Deep learning has driven great progress in natural and biological image processing. However, in materials science and engineering, there are often some flaws and indistinctions in material microscopic images induced from complex sample preparation, even due to the material itself, hindering the detection of target objects. In this work, we propose WPU-net that redesign the architecture and weighted loss of U-Net to force the network to integrate information from adjacent slices and pay more attention to the topology in this boundary detection task. Then, the WPU-net was applied into a typical material example, i.e., the grain boundary detection of polycrystalline material. Experiments demonstrate that the proposed method achieves promising performance compared to state-of-the-art methods. Besides, we propose a new method for object tracking between adjacent slices, which can effectively reconstruct the 3D structure of the whole material while maintaining relative accuracy.
http://arxiv.org/abs/1905.09226
Representation of defeasible information is of interest in description logics, as it is related to the need of accommodating exceptional instances in knowledge bases. In this direction, in our previous works we presented a datalog translation for reasoning on (contextualized) OWL RL knowledge bases with a notion of justified exceptions on defeasible axioms. While it covers a relevant fragment of OWL, the resulting reasoning process needs a complex encoding in order to capture reasoning on negative information. In this paper, we consider the case of knowledge bases in $\textit{DL-Lite}{\cal R}$, i.e. the language underlying OWL QL. We provide a definition for $\textit{DL-Lite}{\cal R}$ knowledge bases with defeasible axioms and study their properties. The limited form of $\textit{DL-Lite}{\cal R}$ axioms allows us to formulate a simpler encoding into datalog (under answer set semantics) with direct rules for reasoning on negative information. The resulting materialization method gives rise to a complete reasoning procedure for instance checking in $\textit{DL-Lite}{\cal R}$ with defeasible axioms.
http://arxiv.org/abs/1905.09221
Neural networks provide new possibilities to automatically learn complex language patterns and query-document relations. Neural IR models have achieved promising results in learning query-document relevance patterns, but few explorations have been done on understanding the text content of a query or a document. This paper studies leveraging a recently-proposed contextual neural language model, BERT, to provide deeper text understanding for IR. Experimental results demonstrate that the contextual text representations from BERT are more effective than traditional word embeddings. Compared to bag-of-words retrieval models, the contextual language model can better leverage language structures, bringing large improvements on queries written in natural languages. Combining the text understanding ability with search knowledge leads to an enhanced pre-trained BERT model that can benefit related search tasks where training data are limited.
http://arxiv.org/abs/1905.09217
This review considers a problem in the development of mobile robot adhesion methods with vertical surfaces and the appropriate locomotion mechanism design. The evolution of adhesion methods for wall-climbing robots (based on friction, magnetic forces, air pressure, electrostatic adhesion, molecular forces, rheological properties of fluids and their combinations) and their locomotion principles (wheeled, tracked, walking, sliding framed and hybrid) is studied. Wall-climbing robots are classified according to the applications, adhesion methods and locomotion mechanisms. The advantages and disadvantages of various adhesion methods and locomotion mechanisms are analyzed in terms of mobility, noiselessness, autonomy and energy efficiency. Focus is placed on the physical and technical aspects of the adhesion methods and the possibility of combining adhesion and locomotion methods.
http://arxiv.org/abs/1905.09214
In this paper, we propose an unified hyperspectral image classification method which takes three-dimensional hyperspectral data cube as an input and produces a classification map. In the proposed method, a deep neural network which uses spectral and spatial information together with residual connections, and pixel affinity network based segmentation-aware superpixels are used together. In the architecture, segmentation-aware superpixels run on the initial classification map of deep residual network, and apply majority voting on obtained results. Experimental results show that our propoped method yields state-of-the-art results in two benchmark datasets. Moreover, we also show that the segmentation-aware superpixels have great contribution to the success of hyperspectral image classification methods in cases where training data is insufficient.
http://arxiv.org/abs/1905.09211
Purpose. Precise placement of needles is a challenge in a number of clinical applications such as brachytherapy or biopsy. Forces acting at the needle cause tissue deformation and needle deflection which in turn may lead to misplacement or injury. Hence, a number of approaches to estimate the forces at the needle have been proposed. Yet, integrating sensors into the needle tip is challenging and a careful calibration is required to obtain good force estimates. Methods. We describe a fiber-optical needle tip force sensor design using a single OCT fiber for measurement. The fiber images the deformation of an epoxy layer placed below the needle tip which results in a stream of 1D depth profiles. We study different deep learning approaches to facilitate calibration between this spatio-temporal image data and the related forces. In particular, we propose a novel convGRU-CNN architecture for simultaneous spatial and temporal data processing. Results. The needle can be adapted to different operating ranges by changing the stiffness of the epoxy layer. Likewise, calibration can be adapted by training the deep learning models. Our novel convGRU-CNN architecture results in the lowest mean absolute error of 1.59 +- 1.3 mN and a cross-correlation coefficient of 0.9997, and clearly outperforms the other methods. Ex vivo experiments in human prostate tissue demonstrate the needle’s application. Conclusions. Our OCT-based fiber-optical sensor presents a viable alternative for needle tip force estimation. The results indicate that the rich spatio-temporal information included in the stream of images showing the deformation throughout the epoxy layer can be effectively used by deep learning models. Particularly, we demonstrate that the convGRU-CNN architecture performs favorably, making it a promising approach for other spatio-temporal learning problems.
http://arxiv.org/abs/1905.09282
Options are generally learned by using an inaccurate environment model (or simulator), which contains uncertain model parameters. While there are several methods to learn options that are robust against the uncertainty of model parameters, these methods only consider either the worst case or the average (ordinary) case for learning options. This limited consideration of the cases often produces options that do not work well in the unconsidered case. In this paper, we propose a conditional value at risk (CVaR)-based method to learn options that work well in both the average and worst cases. We extend the CVaR-based policy gradient method proposed by Chow and Ghavamzadeh (2014) to deal with robust Markov decision processes and then apply the extended method to learning robust options. We conduct experiments to evaluate our method in multi-joint robot control tasks (HopperIceBlock, Half-Cheetah, and Walker2D). Experimental results show that our method produces options that 1) give better worst-case performance than the options learned only to minimize the average-case loss, and 2) give better average-case performance than the options learned only to minimize the worst-case loss.
http://arxiv.org/abs/1905.09191
In this work, we describe a new deep learning based method that can effectively distinguish AI-generated fake videos (referred to as {\em DeepFake} videos hereafter) from real videos. Our method is based on the observations that current DeepFake algorithm can only generate images of limited resolutions, which need to be further warped to match the original faces in the source video. Such transforms leave distinctive artifacts in the resulting DeepFake videos, and we show that they can be effectively captured by convolutional neural networks (CNNs). Compared to previous methods which use a large amount of real and DeepFake generated images to train CNN classifier, our method does not need DeepFake generated images as negative training examples since we target the artifacts in affine face warping as the distinctive feature to distinguish real and fake images. The advantages of our method are two-fold: (1) Such artifacts can be simulated directly using simple image processing operations on a image to make it as negative example. Since training a DeepFake model to generate negative examples is time-consuming and resource-demanding, our method saves a plenty of time and resources in training data collection; (2) Since such artifacts are general existed in DeepFake videos from different sources, our method is more robust compared to others. Our method is evaluated on two sets of DeepFake video datasets for its effectiveness in practice.
http://arxiv.org/abs/1811.00656
Machine learning (ML) architectures such as convolutional neural networks (CNNs) have garnered considerable recent attention in the study of quantum many-body systems. However, advanced ML approaches such as gated recurrent neural networks (RNNs) have seldom been applied to such contexts. Here we demonstrate that a special class of RNNs known as long short-term memory (LSTM) networks is capable of learning and accurately predicting the time evolution of one-dimensional (1D) Ising model with simultaneous transverse and parallel magnetic fields, as quantitatively corroborated by relative entropy measurements and magnetization between the predicted and exact state distributions. In this unsupervised learning task, the many-body state evolution was predicted in an autoregressive way from an initial state, without any guidance or knowledge of any Hamiltonian. Our work paves the way for future applications of advanced ML methods in quantum many-body dynamics without relying on the explicit form of the Hamiltonian.
https://arxiv.org/abs/1905.09168
Machine learning models trained on confidential datasets are increasingly being deployed for profit. Machine Learning as a Service (MLaaS) has made such models easily accessible to end-users. Prior work has developed model extraction attacks, in which an adversary extracts an approximation of MLaaS models by making black-box queries to it. However, none of these works is able to satisfy all the three essential criteria for practical model extraction: (1) the ability to work on deep learning models, (2) the non-requirement of domain knowledge and (3) the ability to work with a limited query budget. We design a model extraction framework that makes use of active learning and large public datasets to satisfy them. We demonstrate that it is possible to use this framework to steal deep classifiers trained on a variety of datasets from image and text domains. By querying a model via black-box access for its top prediction, our framework improves performance on an average over a uniform noise baseline by 4.70x for image tasks and 2.11x for text tasks respectively, while using only 30% (30,000 samples) of the public dataset at its disposal.
http://arxiv.org/abs/1905.09165
For the Small Size League of RoboCup 2018, Team ZJUNLict has won the champion and therefore, this paper thoroughly described the devotion which ZJUNLict has devoted and the effort that ZJUNLict has contributed. There are three mean optimizations for the mechanical part which accounted for most of our incredible goals, they are “Touching Point Optimization”, “Damping System Optimization”, and “Dribbler Optimization”. For the electrical part, we realized “Direct Torque Control”, “Efficient Radio Communication Protocol” which will be credited for stabilizing the dribbler and a more secure communication between robots and the computer. Our software group contributed as much as our hardware group with the effort of “Vision Lost Compensation” to predict the movement by kalman filter, and “Interception Prediction Algorithm” to achieve some skills and improve our ball possession rate.
http://arxiv.org/abs/1905.09157
Unsupervised domain adaptation (UDA) is the task of modifying a statistical model trained on labeled data from a source domain to achieve better performance on data from a target domain, with access to only unlabeled data in the target domain. Existing state-of-the-art UDA approaches use neural networks to learn representations that can predict the values of subset of important features called “pivot features.” In this work, we show that it is possible to improve on these methods by jointly training the representation learner with the task learner, and examine the importance of existing pivot selection methods.
http://arxiv.org/abs/1905.09153
Given enough multi-view image corresponding points (also called tie points) and ground control points (GCP), bundle adjustment for high-resolution satellite images is used to refine the orientations or most often used geometric parameters Rational Polynomial Coefficients (RPC) of each satellite image in a unified geodetic framework, which is very critical in many photogrammetry and computer vision applications. However, the growing number of high resolution spaceborne optical sensors has brought two challenges to the bundle adjustment: 1) images come from different satellite cameras may have different imaging dates, viewing angles, resolutions, etc., thus resulting in geometric and radiometric distortions in the bundle adjustment; 2) The large-scale mapping area always corresponds to vast number of bundle adjustment corrections (including RPC bias and object space point coordinates). Due to the limitation of computer memory, it is hard to refine all corrections at the same time. Hence, how to efficiently realize the bundle adjustment in large-scale regions is very important. This paper particularly addresses the multi-view large-scale bundle adjustment problem by two steps: 1) to get robust tie points among different satellite images, we design a multi-view, multi-source tie point matching algorithm based on plane rectification and epipolar constraints, which is able to compensate geometric and local nonlinear radiometric distortions among satellite datasets, and 2) to solve dozens of thousands or even millions of variables bundle adjustment corrections in the large scale bundle adjustment, we use an efficient solution with only a little computer memory. Experiments on in-track and off-track satellite datasets show that the proposed method is capable of computing sub-pixel accuracy bundle adjustment results.
http://arxiv.org/abs/1905.09152
Nowadays dense stereo matching has become one of the dominant tools in 3D reconstruction of urban regions for its low cost and high flexibility in generating dense 3D points. However, state-of-the-art stereo matching algorithms usually apply a semi-global matching (SGM) strategy. This strategy normally assumes the surface geometry pieceswise planar, where a smooth penalty is imposed to deal with non-texture or repeating-texture areas. This on one hand, generates much smooth surface models, while on the other hand, may partially leads to smoothing on depth discontinuities, particularly for fence-shaped regions or densely built areas with narrow streets. To solve this problem, in this work, we propose to use the line segment information extracted from the corresponding orthophoto as a pose-processing tool to sharpen the building boundary of the Digital Surface Model (DSM) generated by SGM. Two methods which are based on graph-cut and plane fitting are proposed and compared. Experimental results on several satellite datasets with ground truth show the robustness and effectiveness of the proposed DSM sharpening method.
http://arxiv.org/abs/1905.09150
Stereo dense image matching can be categorized to low-level feature based matching and deep feature based matching according to their matching cost metrics. Census has been proofed to be one of the most efficient low-level feature based matching methods, while fast Convolutional Neural Network (fst-CNN), as a deep feature based method, has small computing time and is robust for satellite images. Thus, a comparison between fst-CNN and census is critical for further studies in stereo dense image matching. This paper used cost function of fst-CNN and census to do stereo matching, then utilized semi-global matching method to obtain optimized disparity images. Those images are used to produce digital surface model to compare with ground truth points. It addresses that fstCNN performs better than census in the aspect of absolute matching accuracy, histogram of error distribution and matching completeness, but these two algorithms still performs in the same order of magnitude.
http://arxiv.org/abs/1905.09147
The distribution of sentence length in ordinary language is not well captured by the existing models. Here we survey previous models of sentence length and present our random walk model that offers both a better fit with the data and a better understanding of the distribution. We develop a generalization of KL divergence, discuss measuring the noise inherent in a corpus, and present a hyperparameter-free Bayesian model comparison method that has strong conceptual ties to Minimal Description Length modeling. The models we obtain require only a few dozen bits, orders of magnitude less than the naive nonparametric MDL models would.
http://arxiv.org/abs/1905.09139
We study a variant of domain adaptation for named-entity recognition where multiple, heterogeneously tagged training sets are available. Furthermore, the test tag-set is not identical to any individual training tag-set. Yet, the relations between all tags are provided in a tag hierarchy, covering the test tags as a combination of training tags. This setting occurs when various datasets are created using different annotation schemes. This is also the case of extending a tag-set with a new tag by annotating only the new tag in a new dataset. We propose to use the given tag hierarchy to jointly learn a neural network that shares its tagging layer among all tag-sets. We compare this model to combining independent models and to a model based on the multitasking approach. Our experiments show the benefit of the tag-hierarchy model, especially when facing non-trivial consolidation of tag-sets.
http://arxiv.org/abs/1905.09135
We propose AI-CARGO, a revenue management system for air-cargo that combines machine learning prediction with decision-making using mathematical optimization methods. AI-CARGO addresses a problem that is unique to the air-cargo business, namely the wide discrepancy between the quantity (weight or volume) that a shipper will book and the actual received amount at departure time by the airline. The discrepancy results in sub-optimal and inefficient behavior by both the shipper and the airline resulting in the overall loss of potential revenue for the airline. AI-CARGO also includes a data cleaning component to deal with the heterogeneous forms in which booking data is transmitted to the airline cargo system. AI-CARGO is deployed in the production environment of a large commercial airline company. We have validated the benefits of AI-CARGO using real and synthetic datasets. Especially, we have carried out simulations using dynamic programming techniques to elicit the impact on offloading costs and revenue generation of our proposed system. Our results suggest that combining prediction within a decision-making framework can help dramatically to reduce offloading costs and optimize revenue generation.
http://arxiv.org/abs/1905.09130
Automatic analysis of scanned historical documents comprises a wide range of image analysis tasks, which are often challenging for machine learning due to a lack of human-annotated learning samples. With the advent of deep neural networks, a promising way to cope with the lack of training data is to pre-train models on images from a different domain and then fine-tune them on historical documents. In the current research, a typical example of such cross-domain transfer learning is the use of neural networks that have been pre-trained on the ImageNet database for object recognition. It remains a mostly open question whether or not this pre-training helps to analyse historical documents, which have fundamentally different image properties when compared with ImageNet. In this paper, we present a comprehensive empirical survey on the effect of ImageNet pre-training for diverse historical document analysis tasks, including character recognition, style classification, manuscript dating, semantic segmentation, and content-based retrieval. While we obtain mixed results for semantic segmentation at pixel-level, we observe a clear trend across different network architectures that ImageNet pre-training has a positive effect on classification as well as content-based retrieval.
http://arxiv.org/abs/1905.09113
Deep learning is bringing remarkable contributions to the field of argumentation mining, but the existing approaches still need to fill the gap towards performing advanced reasoning tasks. We illustrate how neural-symbolic and statistical relational learning could play a crucial role in the integration of symbolic and sub-symbolic methods to achieve this goal.
http://arxiv.org/abs/1905.09103
Word embeddings have been widely adopted across several NLP applications. Most existing word embedding methods utilize sequential context of a word to learn its embedding. While there have been some attempts at utilizing syntactic context of a word, such methods result in an explosion of the vocabulary size. In this paper, we overcome this problem by proposing SynGCN, a flexible Graph Convolution based method for learning word embeddings. SynGCN utilizes the dependency context of a word without increasing the vocabulary size. Word embeddings learned by SynGCN outperform existing methods on various intrinsic and extrinsic tasks and provide an advantage when used with ELMo. We also propose SemGCN, an effective framework for incorporating diverse semantic knowledge for further enhancing learned word representations. We make the source code of both models available to encourage reproducible research.
http://arxiv.org/abs/1809.04283
In the past decade, social innovation projects have gained the attention of policy makers, as they address important social issues in an innovative manner. A database of social innovation is an important source of information that can expand collaboration between social innovators, drive policy and serve as an important resource for research. Such a database needs to have projects described and summarized. In this paper, we propose and compare several methods (e.g. SVM-based, recurrent neural network based, ensambled) for describing projects based on the text that is available on project websites. We also address and propose a new metric for automated evaluation of summaries based on topic modelling.
http://arxiv.org/abs/1905.09086
Performance of end-to-end neural networks on a given hardware platform is a function of its compute and memory signature, which in-turn, is governed by a wide range of parameters such as topology size, primitives used, framework used, batching strategy, latency requirements, precision etc. Current benchmarking tools suffer from limitations such as a) being either too granular like DeepBench (or) b) mandate a working implementation that is either framework specific or hardware-architecture specific (or) c) provide only high level benchmark metrics. In this paper, we present NTP (Neural Net Topology Profiler), a sophisticated benchmarking framework, to effectively identify memory and compute signature of an end-to-end topology on multiple hardware architectures, without the need to actually implement the topology in a framework. NTP is tightly integrated with hardware specific benchmark tools to enable exhaustive data collection and analysis. Using NTP, a deep learning researcher can quickly establish baselines needed to understand performance of an end-to-end neural network topology and make high level architectural decisions based on optimization techniques like layer sizing, quantization, pruning etc. Further, integration of NTP with frameworks like Tensorflow, Pytorch, Intel OpenVINO etc. allows for performance comparison along several vectors like a) Comparison of different frameworks on a given hardware b) Comparison of different hardware using a given framework c) Comparison across different heterogeneous hardware configurations for given framework etc. These capabilities empower a researcher to effortlessly make architectural decisions needed for achieving optimized performance on any hardware platform. The paper documents the architectural approach of NTP and demonstrates the capabilities of the tool by benchmarking Mozilla DeepSpeech, a popular Speech Recognition topology.
http://arxiv.org/abs/1905.09063
In recent studies, several asymptotic upper bounds on generalization errors on deep neural networks (DNNs) are theoretically derived. These bounds are functions of several norms of weights of the DNNs, such as the Frobenius and spectral norms, and they are computed for weights grouped according to either input and output channels of the DNNs. In this work, we conjecture that if we can impose multiple constraints on weights of DNNs to upper bound the norms of the weights, and train the DNNs with these weights, then we can attain empirical generalization errors closer to the derived theoretical bounds, and improve accuracy of the DNNs. To this end, we pose two problems. First, we aim to obtain weights whose different norms are all upper bounded by a constant number, e.g. 1.0. To achieve these bounds, we propose a two-stage renormalization procedure; (i) normalization of weights according to different norms used in the bounds, and (ii) reparameterization of the normalized weights to set a constant and finite upper bound of their norms. In the second problem, we consider training DNNs with these renormalized weights. To this end, we first propose a strategy to construct joint spaces (manifolds) of weights according to different constraints in DNNs. Next, we propose a fine-grained SGD algorithm (FG-SGD) for optimization on the weight manifolds to train DNNs with assurance of convergence to minima. Experimental results show that image classification accuracy of baseline DNNs can be boosted using FG-SGD on collections of manifolds identified by multiple constraints.
http://arxiv.org/abs/1905.09054
Word embeddings have gained significant attention as learnable representations of semantic relations between words, and have been shown to improve upon the results of traditional word representations. However, little effort has been devoted to using embeddings for the retrieval of entity associations beyond pairwise relations. In this paper, we use popular embedding methods to train vector representations of an entity-annotated news corpus, and evaluate their performance for the task of predicting entity participation in news events versus a traditional word cooccurrence network as a baseline. To support queries for events with multiple participating entities, we test a number of combination modes for the embedding vectors. While we find that even the best combination modes for word embeddings do not quite reach the performance of the full cooccurrence network, especially for rare entities, we observe that different embedding methods model different types of relations, thereby indicating the potential for ensemble methods.
http://arxiv.org/abs/1905.09052
Matrix Factorization is a popular non-convex objective, for which alternating minimization schemes are mostly used. They usually suffer from the major drawback that the solution is biased towards one of the optimization variables. A remedy is non-alternating schemes. However, due to a lack of Lipschitz continuity of the gradient in matrix factorization problems, convergence cannot be guaranteed. A recently developed remedy relies on the concept of Bregman distances, which generalizes the standard Euclidean distance. We exploit this theory by proposing a novel Bregman distance for matrix factorization problems, which, at the same time, allows for simple/closed form update steps. Therefore, for non-alternating schemes, such as the recently introduced Bregman Proximal Gradient (BPG) method and an inertial variant Convex–Concave Inertial BPG (CoCaIn BPG), convergence of the whole sequence to a stationary point is proved for Matrix Factorization. In several experiments, we observe a superior performance of our non-alternating schemes in terms of speed and objective value at the limit point.
http://arxiv.org/abs/1905.09050
The hyperdense middle cerebral artery (MCA) dot sign has been reported as an important factor in the diagnosis of acute ischemic stroke due to large vessel occlusion. Interpreting the initial CT brain scan in these patients requires high level of expertise, and has high inter-observer variability. An automated computerized interpretation of the urgent CT brain image, with an emphasis to pick up early signs of ischemic stroke will facilitate early patient diagnosis, triage, and shorten the door-to-revascularization time for these group of patients. In this paper, we present an automated detection method of segmenting the MCA dot sign on non-contrast CT brain image scans based on powerful deep learning technique.
http://arxiv.org/abs/1905.09049
This work regards our preliminary investigation on the problem of path planning for autonomous vehicles that move on a freeway. We approach this problem by proposing a driving policy based on Reinforcement Learning. The proposed policy makes minimal or no assumptions about the environment, since no a priori knowledge about the system dynamics is required. We compare the performance of the proposed policy against an optimal policy derived via Dynamic Programming and against manual driving simulated by SUMO traffic simulator.
http://arxiv.org/abs/1905.09046
We present an end-to-end learned algorithm for seeded segmentation. Our method is based on the Random Walker algorithm, where we predict the edge weights of the underlying graph using a convolutional neural network. This can be interpreted as learning context-dependent diffusivities for a linear diffusion process. Besides calculating the exact gradient for optimizing these diffusivities, we also propose simplifications that sparsely sample the gradient and still yield competitive results. The proposed method achieves the currently best results on a seeded version of the CREMI neuron segmentation challenge.
http://arxiv.org/abs/1905.09045
In this paper we address a classification problem that has not been considered before, namely motion segmentation given pairwise matches only. Our contribution to this unexplored task is a novel formulation of motion segmentation as a two-step process. First, motion segmentation is performed on image pairs independently. Secondly, we combine independent pairwise segmentation results in a robust way into the final globally consistent segmentation. Our approach is inspired by the success of averaging methods. We demonstrate in simulated as well as in real experiments that our method is very effective in reducing the errors in the pairwise motion segmentation and can cope with large number of mismatches.
http://arxiv.org/abs/1905.09043
Egocentric action anticipation consists in understanding which objects the camera wearer will interact with in the near future and which actions they will perform. We tackle the problem proposing an architecture able to anticipate actions at multiple temporal scales using two LSTMs to 1) summarize the past, and 2) formulate predictions about the future. The input video is processed considering three complimentary modalities: appearance (RGB), motion (optical flow) and objects (object-based features). Modality-specific predictions are fused using a novel Modality ATTention (MATT) mechanism which learns to weigh modalities in an adaptive fashion. Extensive evaluations on two large-scale benchmark datasets show that our method outperforms prior art by up to +7% on the challenging EPIC-KITCHENS dataset including more than 2500 actions, and generalizes to EGTEA Gaze+. Our approach is also shown to generalize to the tasks of early action recognition and action recognition. At the moment of submission, our method is ranked first in the leaderboard of the EPIC-KITCHENS egocentric action anticipation challenge.
http://arxiv.org/abs/1905.09035
We propose a network architecture to perform efficient scene understanding. This work presents three main novelties: the first is an Improved Guided Upsampling Module that can replace in toto the decoder part in common semantic segmentation networks. Our second contribution is the introduction of a new module based on spatial sampling to perform Instance Segmentation. It provides a very fast instance segmentation, needing only thresholding as post-processing step at inference time. Finally, we propose a novel efficient network design that includes the new modules and test it against different datasets for outdoor scene understanding. To our knowledge, our network is one of the themost efficient architectures for scene understanding published to date, furthermore being 8.6% more accurate than the fastest competitor on semantic segmentation and almost five times faster than the most efficient network for instance segmentation.
http://arxiv.org/abs/1905.09033
The connected automated vehicle has been often touted as a technology that will become pervasive in society in the near future. One can view an automated vehicle as having Artificial Intelligence (AI) capabilities, being able to self-drive, sense its surroundings, recognise objects in its vicinity, and perform reasoning and decision-making. Rather than being stand alone, we examine the need for automated vehicles to cooperate and interact within their socio-cyber-physical environments, including the problems cooperation will solve, but also the issues and challenges. We review current work in cooperation for automated vehicles, based on selected examples from the literature. We conclude noting the need for the ability to behave cooperatively as a form of social-AI capability for automated vehicles, beyond sensing the immediate environment and beyond the underlying networking technology.
http://arxiv.org/abs/1710.00461
It is said that beauty is in the eye of the beholder. But how exactly can we characterize such discrepancies in interpretation? For example, are there any specific features of an image that makes person A regard an image as beautiful while person B finds the same image displeasing? Such questions ultimately aim at explaining our individual ways of interpretation, an intention that has been of fundamental importance to the social sciences from the beginning. More recently, advances in computer science brought up two related questions: First, can computational tools be adopted for analyzing ways of interpretation? Second, what if the “beholder” is a computer model, i.e., how can we explain a computer model’s point of view? Numerous efforts have been made regarding both of these points, while many existing approaches focus on particular aspects and are still rather separate. With this paper, in order to connect these approaches we introduce a theoretical framework for analyzing interpretation, which is applicable to interpretation of both human beings and computer models. We give an overview of relevant computational approaches from various fields, and discuss the most common and promising application areas. The focus of this paper lies on interpretation of text and image data, while many of the presented approaches are applicable to other types of data as well.
http://arxiv.org/abs/1811.04028
Is it possible to predict the motivation of players just by observing their gameplay data? Even if so, how should we measure motivation in the first place? To address the above questions, on the one end, we collect a large dataset of gameplay data from players of the popular game Tom Clancy’s The Division. On the other end, we ask them to report their levels of competence, autonomy, relatedness and presence using the Ubisoft Perceived Experience Questionnaire. After processing the survey responses in an ordinal fashion we employ preference learning methods based on support vector machines to infer the mapping between gameplay and the reported four motivation factors. Our key findings suggest that gameplay features are strong predictors of player motivation as the best obtained models reach accuracies of near certainty, from 92% up to 94% on unseen players.
http://arxiv.org/abs/1902.00040
Robots need to learn behaviors in intuitive and practical ways for widespread deployment in human environments. To learn a robot behavior end-to-end, we train a variant of the ResNet that maps eye-in-hand camera images to end-effector velocities. In our setup, a human teacher demonstrates the task via joystick. We show that a simple servoing task can be learned in less than an hour including data collection, model training and deployment time. Moreover, 16 minutes of demonstrations were enough for the robot to learn the task.
http://arxiv.org/abs/1905.09025
Generative adversarial network (GAN)-based image inpainting methods which utilize coarse-to-fine network with a contextual attention module (CAM) have shown remarkable performance. However, they require numerous computational resources such as convolution operations and network parameters due to two stacked generative networks, which results in a low speed. To address this problem, we propose a novel network structure called PEPSI: parallel extended-decoder path for semantic inpainting network, which aims at not only reducing hardware costs but also improving the inpainting performance. The PEPSI consists of a single shared encoding network and parallel decoding networks with coarse and inpainting paths. The coarse path generates a preliminary inpainting result to train the encoding network for prediction of features for the CAM. At the same time, the inpainting path results in higher inpainting quality with refined features reconstructed using the CAM. In addition, we propose a Diet-PEPSI which significantly reduces the network parameters while maintaining the performance. In the proposed method, we present a Diet-PEPSI unit (DPU) which effectively aggregates the global contextual information with a small number of parameters. Extensive experiments and comparisons with state-of-the-art image inpainting methods demonstrate that both PEPSI and Diet-PEPSI achieve significant improvements in qualitative scores and reduced computation cost.
http://arxiv.org/abs/1905.09010
Visual inspection of underwater structures by vehicles, e.g. remotely operated vehicles (ROVs), plays an important role in scientific, military, and commercial sectors. However, the automatic extraction of information using software tools is hindered by the characteristics of water which degrade the quality of captured videos. As a contribution for restoring the color of underwater images, Underwater Denoising Autoencoder (UDAE) model is developed using a denoising autoencoder with U-Net architecture. The proposed network takes into consideration the accuracy and the computation cost to enable real-time implementation on underwater visual tasks using end-to-end autoencoder network. Underwater vehicles perception is improved by reconstructing captured frames; hence obtaining better performance in underwater tasks. Related learning methods use generative adversarial networks (GANs) to generate color corrected underwater images, and to our knowledge this paper is the first to deal with a single autoencoder capable of producing same or better results. Moreover, image pairs are constructed for training the proposed network, where it is hard to obtain such dataset from underwater scenery. At the end, the proposed model is compared to a state-of-the-art method.
http://arxiv.org/abs/1905.09000
Vehicle Re-ID has recently attracted enthusiastic attention due to its potential applications in smart city and urban surveillance. However, it suffers from large intra-class variation caused by view variations and illumination changes, and inter-class similarity especially for different identities with the similar appearance. To handle these issues, in this paper, we propose a novel deep network architecture, which guided by meaningful attributes including camera views, vehicle types and colors for vehicle Re-ID. In particular, our network is end-to-end trained and contains three subnetworks of deep features embedded by the corresponding attributes (i.e., camera view, vehicle type and vehicle color). Moreover, to overcome the shortcomings of limited vehicle images of different views, we design a view-specified generative adversarial network to generate the multi-view vehicle images. For network training, we annotate the view labels on the VeRi-776 dataset. Note that one can directly adopt the pre-trained view (as well as type and color) subnetwork on the other datasets with only ID information, which demonstrates the generalization of our model. Extensive experiments on the benchmark datasets VeRi-776 and VehicleID suggest that the proposed approach achieves the promising performance and yields to a new state-of-the-art for vehicle Re-ID.
http://arxiv.org/abs/1905.08997
We propose a new multilabel classifier, called LapTool-Net to detect the presence of surgical tools in each frame of a laparoscopic video. The novelty of LapTool-Net is the exploitation of the correlation among the usage of different tools and, the tools and tasks - namely, the context of the tools’ usage. Towards this goal, the pattern in the co-occurrence of the tools is utilized for designing a decision policy for a multilabel classifier based on a Recurrent Convolutional Neural Network (RCNN) architecture to simultaneously extract the spatio-temporal features. In contrast to the previous multilabel classification methods, the RCNN and the decision model are trained in an end-to-end manner using a multitask learning scheme. To overcome the high imbalance and avoid overfitting caused by the lack of variety in the training data, a high down-sampling rate is chosen based on the more frequent combinations. Furthermore, at the post-processing step, the prediction for all the frames of a video are corrected by designing a bi-directional RNN to model the long-term task’s order. LapTool-net was trained using a publicly available dataset of laparoscopic cholecystectomy. The results show LapTool-Net outperforms existing methods significantly, even while using fewer training samples and a shallower architecture.
http://arxiv.org/abs/1905.08983
Several recent works discussed application-driven image restoration neural networks, which are capable of not only removing noise in images but also preserving their semantic-aware details, making them suitable for various high-level computer vision tasks as the pre-processing step. However, such approaches require extra annotations for their high-level vision tasks, in order to train the joint pipeline using hybrid losses. The availability of those annotations is yet often limited to a few image sets, potentially restricting the general applicability of these methods to denoising more unseen and unannotated images. Motivated by that, we propose a segmentation-aware image denoising model dubbed U-SAID, based on a novel unsupervised approach with a pixel-wise uncertainty loss. U-SAID does not need any ground-truth segmentation map, and thus can be applied to any image dataset. It generates denoised images with comparable or even better quality, and the denoised results show stronger robustness for subsequent semantic segmentation tasks, when compared to either its supervised counterpart or classical “application-agnostic” denoisers. Moreover, we demonstrate the superior generalizability of U-SAID in three-folds, by plugging its “universal” denoiser without fine-tuning: (1) denoising unseen types of images; (2) denoising as pre-processing for segmenting unseen noisy images; and (3) denoising for unseen high-level tasks. Extensive experiments demonstrate the effectiveness, robustness and generalizability of the proposed U-SAID over various popular image sets.
http://arxiv.org/abs/1905.08965
We introduce a kind of partial observability to the projective simulation (PS) learning method. It is done by adding a belief projection operator and an observability parameter to the original framework of the efficiency of the PS model. I provide theoretical formulations, network representations, and situated scenarios derived from the invasion toy problem as a starting point for some multi-agent PS models.
http://arxiv.org/abs/1610.09372
Considering the widespread use of mobile and voice search, answer passage retrieval for non-factoid questions plays a critical role in modern information retrieval systems. Despite the importance of the task, the community still feels the significant lack of large-scale non-factoid question answering collections with real questions and comprehensive relevance judgments. In this paper, we develop and release a collection of 2,626 open-domain non-factoid questions from a diverse set of categories. The dataset, called ANTIQUE, contains 34,011 manual relevance annotations. The questions were asked by real users in a community question answering service, i.e., Yahoo! Answers. Relevance judgments for all the answers to each question were collected through crowdsourcing. To facilitate further research, we also include a brief analysis of the data as well as baseline results on both classical and recently developed neural IR models.
http://arxiv.org/abs/1905.08957
We present a method to find globally optimal topology and trajectory jointly for planar linkages. Planar linkage structures can generate complex end-effector trajectories using only a single rotational actuator, which is very useful in building low-cost robots. We address the problem of searching for the optimal topology and geometry of these structures. However, since topology changes are non-smooth and non-differentiable, conventional gradient-based searches cannot be used. We formulate this problem as a mixed-integer convex programming (MICP) problem, for which a global optimum can be found using the branch-and-bound (BB) algorithm. Compared to existing methods, our experiments show that the proposed approach finds complex linkage structures more efficiently and generates end-effector trajectories more accurately.
http://arxiv.org/abs/1905.08956
Point cloud data from 3D LiDAR sensors are one of the most crucial sensor modalities for versatile safety-critical applications such as self-driving vehicles. Since the annotations of point cloud data is an expensive and time-consuming process, therefore recently the utilisation of simulated environments and 3D LiDAR sensors for this task started to get some popularity. With simulated sensors and environments, the process for obtaining an annotated synthetic point cloud data became much easier. However, the generated synthetic point cloud data are still missing the artefacts usually exist in point cloud data from real 3D LiDAR sensors. As a result, the performance of the trained models on this data for perception tasks when tested on real point cloud data is degraded due to the domain shift between simulated and real environments. Thus, in this work, we are proposing a domain adaptation framework for bridging this gap between synthetic and real point cloud data. Our proposed framework is based on the deep cycle-consistent generative adversarial networks (CycleGAN) architecture. We have evaluated the performance of our proposed framework on the task of vehicle detection from a bird’s eye view (BEV) point cloud images coming from real 3D LiDAR sensors. The framework has shown competitive results with an improvement of more than 7% in average precision score over other baseline approaches when tested on real BEV point cloud images.
http://arxiv.org/abs/1905.08955
Emerging research in Neural Question Generation (NQG) has started to integrate a larger variety of inputs, and generating questions requiring higher levels of cognition. These trends point to NQG as a bellwether for NLP, about how human intelligence embodies the skills of curiosity and integration. We present a comprehensive survey of neural question generation, examining the corpora, methodologies, and evaluation methods. From this, we elaborate on what we see as emerging on NQG’s trend: in terms of the learning paradigms, input modalities, and cognitive levels considered by NQG. We end by pointing out the potential directions ahead.
http://arxiv.org/abs/1905.08949
Neural Machine Translation (NMT) has been proven to achieve impressive results. The NMT system translation results depend strongly on the size and quality of parallel corpora. Nevertheless, for many language pairs, no rich-resource parallel corpora exist. As described in this paper, we propose a corpus augmentation method by segmenting long sentences in a corpus using back-translation and generating pseudo-parallel sentence pairs. The experiment results of the Japanese-Chinese and Chinese-Japanese translation with Japanese-Chinese scientific paper excerpt corpus (ASPEC-JC) show that the method improves translation performance.
http://arxiv.org/abs/1905.08945
Mixup, a recent proposed data augmentation method through linearly interpolating inputs and modeling targets of random samples, has demonstrated its capability of significantly improving the predictive accuracy of the state-of-the-art networks for image classification. However, how this technique can be applied to and what is its effectiveness on natural language processing (NLP) tasks have not been investigated. In this paper, we propose two strategies for the adaption of Mixup on sentence classification: one performs interpolation on word embeddings and another on sentence embeddings. We conduct experiments to evaluate our methods using several benchmark datasets. Our studies show that such interpolation strategies serve as an effective, domain independent data augmentation approach for sentence classification, and can result in significant accuracy improvement for both CNN and LSTM models.
http://arxiv.org/abs/1905.08941
Hiring robots for the workplaces is a challenging task as robots have to cater to customer demands, follow organizational protocols and behave with social etiquette. In this study, we propose to have a humanoid social robot, Nadine, as a customer service agent in an open social work environment. The objective of this study is to analyze the effects of humanoid robots on customers at work environment, and see if it can handle social scenarios. We propose to evaluate these objectives through two modes, namely, survey questionnaire and customer feedback. We also propose a novel approach to analyze customer feedback data (text) using sentic computing methods. Specifically, we employ aspect extraction and sentiment analysis to analyze the data. From our framework, we detect sentiment associated to the aspects that mainly concerned the customers during their interaction. This allows us to understand customers expectations and current limitations of robots as employees.
http://arxiv.org/abs/1905.08937
Semantic segmentation is pixel-wise classification which retains critical spatial information. The “feature map reuse” has been commonly adopted in CNN based approaches to take advantage of feature maps in the early layers for the later spatial reconstruction. Along this direction, we go a step further by proposing a fully dense neural network with an encoder-decoder structure that we abbreviate as FDNet. For each stage in the decoder module, feature maps of all the previous blocks are adaptively aggregated to feed-forward as input. On the one hand, it reconstructs the spatial boundaries accurately. On the other hand, it learns more efficiently with the more efficient gradient backpropagation. In addition, we propose the boundary-aware loss function to focus more attention on the pixels near the boundary, which boosts the “hard examples” labeling. We have demonstrated the best performance of the FDNet on the two benchmark datasets: PASCAL VOC 2012, NYUDv2 over previous works when not considering training on other datasets.
http://arxiv.org/abs/1905.08929