In the Big Data era, the community of PAM faces strong challenges, including the need for more standardized processing tools accross its different applications in oceanography, and for more scalable and high-performance computing systems to process more efficiently the everly growing datasets. In this work we address conjointly both issues by first proposing a detailed theory-plus-code document of a classical analysis workflow to describe the content of PAM data, which hopefully will be reviewed and adopted by a maximum of PAM experts to make it standardized. Second, we transposed this workflow into the Scala language within the Spark/Hadoop frameworks so it can be directly scaled out on several node cluster.
http://arxiv.org/abs/1902.06659
Deep convolutional networks have recently shown excellent performance on Fine-Grained Vehicle Classification. Based on these existing works, we consider that the back-probation algorithm does not focus on extracting less discriminative feature as much as possible, but focus on that the loss function equals zero. Intuitively, if we can learn less discriminative features, and these features still could fit the training data well, the generalization ability of neural network could be improved. Therefore, we propose a new layer which is placed between fully connected layers and convolutional layers, called as Chanel Max Pooling. The proposed layer groups the features map first and then compress each group into a new feature map by computing maximum of pixels with same positions in the group of feature maps. Meanwhile, the proposed layer has an advantage that it could help neural network reduce massive parameters. Experimental results on two fine-grained vehicle datasets, the Stanford Cars-196 dataset and the Comp Cars dataset, demonstrate that the proposed layer could improve classification accuracies of deep neural networks on fine-grained vehicle classification in the situation that a massive of parameters are reduced. Moreover, it has a competitive performance with the-state-of-art performance on the two datasets.
http://arxiv.org/abs/1902.11107
Current captioning approaches can describe images using black-box architectures whose behavior is hardly controllable and explainable from the exterior. As an image can be described in infinite ways depending on the goal and the context at hand, a higher degree of controllability is needed to apply captioning algorithms in complex scenarios. In this paper, we introduce a novel framework for image captioning which can generate diverse descriptions by allowing both grounding and controllability. Given a control signal in the form of a sequence or set of image regions, we generate the corresponding caption through a recurrent architecture which predicts textual chunks explicitly grounded on regions, following the constraints of the given control. Experiments are conducted on Flickr30k Entities and on COCO Entities, an extended version of COCO in which we add grounding annotations collected in a semi-automatic manner. Results demonstrate that our method achieves state of the art performances on controllable image captioning, in terms of caption quality and diversity. Code and annotations are publicly available at: this https URL.
https://arxiv.org/abs/1811.10652
This work proposes a new method to accurately complete sparse LiDAR maps guided by RGB images. For autonomous vehicles and robotics the use of LiDAR is indispensable in order to achieve precise depth predictions. A multitude of applications depend on the awareness of their surroundings, and use depth cues to reason and react accordingly. On the one hand, monocular depth prediction methods fail to generate absolute and precise depth maps. On the other hand, stereoscopic approaches are still significantly outperformed by LiDAR based approaches. The goal of the depth completion task is to generate dense depth predictions from sparse and irregular point clouds which are mapped to a 2D plane. We propose a new framework which extracts both global and local information in order to produce proper depth maps. We argue that simple depth completion does not require a deep network. However, we additionally propose a fusion method with RGB guidance from a monocular camera in order to leverage object information and to correct mistakes in the sparse input. This improves the accuracy significantly. Moreover, confidence masks are exploited in order to take into account the uncertainty in the depth predictions from each modality. This fusion method outperforms the state-of-the-art and ranks first on the KITTI depth completion benchmark. Our code with visualizations is available.
http://arxiv.org/abs/1902.05356
Towards improving the performance in various music information processing tasks, recent studies exploit different modalities able to capture diverse aspects of music. Such modalities include audio recordings, symbolic music scores, mid-level representations, motion, and gestural data, video recordings, editorial or cultural tags, lyrics and album cover arts. This paper critically reviews the various approaches adopted in Music Information Processing and Retrieval and highlights how multimodal algorithms can help Music Computing applications. First, we categorize the related literature based on the application they address. Subsequently, we analyze existing information fusion approaches, and we conclude with the set of challenges that Music Information Retrieval and Sound and Music Computing research communities should focus in the next years.
http://arxiv.org/abs/1902.05347
The use of the Series Elastic Actuator (SEA) system as an actuator system equipped with a compliant element has contributed not only to advances in human interacting robots but also to a wide range of improvements in the robotics area. Nevertheless, there are still limitations in its performance; the elastic spring that is adopted to provide compliance is considered to limit the actuator performance thus lowering the frequency bandwidth of force/torque generation, and the bandwidth decreases even more when it is supposed to provide large torque. This weakness is in turn owing to the limitations of motor and motor drives such as torque and velocity limits. In this paper, mathematical tools to analyze the impact of these limitations on the performance of SEA as a transmission system are provided. A novel criterion called Maximum Torque Transmissibility (MTT)is defined to assess the ability of SEA to fully utilize maximum continuous motor torque. Moreover, an original frequency bandwidth concept, maximum torque frequency bandwidth, which can indicate the maximum frequency up to which the SEA can generate the maximum torque, is proposed based on the proposed MTT. The proposed MTT can be utilized as a unique criterion of the performance, and thus various design parameters including the load condition, mechanical design parameters, and controller parameters of a SEA can be evaluated with its use. Experimental results under various conditions verify that MTT can precisely indicate the limitation of the performance of SEA, and that it can be utilized to accurately analyze the limitation of the controller of SEA.
http://arxiv.org/abs/1902.05346
In this paper, we consider the general problem of obstacle avoidance based on dynamical system. The modulation matrix is developed by introducing orthogonal coordinates, which makes the modulation matrix more reasonable. The new trajectory’s direction can be represented by the linear combination of orthogonal coordinates. A orthogonal coordinates manipulating approach is proposed by introducing rotating matrix to solve the local minimal problem and provide more reasonable motions in 3-D or higher dimension space. Experimental results on several designed dynamical systems demonstrate the effectiveness of the proposed approach.
http://arxiv.org/abs/1902.05343
Following improvements in deep neural networks, state-of-the-art networks have been proposed for human recognition using point clouds captured by LiDAR. However, the performance of these networks strongly depends on the training data. An issue with collecting training data is labeling. Labeling by humans is necessary to obtain the ground truth label; however, labeling requires huge costs. Therefore, we propose an automatic labeled data generation pipeline, for which we can change any parameters or data generation environments. Our approach uses a human model named Dhaiba and a background of Miraikan and consequently generated realistic artificial data. We present 500k+ data generated by the proposed pipeline. This paper also describes the specification of the pipeline and data details with evaluations of various approaches.
http://arxiv.org/abs/1902.05341
Breast lesion localization using tactile imaging is a new and developing direction in medical science. To achieve the goal, proper image reconstruction and image registration can be a valuable asset. In this paper, a new approach of the segmentation-based image surface reconstruction algorithm is used to reconstruct the surface of a breast phantom. In breast tissue, the sub-dermal vein network is used as a distinguishable pattern for reconstruction. The proposed image capturing device contacts the surface of the phantom, and surface deformation will occur due to applied force at the time of scanning. A novel force based surface rectification system is used to reconstruct a deformed surface image to its original structure. For the construction of the full surface from rectified images, advanced affine scale-invariant feature transform (A-SIFT) is proposed to reduce the affine effect in time when data capturing. Camera position based image stitching approach is applied to construct the final original non-rigid surface. The proposed model is validated in theoretical models and real scenarios, to demonstrate its advantages with respect to competing methods. The result of the proposed method, applied to path reconstruction, ends with a positioning accuracy of 99.7%
http://arxiv.org/abs/1902.05340
This paper develops an accurate force control algorithm for series elastic actuators (SEAs) based on a novel force estimation scheme, called transmission force observer (TFOB). The proposed method is designed to improve an inferior force measurement of the SEA caused by nonlinearities of the elastic transmission and measurement noise and error of its deformation sensor. This paper first analyzes the limitation of the conventional methods for the SEA transmission force sensing and then investigates its stochastic characteristics, which indeed provide the base to render the accurate force control performance incorporated with the TFOB. In particular, a tuning parameter is introduced from holistic closed-loop system analyses in the frequency domain. This gives a guideline to attain optimum performance of the force-controlled SEA system. The proposed algorithm is experimentally verified in an actual SEA hardware setup.
http://arxiv.org/abs/1902.05338
In this paper we address the problem of artist style transfer where the painting style of a given artist is applied on a real world photograph. We train our neural networks in adversarial setting via recently introduced quadratic potential divergence for stable learning process. To further improve the quality of generated artist stylized images we also integrate some of the recently introduced deep learning techniques in our method. To our best knowledge this is the first attempt towards artist style transfer via quadratic potential divergence. We provide some stylized image samples in the supplementary material. The source code for experimentation was written in PyTorch and is available online in my GitHub repository.
http://arxiv.org/abs/1902.11108
In image quality enhancement processing, it is the most important to predict how humans perceive processed images since human observers are the ultimate receivers of the images. Thus, objective image quality assessment (IQA) methods based on human visual sensitivity from psychophysical experiments have been extensively studied. Thanks to the powerfulness of deep convolutional neural networks (CNN), many CNN based IQA models have been studied. However, previous CNN-based IQA models have not fully utilized the characteristics of human visual systems (HVS) for IQA problems by simply entrusting everything to CNN where the CNN-based models are often trained as a regressor to predict the scores of subjective quality assessment obtained from IQA datasets. In this paper, we propose a novel HVS-inspired deep IQA network, called Deep HVS-IQA Net, where the human psychophysical characteristics such as visual saliency and just noticeable difference (JND) are incorporated at the front-end of the Deep HVS-IQA Net. To our best knowledge, our work is the first HVS-inspired trainable IQA network that considers both the visual saliency and JND characteristics of HVS. Furthermore, we propose a rank loss to train our Deep HVS-IQA Net effectively so that perceptually important features can be extracted for image quality prediction. The rank loss can penalize the Deep HVS-IQA Net when the order of its predicted quality scores is different from that of the ground truth scores. We evaluate the proposed Deep HVS-IQA Net on large IQA datasets where it outperforms all the recent state-of-the-art IQA methods.
http://arxiv.org/abs/1902.05316
In this paper, we propose an approach for transferring the knowledge of a neural model for sequence labeling, learned from the source domain, to a new model trained on a target domain, where new label categories appear. Our transfer learning (TL) techniques enable to adapt the source model using the target data and new categories, without accessing to the source data. Our solution consists in adding new neurons in the output layer of the target model and transferring parameters from the source model, which are then fine-tuned with the target data. Additionally, we propose a neural adapter to learn the difference between the source and the target label distribution, which provides additional important information to the target model. Our experiments on Named Entity Recognition show that (i) the learned knowledge in the source model can be effectively transferred when the target data contains new categories and (ii) our neural adapter further improves such transfer.
http://arxiv.org/abs/1902.05309
Deep learning, due to its unprecedented success in tasks such as image classification, has emerged as a new tool in image reconstruction with potential to change the field. In this paper we demonstrate a crucial phenomenon: deep learning typically yields unstablemethods for image reconstruction. The instabilities usually occur in several forms: (1) tiny, almost undetectable perturbations, both in the image and sampling domain, may result in severe artefacts in the reconstruction, (2) a small structural change, for example a tumour, may not be captured in the reconstructed image and (3) (a counterintuitive type of instability) more samples may yield poorer performance. Our new stability test with algorithms and easy to use software detects the instability phenomena. The test is aimed at researchers to test their networks for instabilities and for government agencies, such as the Food and Drug Administration (FDA), to secure safe use of deep learning methods.
http://arxiv.org/abs/1902.05300
Controller placement problem (CPP) is a key issue for Software-Defined Networking (SDN) with distributed controller architectures. This problem aims to determine a suitable number of controllers deployed in important locations so as to optimize the overall network performance. In comparison to communication delay, existing literature on the CPP assumes that the influence of controller workload distribution on network performance is negligible. In this paper, we tackle the CPP that simultaneously considers the communication delay, the control plane utilization, and the controller workload distribution. Due to this reason, our CPP is intrinsically different from and clearly more difficult than any previously studied CPPs that are NP-hard. To tackle this challenging issue, we develop a new algorithm that seamlessly integrates the genetic algorithm (GA) and the gradient descent (GD) optimization method. Particularly, GA is used to search for suitable CPP solutions. The quality of each solution is further evaluated through GD. Simulation results on two representative network scenarios (small-scale and large-scale) show that our algorithm can effectively strike the trade-off between the control plane utilization and the network response time.
http://arxiv.org/abs/1902.09451
Effective fusion of complementary information captured by multi-modal sensors (visible and infrared cameras) enables robust pedestrian detection under various surveillance situations (e.g. daytime and nighttime). In this paper, we present a novel box-level segmentation supervised learning framework for accurate and real-time multispectral pedestrian detection by incorporating features extracted in visible and infrared channels. Specifically, our method takes pairs of aligned visible and infrared images with easily obtained bounding box annotations as input and estimates accurate prediction maps to highlight the existence of pedestrians. It offers two major advantages over the existing anchor box based multispectral detection methods. Firstly, it overcomes the hyperparameter setting problem occurred during the training phase of anchor box based detectors and can obtain more accurate detection results, especially for small and occluded pedestrian instances. Secondly, it is capable of generating accurate detection results using small-size input images, leading to improvement of computational efficiency for real-time autonomous driving applications. Experimental results on KAIST multispectral dataset show that our proposed method outperforms state-of-the-art approaches in terms of both accuracy and speed.
http://arxiv.org/abs/1902.05291
Rolling Horizon Evolutionary Algorithms (RHEA) are a class of online planning methods for real-time game playing; their performance is closely related to the planning horizon and the search time allowed. In this paper, we propose to learn a prior for RHEA in an offline manner by training a value network and a policy network. The value network is used to reduce the planning horizon by providing an estimation of future rewards, and the policy network is used to initialize the population, which helps to narrow down the search scope. The proposed algorithm, named prior-based RHEA (p-RHEA), trains policy and value networks by performing planning and learning iteratively. In the planning stage, the horizon-limited search assisted with the policy network and value network is performed to improve the policies and collect training samples. In the learning stage, the policy network and value network are trained with the collected samples to learn better prior knowledge. Experimental results on OpenAI Gym MuJoCo tasks show that the performance of the proposed p-RHEA is significantly improved compared to that of RHEA.
http://arxiv.org/abs/1902.05284
Image-based algorithmic software segmentation is an increasingly important topic in many medical fields. Algorithmic segmentation is used for medical three-dimensional visualization, diagnosis or treatment support, especially in complex medical cases. However, accessible medical databases are limited, and valid medical ground truth databases for the evaluation of algorithms are rare and usually comprise only a few images. Inaccuracy or invalidity of medical ground truth data and image-based artefacts also limit the creation of such databases, which is especially relevant for CT data sets of the maxillomandibular complex. This contribution provides a unique and accessible data set of the complete mandible, including 20 valid ground truth segmentation models originating from 10 CT scans from clinical practice without artefacts or faulty slices. From each CT scan, two 3D ground truth models were created by clinical experts through independent manual slice-by-slice segmentation, and the models were statistically compared to prove their validity. These data could be used to conduct serial image studies of the human mandible, evaluating segmentation algorithms and developing adequate image tools.
http://arxiv.org/abs/1902.05255
This paper introduces a novel approach for 3D semantic instance segmentation on point clouds. A 3D convolutional neural network called submanifold sparse convolutional network is used to generate semantic predictions and instance embeddings simultaneously. To obtain discriminative embeddings for each 3D instance, a structure-aware loss function is proposed which considers both the structure information and the embedding information. To get more consistent embeddings for each 3D instance, attention-based k nearest neighbour (KNN) is proposed to assign different weights for different neighbours. Based on the attention-based KNN, we add a graph convolutional network after the sparse convolutional network to get refined embeddings. Our network can be trained end-to-end. A simple mean-shift algorithm is utilized to cluster refined embeddings to get final instance predictions. As a result, our framework can output both the semantic prediction and the instance prediction. Experiments show that our approach outperforms all state-of-art methods on ScanNet benchmark and NYUv2 dataset.
http://arxiv.org/abs/1902.05247
Multilinguality is gradually becoming ubiquitous in the sense that more and more researchers have successfully shown that using additional languages help improve the results in many Natural Language Processing tasks. Multilingual Multiway Corpora (MMC) contain the same sentence in multiple languages. Such corpora have been primarily used for Multi-Source and Pivot Language Machine Translation but are also useful for developing multilingual sequence taggers by transfer learning. While these corpora are available, they are not organized for multilingual experiments and researchers need to write boilerplate code every time they want to use said corpora. Moreover, because there is no official MMC collection it becomes difficult to compare against existing approaches. As such we present our work on creating a unified and systematically organized repository of MMC spanning a large number of languages. We also provide training, development and test splits for corpora where official splits are unavailable. We hope that this will help speed up the pace of multilingual NLP research and ensure that NLP researchers obtain results that are more trustable since they can be compared easily. We indicate corpora sources, extraction procedures if any and relevant statistics. We also make our collection public for research purposes.
http://arxiv.org/abs/1710.01025
Learning image representations to capture fine-grained semantics has been a challenging and important task enabling many applications such as image search and clustering. In this paper, we present Graph-Regularized Image Semantic Embedding (Graph-RISE), a large-scale neural graph learning framework that allows us to train embeddings to discriminate an unprecedented O(40M) ultra-fine-grained semantic labels. Graph-RISE outperforms state-of-the-art image embedding algorithms on several evaluation tasks, including image classification and triplet ranking. We provide case studies to demonstrate that, qualitatively, image retrieval based on Graph-RISE effectively captures semantics and, compared to the state-of-the-art, differentiates nuances at levels that are closer to human-perception.
http://arxiv.org/abs/1902.10814
Sequence transduction models have been widely explored in many natural language processing tasks. However, the target sequence usually consists of discrete tokens which represent word indices in a given vocabulary. We barely see the case where target sequence is composed of continuous vectors, where each vector is an element of a time series taken successively in a temporal domain. In this work, we introduce a new data set, named Action Generation Data Set (AGDS) which is specifically designed to carry out the task of caption-to-action generation. This data set contains caption-action pairs. The caption is comprised of a sequence of words describing the interactive movement between two people, and the action is a captured sequence of poses representing the movement. This data set is introduced to study the ability of generating continuous sequences through sequence transduction models. We also propose a model to innovatively combine Multi-Head Attention (MHA) and Generative Adversarial Network (GAN) together. In our model, we have one generator to generate actions from captions and three discriminators where each of them is designed to carry out a unique functionality: caption-action consistency discriminator, pose discriminator and pose transition discriminator. This novel design allowed us to achieve plausible generation performance which is demonstrated in the experiments.
http://arxiv.org/abs/1902.11109
Employing one or more additional classifiers to break the self-learning loop in tracing-by-detection has gained considerable attention. Most of such trackers merely utilize the redundancy to address the accumulating label error in the tracking loop, and suffer from high computational complexity as well as tracking challenges that may interrupt all classifiers (e.g. temporal occlusions). We propose the active co-tracking framework, in which the main classifier of the tracker labels samples of the video sequence, and only consults auxiliary classifier when it is uncertain. Based on the source of the uncertainty and the differences of two classifiers (e.g. accuracy, speed, update frequency, etc.), different policies should be taken to exchange the information between two classifiers. Here, we introduce a reinforcement learning approach to find the appropriate policy by considering the state of the tracker in a specific sequence. The proposed method yields promising results in comparison to the best tracking-by-detection approaches.
http://arxiv.org/abs/1902.05211
Multi-vehicle trajectories generated from existing and real-time data provide valuable resources for autonomous vehicle development and testing. This paper introduces a multi-vehicle trajectory generator (MTG) that extracts the interpretable representations of driving encounters. The generator’s encoder has a bi-directional GRU module, and multiple branches of its decoder generate the sequences separately. A new disentanglement metric developed for model analyses and comparisons reveals the robustness of the deep generative models and the dependency among the latent codes. Experiments demonstrate that the proposed trajectory generator outperforms $\beta$-VAE and InfoGAN in terms of traffic rationality and disentanglement. Based on the results, we conclude that the generator will provide additional valuable data to the engineers and researchers who develop simulation scenarios for autonomous vehicle development and testing.
http://arxiv.org/abs/1809.05680
The performance of text classification has improved tremendously using intelligently engineered neural-based models, especially those injecting categorical metadata as additional information, e.g., using user/product information for sentiment classification. These information have been used to modify parts of the model (e.g., word embeddings, attention mechanisms) such that results can be customized according to the metadata. We observe that current representation methods for categorical metadata, which are devised for human consumption, are not as effective as claimed in popular classification methods, outperformed even by simple concatenation of categorical features in the final layer of the sentence encoder. We conjecture that categorical features are harder to represent for machine use, as available context only indirectly describes the category, and even such context is often scarce (for tail category). To this end, we propose to use basis vectors to effectively incorporate categorical metadata on various parts of a neural-based model. This additionally decreases the number of parameters dramatically, especially when the number of categorical features is large. Extensive experiments on various datasets with different properties are performed and show that through our method, we can represent categorical metadata more effectively to customize parts of the model, including unexplored ones, and increase the performance of the model greatly.
http://arxiv.org/abs/1902.05196
Extracting the instantaneous heart rate (iHR) from face videos has been well studied in recent years. It is well known that changes in skin color due to blood flow can be captured using conventional cameras. One of the main limitations of methods that rely on this principle is the need of an illumination source. Moreover, they have to be able to operate under different light conditions. One way to avoid these constraints is using infrared cameras, allowing the monitoring of iHR under low light conditions. In this work, we present a simple, principled signal extraction method that recovers the iHR from infrared face videos. We tested the procedure on 7 participants, for whom we recorded an electrocardiogram simultaneously with their infrared face video. We checked that the recovered signal matched the ground truth iHR, showing that infrared is a promising alternative to conventional video imaging for heart rate monitoring, especially in low light conditions. Code is available at https://github.com/natalialmg/IR_iHR
http://arxiv.org/abs/1902.05194
In real-world face recognition applications, there is a tremendous amount of data with two images for each person. One is an ID photo for face enrollment, and the other is a probe photo captured on spot. Most existing methods are designed for training data with limited breadth (a relatively small number of classes) and sufficient depth (many samples for each class). They would meet great challenges on ID versus Spot (IvS) data, including the under-represented intra-class variations and an excessive demand on computing devices. In this paper, we propose a deep learning based large-scale bisample learning (LBL) method for IvS face recognition. To tackle the bisample problem with only two samples for each class, a classification-verification-classification (CVC) training strategy is proposed to progressively enhance the IvS performance. Besides, a dominant prototype softmax (DP-softmax) is incorporated to make the deep learning scalable on large-scale classes. We conduct LBL on a IvS face dataset with more than two million identities. Experimental results show the proposed method achieves superior performance to previous ones, validating the effectiveness of LBL on IvS face recognition.
http://arxiv.org/abs/1806.03018
With the increasingly varied applications of deep learning, transfer learning has emerged as a critically important technique. However, the central question of how much feature reuse in transfer is the source of benefit remains unanswered. In this paper, we present an in-depth analysis of the effects of transfer, focusing on medical imaging, which is a particularly intriguing setting. Here, transfer learning is extremely popular, but data differences between pretraining and finetuing are considerable, reiterating the question of what is transferred. With experiments on two large scale medical imaging datasets, and CIFAR-10, we find transfer has almost negligible effects on performance, but significantly helps convergence speed. However, in all of these settings, convergence without transfer can be sped up dramatically by using only mean and variance statistics of the pretrained weights. Visualizing the lower layer filters shows that models trained from random initialization do not learn Gabor filters on medical images. We use CCA (canonical correlation analysis) to study the learned representations of the different models, finding that pretrained models are surprisingly similar to random initialization at higher layers. This similarity is evidenced both through model learning dynamics and a transfusion experiment, which explores the convergence speed using a subset of pretrained weights.
http://arxiv.org/abs/1902.07208
In robotic surgery, pattern cutting through a deformable material is a challenging research field. The cutting procedure requires a robot to concurrently manipulate a scissor and a gripper to cut through a predefined contour trajectory on the deformable sheet. The gripper ensures the cutting accuracy by nailing a point on the sheet and continuously tensioning the pinch point to different directions while the scissor is in action. The goal is to find a pinch point and a corresponding tensioning policy to minimize damage to the material and increase cutting accuracy measured by the symmetric difference between the predefined contour and the cut contour. Previous study considers finding one fixed pinch point during the course of cutting, which is inaccurate and unsafe when the contour trajectory is complex. In this paper, we examine the soft tissue cutting task by using multiple pinch points, which imitates human operations while cutting. This approach, however, does not require the use of a multi-gripper robot. We use a deep reinforcement learning algorithm to find an optimal tensioning policy of a pinch point. Simulation results show that the multi-point approach outperforms the state-of-the-art method in soft pattern cutting task with respect to both accuracy and reliability.
http://arxiv.org/abs/1902.05183
In the multi-robot systems literature, control policies are typically obtained through descent rules for a potential function which encodes a single team-level objective. However, for multi-objective tasks, it can be hard to design a single control policy that fulfills all the objectives. In this paper, we exploit the idea of decomposing the multi-objective task into a set of simple subtasks. We associate each subtask with a potentially lower-dimensional manifold, and design Riemannian Motion Policies (RMPs) on these manifolds. Centralized and decentralized algorithms are proposed to combine these policies into a final control policy on the configuration space that the robots can execute. We propose a collection of RMPs for simple multi-robot tasks that can be used for building controllers for more complicated tasks. In particular, we prove that many existing multi-robot controllers can be closely approximated by combining the proposed RMPs. Theoretical analysis shows that the multi-robot system under the generated control policy is stable. The proposed framework is validated through both simulated tasks and robotic implementations.
http://arxiv.org/abs/1902.05177
Automated real-time prediction of the ergonomic risks of manipulating objects is a key unsolved challenge in developing effective human-robot collaboration systems for logistics and manufacturing applications. We present a foundational paradigm to address this challenge by formulating the problem as one of action segmentation from RGB-D camera videos. Spatial features are first learned using a deep convolutional model from the video frames, which are then fed sequentially to temporal convolutional networks to semantically segment the frames into a hierarchy of actions, which are either ergonomically safe, require monitoring, or need immediate attention. For performance evaluation, in addition to an open-source kitchen dataset, we collected a new dataset comprising twenty individuals picking up and placing objects of varying weights to and from cabinet and table locations at various heights. Results show very high (87-94)% F1 overlap scores among the ground truth and predicted frame labels for videos lasting over two minutes and comprising a large number of actions.
http://arxiv.org/abs/1902.05176
Regularization of Deep Neural Networks (DNNs) for the sake of improving their generalization capability is important and challenging. The development in this line benefits theoretical foundation of DNNs and promotes their usability in different areas of artificial intelligence. In this paper, we investigate the role of Rademacher complexity in improving generalization of DNNs and propose a novel regularizer rooted in Local Rademacher Complexity (LRC). While Rademacher complexity is well known as a distribution-free complexity measure of function class that help boost generalization of statistical learning methods, extensive study shows that LRC, its counterpart focusing on a restricted function class, leads to sharper convergence rates and potential better generalization given finite training sample. Our LRC based regularizer is developed by estimating the complexity of the function class centered at the minimizer of the empirical loss of DNNs. Experiments on various types of network architecture demonstrate the effectiveness of LRC regularization in improving generalization. Moreover, our method features the state-of-the-art result on the CIFAR-$10$ dataset with network architecture found by neural architecture search.
https://arxiv.org/abs/1902.00873
This paper proposes a novel framework to reconstruct the dynamic magnetic resonance images (DMRI) with motion compensation (MC). Due to the inherent motion effects during DMRI acquisition, reconstruction of DMRI using motion estimation/compensation (ME/MC) has been studied under a compressed sensing (CS) scheme. In this paper, by embedding the intensity-based optical flow (OF) constraint into the traditional CS scheme, we are able to couple the DMRI reconstruction with motion field estimation. The formulated optimization problem is solved by a primal-dual algorithm with linesearch due to its efficiency when dealing with non-differentiable problems. With the estimated motion field, the DMRI reconstruction is refined through MC. By employing the multi-scale coarse-to-fine strategy, we are able to update the variables(temporal image sequences and motion vectors) and to refine the image reconstruction alternately. Moreover, the proposed framework is capable of handling a wide class of prior information (regularizations) for DMRI reconstruction, such as sparsity, low rank and total variation. Experiments on various DMRI data, ranging from in vivo lung to cardiac dataset, validate the reconstruction quality improvement using the proposed scheme in comparison to several state-of-the-art algorithms.
http://arxiv.org/abs/1707.07089
Sequential data modeling and analysis have become indispensable tools for analyzing sequential data, such as time-series data, because larger amounts of sensed event data have become available. These methods capture the sequential structure of data of interest, such as input-output relations and correlation among datasets. However, because most studies in this area are specialized or limited to their respective applications, rigorous requirement analysis of such models has not been undertaken from a general perspective. Therefore, we particularly examine the structure of sequential data, and extract the necessity of state duration' and state interval’ of events for efficient and rich representation of sequential data. Specifically addressing the hidden semi-Markov model (HSMM) that represents such state duration inside a model, we attempt to add representational capability of a state interval of events onto HSMM. To this end, we propose two extended models: an interval state hidden semi-Markov model (IS-HSMM) to express the length of a state interval with a special state node designated as “interval state node”; and an interval length probability hidden semi-Markov model (ILP-HSMM) which represents the length of the state interval with a new probabilistic parameter “interval length probability.” Exhaustive simulations have revealed superior performance of the proposed models in comparison with HSMM. These proposed models are the first reported extensions of HMM to support state interval representation as well as state duration representation.
http://arxiv.org/abs/1608.06954
Obtaining reliable data describing local poverty metrics at a granularity that is informative to policy-makers requires expensive and logistically difficult surveys, particularly in the developing world. Not surprisingly, the poverty stricken regions are also the ones which have a high probability of being a war zone, have poor infrastructure and sometimes have governments that do not cooperate with internationally funded development efforts. We train a CNN on free and publicly available daytime satellite images of the African continent from Landsat 7 to build a model for predicting local economic livelihoods. Only 5% of the satellite images can be associated with labels (which are obtained from DHS Surveys) and thus a semi-supervised approach using a GAN (similar to the approach of Salimans, et al. (2016)), albeit with a more stable-to-train flavor of GANs called the Wasserstein GAN regularized with gradient penalty(Gulrajani, et al. (2017)) is used. The method of multitask learning is employed to regularize the network and also create an end-to-end model for the prediction of multiple poverty metrics.
http://arxiv.org/abs/1902.11110
In this paper, we highlight three issues that limit performance of machine learning on biomedical images, and tackle them through 3 case studies: 1) Interactive Machine Learning (IML): we show how IML can drastically improve exploration time and quality of direct volume rendering. 2) transfer learning: we show how transfer learning along with intelligent pre-processing can result in better Alzheimer’s diagnosis using a much smaller training set 3) data imbalance: we show how our novel focal Tversky loss function can provide better segmentation results taking into account the imbalanced nature of segmentation datasets. The case studies are accompanied by in-depth analytical discussion of results with possible future directions.
http://arxiv.org/abs/1902.05908
In neural architecture search (NAS), the space of neural network architectures is automatically explored to maximize predictive accuracy for a given task. Despite the success of recent approaches, most existing methods cannot be directly applied to large scale problems because of their prohibitive computational complexity or high memory usage. In this work, we propose a Probabilistic approach to neural ARchitecture SEarCh (PARSEC) that drastically reduces memory requirements while maintaining state-of-the-art computational complexity, making it possible to directly search over more complex architectures and larger datasets. Our approach only requires as much memory as is needed to train a single architecture from our search space. This is due to a memory-efficient sampling procedure wherein we learn a probability distribution over high-performing neural network architectures. Importantly, this framework enables us to transfer the distribution of architectures learnt on smaller problems to larger ones, further reducing the computational cost. We showcase the advantages of our approach in applications to CIFAR-10 and ImageNet, where our approach outperforms methods with double its computational cost and matches the performance of methods with costs that are three orders of magnitude larger.
https://arxiv.org/abs/1902.05116
We build new test sets for the CIFAR-10 and ImageNet datasets. Both benchmarks have been the focus of intense research for almost a decade, raising the danger of overfitting to excessively re-used test sets. By closely following the original dataset creation processes, we test to what extent current classification models generalize to new data. We evaluate a broad range of models and find accuracy drops of 3% - 15% on CIFAR-10 and 11% - 14% on ImageNet. However, accuracy gains on the original test sets translate to larger gains on the new test sets. Our results suggest that the accuracy drops are not caused by adaptivity, but by the models’ inability to generalize to slightly “harder” images than those found in the original test sets.
http://arxiv.org/abs/1902.10811
The ability to obtain accurate food security metrics in developing areas where relevant data can be sparse is critically important for policy makers tasked with implementing food aid programs. As a result, a great deal of work has been dedicated to predicting important food security metrics such as annual crop yields using a variety of methods including simulation, remote sensing, weather models, and human expert input. As a complement to existing techniques in crop yield prediction, this work develops neural network models for predicting the sentiment of Twitter feeds from farming communities. Specifically, we investigate the potential of both direct learning on a small dataset of agriculturally-relevant tweets and transfer learning from larger, well-labeled sentiment datasets from other domains (e.g.~politics) to accurately predict agricultural sentiment, which we hope would ultimately serve as a useful crop yield predictor. We find that direct learning from small, relevant datasets outperforms transfer learning from large, fully-labeled datasets, that convolutional neural networks broadly outperform recurrent neural networks on Twitter sentiment classification, and that these models perform substantially less well on ternary sentiment problems characteristic of practical settings than on binary problems often found in the literature.
http://arxiv.org/abs/1902.07087
This paper addresses a synchronization problem that arises when a team of aerial robots (ARs) need to communicate while performing assigned tasks in a cooperative scenario. Each robot has a limited communication range and flies within a previously assigned closed trajectory. When two robots are close enough, a communication link may be established, allowing the robots to exchange information. The goal is to schedule the flights such that the entire system can be synchronized for maximum information exchange, that is, every pair of neighbors always visit the feasible communication link at the same time. We propose an algorithm for scheduling a team of robots in this scenario and propose a robust framework in which the synchronization of a large team of robots is assured. The approach allows us to design a fault-tolerant system that can be used for multiple tasks such as surveillance, area exploration, searching for targets in a hazardous environment, and assembly and structure construction, to name a few.
http://arxiv.org/abs/1902.05107
We present a single-shot, bottom-up approach for whole image parsing. Whole image parsing, also known as Panoptic Segmentation, generalizes the tasks of semantic segmentation for ‘stuff’ classes and instance segmentation for ‘thing’ classes, assigning both semantic and instance labels to every pixel in an image. Recent approaches to whole image parsing typically employ separate standalone modules for the constituent semantic and instance segmentation tasks and require multiple passes of inference. Instead, the proposed DeeperLab image parser performs whole image parsing with a significantly simpler, fully convolutional approach that jointly addresses the semantic and instance segmentation tasks in a single-shot manner, resulting in a streamlined system that better lends itself to fast processing. For quantitative evaluation, we use both the instance-based Panoptic Quality (PQ) metric and the proposed region-based Parsing Covering (PC) metric, which better captures the image parsing quality on ‘stuff’ classes and larger object instances. We report experimental results on the challenging Mapillary Vistas dataset, in which our single model achieves 31.95% (val) / 31.6% PQ (test) and 55.26% PC (val) with 3 frames per second (fps) on GPU or near real-time speed (22.6 fps on GPU) with reduced accuracy.
http://arxiv.org/abs/1902.05093
We investigate the problem of parsing conversational data of morphologically-rich languages such as Hindi where argument scrambling occurs frequently. We evaluate a state-of-the-art non-linear transition-based parsing system on a new dataset containing 506 dependency trees for sentences from Bollywood (Hindi) movie scripts and Twitter posts of Hindi monolingual speakers. We show that a dependency parser trained on a newswire treebank is strongly biased towards the canonical structures and degrades when applied to conversational data. Inspired by Transformational Generative Grammar, we mitigate the sampling bias by generating all theoretically possible alternative word orders of a clause from the existing (kernel) structures in the treebank. Training our parser on canonical and transformed structures improves performance on conversational data by around 9% LAS over the baseline newswire parser.
http://arxiv.org/abs/1902.05085
Double-clamped bistable buckled beams, as the most elegant bistable mechanisms, demonstrate great versatility in various fields, such as robotics, energy harvesting, and MEMS. However, their design is always hindered by time-consuming and expensive computations. In this work, we present a method to easily and rapidly design bistable buckled beams subjected to a transverse point force. Based on the Euler-Bernoulli beam theory, we establish a theoretical model of bistable buckled beams to characterize their snap-through properties. This model is verified against the results from an FEA model, with discrepancy less than 7 %. By analyzing and simplifying our theoretical model, we derive explicit analytical expressions for critical behavioral values on the force-displacement curve of the beam. These behavioral values include critical force, critical displacement, and travel, which are generally sufficient for characterizing the snap-through properties of a bistable buckled beam. Based on these analytical formulas, we investigate the influence of a bistable buckled beam’s key design parameters, including its actuation position and precompression, on its critical behavioral values, with our results validated by FEA simulations. This way, our method enables fast and computationally inexpensive design of bistable buckled beams and can guide the design of complex systems that incorporate bistable mechanisms.
http://arxiv.org/abs/1902.05038
Pedestrian trajectory prediction is essential for collision avoidance in autonomous driving and robot navigation. However, predicting a pedestrian’s trajectory in crowded environments is non-trivial as it is influenced by other pedestrians’ motion and static structures that are present in the scene. Such human-human and human-space interactions lead to non-linearities in the trajectories. In this paper, we present a new spatio-temporal graph based Long Short-Term Memory (LSTM) network for predicting pedestrian trajectory in crowded environments, which takes into account the interaction with static (physical objects) and dynamic (other pedestrians) elements in the scene. Our results are based on two widely-used datasets to demonstrate that the proposed method outperforms the state-of-the-art approaches in human trajectory prediction. In particular, our method leads to a reduction in Average Displacement Error (ADE) and Final Displacement Error (FDE) of up to 55% and 61% respectively over state-of-the-art approaches.
http://arxiv.org/abs/1902.05437
In motion planning problems for autonomous robots, such as self-driving cars, the robot must ensure that its planned path is not in close proximity to obstacles in the environment. However, the problem of evaluating the proximity is generally non-convex and serves as a significant computational bottleneck for motion planning algorithms. In this paper, we present methods for a general class of absolutely continuous parametric curves to compute: (i) the minimum separating distance, (ii) tolerance verification, and (iii) collision detection. Our methods efficiently compute bounds on obstacle proximity by bounding the curve in a convex region. This bound is based on an upper bound on the curve arc length that can be expressed in closed form for a useful class of parametric curves including curves with trigonometric or polynomial bases. We demonstrate the computational efficiency and accuracy of our approach through numerical simulations of several proximity problems.
http://arxiv.org/abs/1902.05027
In order to more accurately situate and fit the neutrosophic logic into the framework of nonstandard analysis, we present the neutrosophic inequalities, neutrosophic equality, neutrosophic infimum and supremum, neutrosophic standard intervals, including the cases when the neutrosophic logic standard and nonstandard components T, I, F get values outside of the classical real unit interval [0, 1], and a brief evolution of neutrosophic operators. The paper intends to answer Imamura criticism that we found benefic in better understanding the nonstandard neutrosophic logic, although the nonstandard neutrosophic logic was never used in practical applications.
http://arxiv.org/abs/1812.02534
3D medical image registration is of great clinical importance. However, supervised learning methods require a large amount of accurately annotated corresponding control points (or morphing). The ground truth for 3D medical images is very difficult to obtain. Unsupervised learning methods ease the burden of manual annotation by exploiting unlabeled data without supervision. In this paper, we propose a new unsupervised learning method using convolutional neural networks under an end-to-end framework, Volume Tweening Network (VTN), to register 3D medical images. Three technical components ameliorate our unsupervised learning system for 3D end-to-end medical image registration: (1) We cascade the registration subnetworks; (2) We integrate affine registration into our network; and (3) We incorporate an additional invertibility loss into the training process. Experimental results demonstrate that our algorithm is 880x faster (or 3.3x faster without GPU acceleration) than traditional optimization-based methods and achieves state-of-the-art performance in medical image registration.
http://arxiv.org/abs/1902.05020
To relieve the pain of manually selecting machine learning algorithms and tuning hyperparameters, automated machine learning (AutoML) methods have been developed to automatically search for good models. Due to the huge model search space, it is impossible to try all models. Users tend to distrust automatic results and increase the search budget as much as they can, thereby undermining the efficiency of AutoML. To address these issues, we design and implement ATMSeer, an interactive visualization tool that supports users in refining the search space of AutoML and analyzing the results. To guide the design of ATMSeer, we derive a workflow of using AutoML based on interviews with machine learning experts. A multi-granularity visualization is proposed to enable users to monitor the AutoML process, analyze the searched models, and refine the search space in real time. We demonstrate the utility and usability of ATMSeer through two case studies, expert interviews, and a user study with 13 end users.
http://arxiv.org/abs/1902.05009
In this paper we propose to perform model ensembling in a multiclass or a multilabel learning setting using Wasserstein (W.) barycenters. Optimal transport metrics, such as the Wasserstein distance, allow incorporating semantic side information such as word embeddings. Using W. barycenters to find the consensus between models allows us to balance confidence and semantics in finding the agreement between the models. We show applications of Wasserstein ensembling in attribute-based classification, multilabel learning and image captioning generation. These results show that the W. ensembling is a viable alternative to the basic geometric or arithmetic mean ensembling.
https://arxiv.org/abs/1902.04999
We present an imaging framework which converts three images from a gated camera into high-resolution depth maps with depth resolution comparable to pulsed lidar measurements. Existing scanning lidar systems achieve low spatial resolution at large ranges due to mechanically-limited angular sampling rates, restricting scene understanding tasks to close-range clusters with dense sampling. In addition, today’s lidar detector technologies, short-pulsed laser sources and scanning mechanics result in high cost, power consumption and large form-factors. We depart from point scanning and propose a learned architecture that recovers high-fidelity dense depth from three temporally gated images, acquired with a flash source and a high-resolution CMOS sensor. The proposed architecture exploits semantic context across gated slices, and is trained on a synthetic discriminator loss without the need of dense depth labels. The method is real-time and essentially turns a gated camera into a low-cost dense flash lidar which we validate on a wide range of outdoor driving captures and in simulations.
http://arxiv.org/abs/1902.04997