arXiv subjects

Yu Sun

Publications and source records attributed to Yu Sun.

At least 325 records · Page 18Linked to original sources

arXiv2018

Long Activity Video Understanding using Functional Object-Oriented Network

Video understanding is one of the most challenging topics in computer vision. In this paper, a four-stage video understanding pipeline is presented to simultaneously recognize all atomic actions and the single on-going activity in a video. This pipeline uses objects and motions from the video and a graph-based knowledge representation network as prior reference. Two deep networks are trained to identify objects and motions in each video sequence associated with an action. Low Level image features are then used to identify objects of interest in that video sequence. Confidence scores are assigned to objects of interest based on their involvement in the action and to motion classes based on results from a deep neural network that classifies the on-going action in video into motion classes. Confidence scores are computed for each candidate functional unit associated with an action using a knowledge representation network, object confidences, and motion confidences. Each action is therefore associated with a functional unit and the sequence of actions is further evaluated to identify the single on-going activity in the video. The knowledge representation used in the pipeline is called the functional object-oriented network which is a graph-based network useful for encoding knowledge about manipulation tasks. Experiments are performed on a dataset of cooking videos to test the proposed algorithm with action inference and activity classification. Experiments show that using functional object oriented network improves video understanding significantly.

cs.CV↗

arXiv2018

A Dataset of Daily Interactive Manipulation

Robots that succeed in factories stumble to complete the simplest daily task humans take for granted, for the change of environment makes the task exceedingly difficult. Aiming to teach robot perform daily interactive manipulation in a changing environment using human demonstrations, we collected our own data of interactive manipulation. The dataset focuses on position, orientation, force, and torque of objects manipulated in daily tasks. The dataset includes 1,593 trials of 32 types of daily motions and 1,596 trials of pouring alone, as well as helper code. We present our dataset to facilitate the research on task-oriented interactive manipulation.

cs.RO↗

arXiv2018

Construction of all-in-focus images assisted by depth sensing

Multi-focus image fusion is a technique for obtaining an all-in-focus image in which all objects are in focus to extend the limited depth of field (DoF) of an imaging system. Different from traditional RGB-based methods, this paper presents a new multi-focus image fusion method assisted by depth sensing. In this work, a depth sensor is used together with a color camera to capture images of a scene. A graph-based segmentation algorithm is used to segment the depth map from the depth sensor, and the segmented regions are used to guide a focus algorithm to locate in-focus image blocks from among multi-focus source images to construct the reference all-in-focus image. Five test scenes and six evaluation metrics were used to compare the proposed method and representative state-of-the-art algorithms. Experimental results quantitatively demonstrate that this method outperforms existing methods in both speed and quality (in terms of comprehensive fusion metrics). The generated images can potentially be used as reference all-in-focus images.

cs.CV↗

arXiv2018

Computational complexity analysis for Monte Carlo approximations of classically scaled population processes

We analyze and compare the computational complexity of different simulation strategies for Monte Carlo in the setting of classically scaled population processes. This allows a range of widely used competing strategies to be judged systematically. Our setting includes stochastically modeled biochemical systems. We consider the task of approximating the expected value of some path functional of the state of the system at a fixed time point. We study the use of standard Monte Carlo when samples are produced by exact simulation and by approximation with tau-leaping or an Euler-Maruyama discretization of a diffusion approximation. Appropriate modifications of recently proposed multilevel Monte Carlo algorithms are also studied for the tau-leaping and Euler-Maruyama approaches. In order to quantify computational complexity in a tractable yet meaningful manner, we consider a parameterization that, in the mass action chemical kinetics setting, corresponds to the classical system size scaling. We base the analysis on a novel asymptotic regime where the required accuracy is a function of the model scaling parameter. Our new analysis shows that, under the specific assumptions made in the manuscript, if the bias inherent in the diffusion approximation is smaller than the required accuracy, then multilevel Monte Carlo for the diffusion approximation is most efficient, besting multilevel Monte Carlo with tau-leaping by a factor of a logarithm of the scaling parameter. However, if the bias of the diffusion model is greater than the error tolerance, or if the bias can not be bounded analytically, multilevel versions of tau-leaping are often the optimal choice.

math.NA↗

arXiv2018

AI Meets Physical World -- Exploring Robot Cooking

This paper describes our recent research effort to bring the computer intelligence into the physical world so that robots could perform physically interactive manipulation tasks. Our proposed approach first gives robots the ability to learn manipulation skills by "watching" online instructional videos. After "watching" over 200 instructional videos, a functional object-oriented network (FOON) is constructed to represent the observed manipulation skills. Using the network, robots can take a high-level task command such as "I want BBQ Ribs for dinner," decipher the task goal, seek the correct objects to operate on, and then generate and execute a sequence of manipulation motions that can deal with physical interactions in a new condition. To best facilitate manipulation motions in the physical world, we also developed new grasping strategies for robots to hold objects with a firm grasp to withstand the disturbance during physical interactions.

cs.RO↗

arXiv2018

Efficient and accurate inversion of multiple scattering with deep learning

Image reconstruction under multiple light scattering is crucial in a number of applications such as diffraction tomography. The reconstruction problem is often formulated as a nonconvex optimization, where a nonlinear measurement model is used to account for multiple scattering and regularization is used to enforce prior constraints on the object. In this paper, we propose a powerful alternative to this optimization-based view of image reconstruction by designing and training a deep convolutional neural network that can invert multiple scattered measurements to produce a high-quality image of the refractive index. Our results on both simulated and experimental datasets show that the proposed approach is substantially faster and achieves higher imaging quality compared to the state-of-the-art methods based on optimization.

cs.CV↗

arXiv2017

A Discrete Packing Model of Granular Material Confined in A Vertical Column

The transmission rules of interparticle forces between granular particles were analyzed, and a discrete packing model was proposed to calculate the static pressure at the bottom of granular material confined in a vertical column. The mechanical analysis and numerical simulation results indicate that the silo effect is caused by the frictional contacts between border particles and inner walls, the static pressure at the bottom depends on the external load initially, and then tends to a saturation pressure (Pn) in an exponential form. The saturation pressure (Pn) is positive linear related to the container radius (R) with the same granular matter and stacking manner. The saturation pressure (Pn) is directly proportional to the particle size (ra), and the increasing or decreasing characteristic depends on the frictional property of inner walls, the friction and stacking angle of grains. At last, the predictions of the aforementioned model are compared with the experimental results from the literature, and good agreement is achieved.

cond-mat.soft↗

arXiv2017

Multivariate Regression with Gross Errors on Manifold-valued Data

We consider the topic of multivariate regression on manifold-valued output, that is, for a multivariate observation, its output response lies on a manifold. Moreover, we propose a new regression model to deal with the presence of grossly corrupted manifold-valued responses, a bottleneck issue commonly encountered in practical scenarios. Our model first takes a correction step on the grossly corrupted responses via geodesic curves on the manifold, and then performs multivariate linear regression on the corrected data. This results in a nonconvex and nonsmooth optimization problem on manifolds. To this end, we propose a dedicated approach named PALMR, by utilizing and extending the proximal alternating linearized minimization techniques. Theoretically, we investigate its convergence property, where it is shown to converge to a critical point under mild conditions. Empirically, we test our model on both synthetic and real diffusion tensor imaging data, and show that our model outperforms other multivariate regression models when manifold-valued responses contain gross errors, and is effective in identifying gross errors.

stat.ML↗

arXiv2017

On Calibration of Modern Neural Networks

Confidence calibration -- the problem of predicting probability estimates representative of the true correctness likelihood -- is important for classification models in many applications. We discover that modern neural networks, unlike those from a decade ago, are poorly calibrated. Through extensive experiments, we observe that depth, width, weight decay, and Batch Normalization are important factors influencing calibration. We evaluate the performance of various post-processing calibration methods on state-of-the-art architectures with image and document classification datasets. Our analysis and experiments not only offer insights into neural network learning, but also provide a simple and straightforward recipe for practical settings: on most datasets, temperature scaling -- a single-parameter variant of Platt Scaling -- is surprisingly effective at calibrating predictions.

cs.LG↗

arXiv2017

Learning to Pour

Pouring is a simple task people perform daily. It is the second most frequently executed motion in cooking scenarios, after pick-and-place. We present a pouring trajectory generation approach, which uses force feedback from the cup to determine the future velocity of pouring. The approach uses recurrent neural networks as its building blocks. We collected the pouring demonstrations which we used for training. To test our approach in simulation, we also created and trained a force estimation system. The simulated experiments show that the system is able to generalize to single unseen element of the pouring characteristics.

cs.RO↗

arXiv2017

Concept Drift Adaptation by Exploiting Historical Knowledge

Incremental learning with concept drift has often been tackled by ensemble methods, where models built in the past can be re-trained to attain new models for the current data. Two design questions need to be addressed in developing ensemble methods for incremental learning with concept drift, i.e., which historical (i.e., previously trained) models should be preserved and how to utilize them. A novel ensemble learning method, namely Diversity and Transfer based Ensemble Learning (DTEL), is proposed in this paper. Given newly arrived data, DTEL uses each preserved historical model as an initial model and further trains it with the new data via transfer learning. Furthermore, DTEL preserves a diverse set of historical models, rather than a set of historical models that are merely accurate in terms of classification accuracy. Empirical studies on 15 synthetic data streams and 4 real-world data streams (all with concept drifts) demonstrate that DTEL can handle concept drift more effectively than 4 other state-of-the-art methods.

cs.LG↗

arXiv2016

Latest Datasets and Technologies Presented in the Workshop on Grasping and Manipulation Datasets

This paper reports the activities and outcomes in the Workshop on Grasping and Manipulation Datasets that was organized under the International Conference on Robotics and Automation (ICRA) 2016. The half day workshop was packed with nine invited talks, 12 interactive presentations, and one panel discussion with ten panelists. This paper summarizes all the talks and presentations and recaps what has been discussed in the panels session. This summary servers as a review of recent developments in data collection in grasping and manipulation. Many of the presentations describe ongoing efforts or explorations that could be achieved and fully available in a year or two. The panel discussion not only commented on the current approaches, but also indicates new directions and focuses. The workshop clearly displayed the importance of quality datasets in robotics and robotic grasping and manipulation field. Hopefully the workshop could motivate larger efforts to create big datasets that are comparable with big datasets in other communities such as computer vision.

cs.RO↗

arXiv2016

Private Causal Inference

Causal inference deals with identifying which random variables "cause" or control other random variables. Recent advances on the topic of causal inference based on tools from statistical estimation and machine learning have resulted in practical algorithms for causal inference. Causal inference has the potential to have significant impact on medical research, prevention and control of diseases, and identifying factors that impact economic changes to name just a few. However, these promising applications for causal inference are often ones that involve sensitive or personal data of users that need to be kept private (e.g., medical records, personal finances, etc). Therefore, there is a need for the development of causal inference methods that preserve data privacy. We study the problem of inferring causality using the current, popular causal inference framework, the additive noise model (ANM) while simultaneously ensuring privacy of the users. Our framework provides differential privacy guarantees for a variety of ANM variants. We run extensive experiments, and demonstrate that our techniques are practical and easy to implement.

stat.ML↗

arXiv2016

Deep Networks with Stochastic Depth

Very deep convolutional networks with hundreds of layers have led to significant reductions in error on competitive benchmarks. Although the unmatched expressiveness of the many layers can be highly desirable at test time, training very deep networks comes with its own set of challenges. The gradients can vanish, the forward flow often diminishes, and the training time can be painfully slow. To address these problems, we propose stochastic depth, a training procedure that enables the seemingly contradictory setup to train short networks and use deep networks at test time. We start with very deep networks but during training, for each mini-batch, randomly drop a subset of layers and bypass them with the identity function. This simple approach complements the recent success of residual networks. It reduces training time substantially and improves the test error significantly on almost all data sets that we used for evaluation. With stochastic depth we can increase the depth of residual networks even beyond 1200 layers and still yield meaningful improvements in test error (4.91% on CIFAR-10).

cs.LG↗

arXiv2016

Datasets on object manipulation and interaction: a survey

A dataset is crucial for model learning and evaluation. Choosing the right dataset to use or making a new dataset requires the knowledge of those that are available. In this work, we provide that knowledge, by reviewing twenty datasets that were published in the recent six years and that are directly related to object manipulation. We report on modalities, activities, and annotations for each individual dataset and give our view on its use for object manipulation. We also compare the datasets and summarize them. We conclude with our suggestion on future datasets.

cs.RO↗

arXiv2016

Reverse Nearest Neighbor Heat Maps: A Tool for Influence Exploration

We study the problem of constructing a reverse nearest neighbor (RNN) heat map by finding the RNN set of every point in a two-dimensional space. Based on the RNN set of a point, we obtain a quantitative influence (i.e., heat) for the point. The heat map provides a global view on the influence distribution in the space, and hence supports exploratory analyses in many applications such as marketing and resource management. To construct such a heat map, we first reduce it to a problem called Region Coloring (RC), which divides the space into disjoint regions within which all the points have the same RNN set. We then propose a novel algorithm named CREST that efficiently solves the RC problem by labeling each region with the heat value of its containing points. In CREST, we propose innovative techniques to avoid processing expensive RNN queries and greatly reduce the number of region labeling operations. We perform detailed analyses on the complexity of CREST and lower bounds of the RC problem, and prove that CREST is asymptotically optimal in the worst case. Extensive experiments with both real and synthetic data sets demonstrate that CREST outperforms alternative algorithms by several orders of magnitude.

cs.DB↗

arXiv2015

A large area plastic scintillation detector with 4-corner-readout

A 760 $\times$ 760 $\times$ 30 mm$^3$ plastic scintillation detector viewed by photomultiplier tubes (PMTs) from four corners has been developed, and the detector has been tested with cosmic rays and $γ$ rays. A position-independent effective time T$_{eff}$ has been found, indicating this detector can be used as a TOF detector. The hit position can also be reconstructed by the time from four corners. A TOF resolution of 236 ps and a position resolution of 48 mm have been achieved, and the detection efficiency has also been investigated.

physics.ins-det↗

arXiv2015

Multilevel Monte Carlo for stochastic differential equations with small noise

We consider the problem of numerically estimating expectations of solutions to stochastic differential equations driven by Brownian motions in the commonly occurring small noise regime. We consider (i) standard Monte Carlo methods combined with numerical discretization algorithms tailored to the small noise setting, and (ii) a multilevel Monte Carlo method combined with a standard Euler-Maruyama implementation. Under the assumptions we make on the underlying model, the multilevel method combined with Euler-Maruyama is often found to be the most efficient option. Moreover, under a wide range of scalings the multilevel method is found to give the same asymptotic complexity that would arise in the idealized case where we have access to exact samples of the required distribution at a cost of $O(1)$ per sample. A key step in our analysis is to analyze the variance between two coupled paths directly, as opposed to their $L^2$ distance. Careful simulations are provided to illustrate the asymptotic results.

math.NA↗