PyTorchKR Papers

최신 논문

총 3,383편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1501.02056

Sequential Kernel Herding: Frank-Wolfe Optimization for Particle Filtering

Recently, the Frank-Wolfe optimization algorithm was suggested as a procedure to obtain adaptive quadrature rules for integrals of functions in a reproducing kernel Hilbert space (RKHS) with a potentially faster rate of convergence than Monte Carlo integration (and "kernel herding" was shown to be a special case of this procedure). In this paper, we propose to replace the random sampling step in a particle filter by Frank-Wolfe optimization. By optimizing the position of the particles, we can obtain better accuracy than random or quasi-Monte Carlo sampling. In applications where the evaluation of the emission probabilities is expensive (such as in robot localization), the additional computational cost to generate the particles through optimization can be justified. Experiments on standard synthetic examples as well as on a robot localization task indicate indeed an improvement of accuracy over random and quasi-Monte Carlo sampling.

arXiv:1502.06081

Study of a Robust Algorithm Applied in the Optimal Position Tuning for the Camera Lens in Automated Visual Inspection Systems

This paper present the mathematical fundaments and experimental study of an algorithm used to find the optimal position for the camera lens to obtain a maximum of details. This information can be further applied to a appropriate system to automatically correct this position. The algorithm is based on the evaluation of a so called resolution function who calculates the maximum of gradient in a certain zone of the image. The paper also presents alternative forms of the function, results of measurements and set up a set of practical rules for the right application of the algorithm.

arXiv:1503.01446

Predicting opponent team activity in a RoboCup environment

The goal of this project is to predict the opponent's configuration in a RoboCup SSL environment. For simplicity, a Markov model assumption is made such that the predicted formation of the opponent team only depends on its current formation. The field is divided into a grid and a robot state per player is created with information about its position and its velocity. To gather a more general sense of what the opposing team is doing, the state also incorporates the team's average position (centroid). All possible state transitions are stored in a hash table that requires minimum storage space. The table is populated with transition probabilities that are learned by reading vision packages and counting the state transitions regardless of the specific robot player. Therefore, the computation during the game is reduced to interpreting a given vision package to assign each player to a state, and looking for the most likely state it will transition to. The confidence of the predicted team's formation is the product of each individual player's probability. The project is noteworthy in that it minimizes the time and space complexity requirements for opponent's moves prediction.

arXiv:1503.03514

Appearance-based indoor localization: A comparison of patch descriptor performance

Vision is one of the most important of the senses, and humans use it extensively during navigation. We evaluated different types of image and video frame descriptors that could be used to determine distinctive visual landmarks for localizing a person based on what is seen by a camera that they carry. To do this, we created a database containing over 3 km of video-sequences with ground-truth in the form of distance travelled along different corridors. Using this database, the accuracy of localization - both in terms of knowing which route a user is on - and in terms of position along a certain route, can be evaluated. For each type of descriptor, we also tested different techniques to encode visual structure and to search between journeys to estimate a user's position. The techniques include single-frame descriptors, those using sequences of frames, and both colour and achromatic descriptors. We found that single-frame indexing worked better within this particular dataset. This might be because the motion of the person holding the camera makes the video too dependent on individual steps and motions of one particular journey. Our results suggest that appearance-based information could be an additional source of navigational data indoors, augmenting that provided by, say, radio signal strength indicators (RSSIs). Such visual information could be collected by crowdsourcing low-resolution video feeds, allowing journeys made by different users to be associated with each other, and location to be inferred without requiring explicit mapping. This offers a complementary approach to methods based on simultaneous localization and mapping (SLAM) algorithms.

arXiv:1503.02391

Deep Human Parsing with Active Template Regression

In this work, the human parsing task, namely decomposing a human image into semantic fashion/body regions, is formulated as an Active Template Regression (ATR) problem, where the normalized mask of each fashion/body item is expressed as the linear combination of the learned mask templates, and then morphed to a more precise mask with the active shape parameters, including position, scale and visibility of each semantic region. The mask template coefficients and the active shape parameters together can generate the human parsing results, and are thus called the structure outputs for human parsing. The deep Convolutional Neural Network (CNN) is utilized to build the end-to-end relation between the input human image and the structure outputs for human parsing. More specifically, the structure outputs are predicted by two separate networks. The first CNN network is with max-pooling, and designed to predict the template coefficients for each label mask, while the second CNN network is without max-pooling to preserve sensitivity to label mask position and accurately predict the active shape parameters. For a new image, the structure outputs of the two networks are fused to generate the probability of each label for each pixel, and super-pixel smoothing is finally used to refine the human parsing result. Comprehensive evaluations on a large dataset well demonstrate the significant superiority of the ATR framework over other state-of-the-arts for human parsing. In particular, the F1-score reaches $64.38\%$ by our ATR framework, significantly higher than $44.76\%$ based on the state-of-the-art algorithm.

arXiv:1503.01903

Partial light field tomographic reconstruction from a fixed-camera focal stack

This paper describes a novel approach to partially reconstruct high-resolution 4D light fields from a stack of differently focused photographs taken with a fixed camera. First, a focus map is calculated from this stack using a simple approach combining gradient detection and region expansion with graph-cut. Then, this focus map is converted into a depth map thanks to the calibration of the camera. We proceed after this with the tomographic reconstruction of the epipolar images by back-projecting the focused regions of the scene only. We call it masked back-projection. The angles of back-projection are calculated from the depth map. Thanks to the high angular resolution we achieve by suitably exploiting the image content captured over a large interval of focus distances, we are able to render puzzling perspective shifts although the original photographs were taken from a single fixed camera at a fixed position.

arXiv:1503.06648

Vehicle Local Position Estimation System

In this paper, a robust vehicle local position estimation with the help of single camera sensor and GPS is presented. A modified Inverse Perspective Mapping, illuminant Invariant techniques and object detection based approach is used to localize the vehicle in the road. Vehicles current lane, its position from road boundary and other cars are used to define its local position. For this purpose Lane markings are detected using a Laplacian edge feature, robust to shadowing. Effect of shadowing and extra sun light are removed using Lab color space and illuminant invariant techniques. Lanes are assumed to be as parabolic model and fitted using robust RANSAC. This method can reliably detect all lanes of the road, estimate lane departure angle and local position of vehicle relative to lanes, road boundary and other cars. Different type of obstacle like pedestrians, vehicles are detected using HOG feature based deformable part model.

arXiv:1401.6606

Continuous Localization and Mapping of a Pan Tilt Zoom Camera for Wide Area Tracking

Pan-tilt-zoom (PTZ) cameras are powerful to support object identification and recognition in far-field scenes. However, the effective use of PTZ cameras in real contexts is complicated by the fact that a continuous on-line camera calibration is needed and the absolute pan, tilt and zoom positional values provided by the camera actuators cannot be used because are not synchronized with the video stream. So, accurate calibration must be directly extracted from the visual content of the frames. Moreover, the large and abrupt scale changes, the scene background changes due to the camera operation and the need of camera motion compensation make target tracking with these cameras extremely challenging. In this paper, we present a solution that provides continuous on-line calibration of PTZ cameras which is robust to rapid camera motion, changes of the environment due to illumination or moving objects and scales beyond thousands of landmarks. The method directly derives the relationship between the position of a target in the 3D world plane and the corresponding scale and position in the 2D image, and allows real-time tracking of multiple targets with high and stable degree of accuracy even at far distances and any zooming level.

arXiv:1504.01840

Autonomous CRM Control via CLV Approximation with Deep Reinforcement Learning in Discrete and Continuous Action Space

The paper outlines a framework for autonomous control of a CRM (customer relationship management) system. First, it explores how a modified version of the widely accepted Recency-Frequency-Monetary Value system of metrics can be used to define the state space of clients or donors. Second, it describes a procedure to determine the optimal direct marketing action in discrete and continuous action space for the given individual, based on his position in the state space. The procedure involves the use of model-free Q-learning to train a deep neural network that relates a client's position in the state space to rewards associated with possible marketing actions. The estimated value function over the client state space can be interpreted as customer lifetime value, and thus allows for a quick plug-in estimation of CLV for a given client. Experimental results are presented, based on KDD Cup 1998 mailing dataset of donation solicitations.

arXiv:1412.6564

Move Evaluation in Go Using Deep Convolutional Neural Networks

The game of Go is more challenging than other board games, due to the difficulty of constructing a position or move evaluation function. In this paper we investigate whether deep convolutional networks can be used to directly represent and learn this knowledge. We train a large 12-layer convolutional neural network by supervised learning from a database of human professional games. The network correctly predicts the expert move in 55% of positions, equalling the accuracy of a 6 dan human player. When the trained convolutional network was used directly to play games of Go, without any search, it beat the traditional search program GnuGo in 97% of games, and matched the performance of a state-of-the-art Monte-Carlo tree search that simulates a million positions per move.

arXiv:1404.3708

Inferring Social Status and Rich Club Effects in Enterprise Communication Networks

Social status, defined as the relative rank or position that an individual holds in a social hierarchy, is known to be among the most important motivating forces in social behaviors. In this paper, we consider the notion of status from the perspective of a position or title held by a person in an enterprise. We study the intersection of social status and social networks in an enterprise. We study whether enterprise communication logs can help reveal how social interactions and individual status manifest themselves in social networks. To that end, we use two enterprise datasets with three communication channels --- voice call, short message, and email --- to demonstrate the social-behavioral differences among individuals with different status. We have several interesting findings and based on these findings we also develop a model to predict social status. On the individual level, high-status individuals are more likely to be spanned as structural holes by linking to people in parts of the enterprise networks that are otherwise not well connected to one another. On the community level, the principle of homophily, social balance and clique theory generally indicate a "rich club" maintained by high-status individuals, in the sense that this community is much more connected, balanced and dense. Our model can predict social status of individuals with 93% accuracy.

arXiv:1311.5954

Robust Vertex Classification

For random graphs distributed according to stochastic blockmodels, a special case of latent position graphs, adjacency spectral embedding followed by appropriate vertex classification is asymptotically Bayes optimal; but this approach requires knowledge of and critically depends on the model dimension. In this paper, we propose a sparse representation vertex classifier which does not require information about the model dimension. This classifier represents a test vertex as a sparse combination of the vertices in the training set and uses the recovered coefficients to classify the test vertex. We prove consistency of our proposed classifier for stochastic blockmodels, and demonstrate that the sparse representation classifier can predict vertex labels with higher accuracy than adjacency spectral embedding approaches via both simulation studies and real data experiments. Our results demonstrate the robustness and effectiveness of our proposed vertex classifier when the model dimension is unknown.

arXiv:1505.00424

Electron Neutrino Classification in Liquid Argon Time Projection Chamber Detector

Neutrinos are one of the least known elementary particles. The detection of neutrinos is an extremely difficult task since they are affected only by weak sub-atomic force or gravity. Therefore large detectors are constructed to reveal neutrino's properties. Among them the Liquid Argon Time Projection Chamber (LAr-TPC) detectors provide excellent imaging and particle identification ability for studying neutrinos. The computerized methods for automatic reconstruction and identification of particles are needed to fully exploit the potential of the LAr-TPC technique. Herein, the novel method for electron neutrino classification is presented. The method constructs a feature descriptor from images of observed event. It characterizes the signal distribution propagated from vertex of interest, where the particle interacts with the detector medium. The classifier is learned with a constructed feature descriptor to decide whether the images represent the electron neutrino or cascade produced by photons. The proposed approach assumes that the position of primary interaction vertex is known. The method's performance in dependency to the noise in a primary vertex position and deposited energy of particles is studied.

arXiv:1412.6618

Permutohedral Lattice CNNs

This paper presents a convolutional layer that is able to process sparse input features. As an example, for image recognition problems this allows an efficient filtering of signals that do not lie on a dense grid (like pixel position), but of more general features (such as color values). The presented algorithm makes use of the permutohedral lattice data structure. The permutohedral lattice was introduced to efficiently implement a bilateral filter, a commonly used image processing operation. Its use allows for a generalization of the convolution type found in current (spatial) convolutional network architectures.

arXiv:1411.6970공식 코드 · Papers with Code

Post-acquisition image based compensation for thickness variation in microscopy section series

Serial section Microscopy is an established method for volumetric anatomy reconstruction. Section series imaged with Electron Microscopy are currently vital for the reconstruction of the synaptic connectivity of entire animal brains such as that of Drosophila melanogaster. The process of removing ultrathin layers from a solid block containing the specimen, however, is a fragile procedure and has limited precision with respect to section thickness. We have developed a method to estimate the relative z-position of each individual section as a function of signal change across the section series. First experiments show promising results on both serial section Transmission Electron Microscopy (ssTEM) data and Focused Ion Beam Scanning Electron Microscopy (FIB-SEM) series. We made our solution available as Open Source plugins for the TrakEM2 software and the ImageJ distribution Fiji.

arXiv:1506.02432

Reflection Invariance: an important consideration of image orientation

In this position paper, we consider the state of computer vision research with respect to invariance to the horizontal orientation of an image -- what we term reflection invariance. We describe why we consider reflection invariance to be an important property and provide evidence where the absence of this invariance produces surprising inconsistencies in state-of-the-art systems. We demonstrate inconsistencies in methods of object detection and scene classification when they are presented with images and the horizontal mirror of those images. Finally, we examine where some of the invariance is exhibited in feature detection and descriptors, and make a case for future consideration of reflection invariance as a measure of quality in computer vision algorithms.

arXiv:1411.4280

Efficient Object Localization Using Convolutional Networks

Recent state-of-the-art performance on human-body pose estimation has been achieved with Deep Convolutional Networks (ConvNets). Traditional ConvNet architectures include pooling and sub-sampling layers which reduce computational requirements, introduce invariance and prevent over-training. These benefits of pooling come at the cost of reduced localization accuracy. We introduce a novel architecture which includes an efficient `position refinement' model that is trained to estimate the joint offset location within a small region of the image. This refinement model is jointly trained in cascade with a state-of-the-art ConvNet model to achieve improved accuracy in human joint location estimation. We show that the variance of our detector approaches the variance of human annotations on the FLIC dataset and outperforms all existing approaches on the MPII-human-pose dataset.

arXiv:1506.04608

Flow Segmentation in Dense Crowds

A framework is proposed in this paper that is used to segment flow of dense crowds. The flow field that is generated by the movement in the crowd is treated just like an aperiodic dynamic system. On this flow field a grid of particles is put over for particle advection by the use of a numerical integration scheme. Then flow maps are generated which associates the initial position of the particles with final position. The gradient of the flow maps gives the amount of divergence of the neighboring particles. For forward integration and analysis forward Finite time Lyapunov Exponent is calculated and backward Finite time Lyapunov Exponent is also calculated it gives the Lagrangian coherent structures of the flow in crowd. Lagrangian Coherent Structures basically divides the flow in crowd into regions and these regions have different dynamics. These regions are then used to get the boundary in the different flow segments by using water shed algorithm. The experiment is conducted on the crowd dataset of UCF (University of central Florida).

arXiv:1506.04366

Artificial general intelligence through recursive data compression and grounded reasoning: a position paper

This paper presents a tentative outline for the construction of an artificial, generally intelligent system (AGI). It is argued that building a general data compression algorithm solving all problems up to a complexity threshold should be the main thrust of research. A measure for partial progress in AGI is suggested. Although the details are far from being clear, some general properties for a general compression algorithm are fleshed out. Its inductive bias should be flexible and adapt to the input data while constantly searching for a simple, orthogonal and complete set of hypotheses explaining the data. It should recursively reduce the size of its representations thereby compressing the data increasingly at every iteration. Abstract Based on that fundamental ability, a grounded reasoning system is proposed. It is argued how grounding and flexible feature bases made of hypotheses allow for resourceful thinking. While the simulation of representation contents on the mental stage accounts for much of the power of propositional logic, compression leads to simple sets of hypotheses that allow the detection and verification of universally quantified statements. Abstract Together, it is highlighted how general compression and grounded reasoning could account for the birth and growth of first concepts about the world and the commonsense reasoning about them.

arXiv:1506.05843공식 코드 · Papers with Code

Dependent Multinomial Models Made Easy: Stick Breaking with the Pólya-Gamma Augmentation

Many practical modeling problems involve discrete data that are best represented as draws from multinomial or categorical distributions. For example, nucleotides in a DNA sequence, children's names in a given state and year, and text documents are all commonly modeled with multinomial distributions. In all of these cases, we expect some form of dependency between the draws: the nucleotide at one position in the DNA strand may depend on the preceding nucleotides, children's names are highly correlated from year to year, and topics in text may be correlated and dynamic. These dependencies are not naturally captured by the typical Dirichlet-multinomial formulation. Here, we leverage a logistic stick-breaking representation and recent innovations in P\'olya-gamma augmentation to reformulate the multinomial distribution in terms of latent variables with jointly Gaussian likelihoods, enabling us to take advantage of a host of Bayesian inference techniques for Gaussian models with minimal overhead.