, forking-sequences, is designed for sequential nets to boost stability and performance. We show that the approach accommodates both temporal and static covariates, learning across multiple related series, shifting seasonality, future planned event spikes and cold-starts in real life large-scale forecasting. The performance of the framework is demonstrated in an application to predict the future demand of items sold on Amazon.com, and in a public probabilistic forecasting competition to predict electricity price and load. |
| Tasks | Time Series |
| Published | 2017-11-29 |
| URL | http://arxiv.org/abs/1711.11053v2 |
| http://arxiv.org/pdf/1711.11053v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-multi-horizon-quantile-recurrent-forecaster |
| Repo | |
| Framework | |
Fast BTG-Forest-Based Hierarchical Sub-sentential Alignment
| Title | Fast BTG-Forest-Based Hierarchical Sub-sentential Alignment |
| Authors | Hao Wang, Yves Lepage |
| Abstract | In this paper, we propose a novel BTG-forest-based alignment method. Based on a fast unsupervised initialization of parameters using variational IBM models, we synchronously parse parallel sentences top-down and align hierarchically under the constraint of BTG. Our two-step method can achieve the same run-time and comparable translation performance as fast_align while it yields smaller phrase tables. Final SMT results show that our method even outperforms in the experiment of distantly related languages, e.g., English-Japanese. |
| Tasks | |
| Published | 2017-11-20 |
| URL | http://arxiv.org/abs/1711.07265v1 |
| http://arxiv.org/pdf/1711.07265v1.pdf | |
| PWC | https://paperswithcode.com/paper/fast-btg-forest-based-hierarchical-sub |
| Repo | |
| Framework | |
Classifying Documents within Multiple Hierarchical Datasets using Multi-Task Learning
| Title | Classifying Documents within Multiple Hierarchical Datasets using Multi-Task Learning |
| Authors | Azad Naik, Anveshi Charuvaka, Huzefa Rangwala |
| Abstract | Multi-task learning (MTL) is a supervised learning paradigm in which the prediction models for several related tasks are learned jointly to achieve better generalization performance. When there are only a few training examples per task, MTL considerably outperforms the traditional Single task learning (STL) in terms of prediction accuracy. In this work we develop an MTL based approach for classifying documents that are archived within dual concept hierarchies, namely, DMOZ and Wikipedia. We solve the multi-class classification problem by defining one-versus-rest binary classification tasks for each of the different classes across the two hierarchical datasets. Instead of learning a linear discriminant for each of the different tasks independently, we use a MTL approach with relationships between the different tasks across the datasets established using the non-parametric, lazy, nearest neighbor approach. We also develop and evaluate a transfer learning (TL) approach and compare the MTL (and TL) methods against the standard single task learning and semi-supervised learning approaches. Our empirical results demonstrate the strength of our developed methods that show an improvement especially when there are fewer number of training examples per classification task. |
| Tasks | Multi-Task Learning, Transfer Learning |
| Published | 2017-06-06 |
| URL | http://arxiv.org/abs/1706.01583v1 |
| http://arxiv.org/pdf/1706.01583v1.pdf | |
| PWC | https://paperswithcode.com/paper/classifying-documents-within-multiple |
| Repo | |
| Framework | |
Optimization by a quantum reinforcement algorithm
| Title | Optimization by a quantum reinforcement algorithm |
| Authors | A. Ramezanpour |
| Abstract | A reinforcement algorithm solves a classical optimization problem by introducing a feedback to the system which slowly changes the energy landscape and converges the algorithm to an optimal solution in the configuration space. Here, we use this strategy to concentrate (localize) preferentially the wave function of a quantum particle, which explores the configuration space of the problem, on an optimal configuration. We examine the method by solving numerically the equations governing the evolution of the system, which are similar to the nonlinear Schr"odinger equations, for small problem sizes. In particular, we observe that reinforcement increases the minimal energy gap of the system in a quantum annealing algorithm. Our numerical simulations and the latter observation show that such kind of quantum feedbacks might be helpful in solving a computationally hard optimization problem by a quantum reinforcement algorithm. |
| Tasks | |
| Published | 2017-06-13 |
| URL | http://arxiv.org/abs/1706.04262v3 |
| http://arxiv.org/pdf/1706.04262v3.pdf | |
| PWC | https://paperswithcode.com/paper/optimization-by-a-quantum-reinforcement |
| Repo | |
| Framework | |
