April 1, 2020

3097 words 15 mins read

Paper Group ANR 439

Variational Inference with Parameter Learning Applied to Vehicle Trajectory Estimation. Sample-Specific Output Constraints for Neural Networks. Multi-Granularity Reference-Aided Attentive Feature Aggregation for Video-based Person Re-identification. Semi-Implicit Back Propagation. Learn and Transfer Knowledge of Preferred Assistance Strategies in S …

Variational Inference with Parameter Learning Applied to Vehicle Trajectory Estimation


Title	Variational Inference with Parameter Learning Applied to Vehicle Trajectory Estimation
Authors	Jeremy N. Wong, David J. Yoon, Angela P. Schoellig, Timothy D. Barfoot
Abstract	We present parameter learning in a Gaussian variational inference setting using only noisy measurements (i.e., no groundtruth). This is demonstrated in the context of vehicle trajectory estimation, although the method we propose is general. The paper extends the Exactly Sparse Gaussian Variational Inference (ESGVI) framework, which has previously been used for large-scale nonlinear batch state estimation. Our contribution is to additionally learn parameters of our system models (which may be difficult to choose in practice) within the ESGVI framework. In this paper, we learn the covariances for the motion and sensor models used within vehicle trajectory estimation. Specifically, we learn the parameters of a white-noise-on-acceleration motion model and the parameters of an Inverse-Wishart prior over measurement covariances for our sensor model. We demonstrate our technique using a 36 km dataset consisting of a car using lidar to localize against a high-definition map; we learn the parameters on a training section of the data and then show that we achieve high-quality state estimates on a test section, even in the presence of outliers.
Tasks
Published	2020-03-21
URL	https://arxiv.org/abs/2003.09736v1
PDF	https://arxiv.org/pdf/2003.09736v1.pdf
PWC	https://paperswithcode.com/paper/variational-inference-with-parameter-learning
Repo
Framework

Sample-Specific Output Constraints for Neural Networks


Title	Sample-Specific Output Constraints for Neural Networks
Authors	Mathis Brosowsky, Olaf Dünkel, Daniel Slieter, Marius Zöllner
Abstract	Neural networks reach state-of-the-art performance in a variety of learning tasks. However, a lack of understanding the decision making process yields to an appearance as black box. We address this and propose ConstraintNet, a neural network with the capability to constrain the output space in each forward pass via an additional input. The prediction of ConstraintNet is proven within the specified domain. This enables ConstraintNet to exclude unintended or even hazardous outputs explicitly whereas the final prediction is still learned from data. We focus on constraints in form of convex polytopes and show the generalization to further classes of constraints. ConstraintNet can be constructed easily by modifying existing neural network architectures. We highlight that ConstraintNet is end-to-end trainable with no overhead in the forward and backward pass. For illustration purposes, we model ConstraintNet by modifying a CNN and construct constraints for facial landmark prediction tasks. Furthermore, we demonstrate the application to a follow object controller for vehicles as a safety-critical application. We submitted an approach and system for the generation of safety-critical outputs of an entity based on ConstraintNet at the German Patent and Trademark Office with the official registration mark DE10 2019 119 739.
Tasks	Decision Making
Published	2020-03-23
URL	https://arxiv.org/abs/2003.10258v1
PDF	https://arxiv.org/pdf/2003.10258v1.pdf
PWC	https://paperswithcode.com/paper/sample-specific-output-constraints-for-neural
Repo
Framework

Multi-Granularity Reference-Aided Attentive Feature Aggregation for Video-based Person Re-identification


Title	Multi-Granularity Reference-Aided Attentive Feature Aggregation for Video-based Person Re-identification
Authors	Zhizheng Zhang, Cuiling Lan, Wenjun Zeng, Zhibo Chen
Abstract	Video-based person re-identification (reID) aims at matching the same person across video clips. It is a challenging task due to the existence of redundancy among frames, newly revealed appearance, occlusion, and motion blurs. In this paper, we propose an attentive feature aggregation module, namely Multi-Granularity Reference-aided Attentive Feature Aggregation (MG-RAFA), to delicately aggregate spatio-temporal features into a discriminative video-level feature representation. In order to determine the contribution/importance of a spatial-temporal feature node, we propose to learn the attention from a global view with convolutional operations. Specifically, we stack its relations, i.e., pairwise correlations with respect to a representative set of reference feature nodes (S-RFNs) that represents global video information, together with the feature itself to infer the attention. Moreover, to exploit the semantics of different levels, we propose to learn multi-granularity attentions based on the relations captured at different granularities. Extensive ablation studies demonstrate the effectiveness of our attentive feature aggregation module MG-RAFA. Our framework achieves the state-of-the-art performance on three benchmark datasets.
Tasks	Person Re-Identification, Video-Based Person Re-Identification
Published	2020-03-27
URL	https://arxiv.org/abs/2003.12224v1
PDF	https://arxiv.org/pdf/2003.12224v1.pdf
PWC	https://paperswithcode.com/paper/multi-granularity-reference-aided-attentive
Repo
Framework

Semi-Implicit Back Propagation


Title	Semi-Implicit Back Propagation
Authors	Ren Liu, Xiaoqun Zhang
Abstract	Neural network has attracted great attention for a long time and many researchers are devoted to improve the effectiveness of neural network training algorithms. Though stochastic gradient descent (SGD) and other explicit gradient-based methods are widely adopted, there are still many challenges such as gradient vanishing and small step sizes, which leads to slow convergence and instability of SGD algorithms. Motivated by error back propagation (BP) and proximal methods, we propose a semi-implicit back propagation method for neural network training. Similar to BP, the difference on the neurons are propagated in a backward fashion and the parameters are updated with proximal mapping. The implicit update for both hidden neurons and parameters allows to choose large step size in the training algorithm. Finally, we also show that any fixed point of convergent sequences produced by this algorithm is a stationary point of the objective loss function. The experiments on both MNIST and CIFAR-10 demonstrate that the proposed semi-implicit BP algorithm leads to better performance in terms of both loss decreasing and training/validation accuracy, compared to SGD and a similar algorithm ProxBP.
Tasks
Published	2020-02-10
URL	https://arxiv.org/abs/2002.03516v1
PDF	https://arxiv.org/pdf/2002.03516v1.pdf
PWC	https://paperswithcode.com/paper/semi-implicit-back-propagation-1
Repo
Framework

Learn and Transfer Knowledge of Preferred Assistance Strategies in Semi-autonomous Telemanipulation


Title	Learn and Transfer Knowledge of Preferred Assistance Strategies in Semi-autonomous Telemanipulation
Authors	Lingfeng Tao, Michael Bowman, Xu Zhou, Xiaoli Zhang
Abstract	Increasing the autonomy level of a robot hand to accomplish remote object manipulation tasks faster and easier is a new and promising topic in teleoperation. Such semi-autonomous telemanipulation, however, is very challenging due to the physical discrepancy between the human hand and the robot hand, along with the fine motion constraints required for the manipulation task. To overcome these challenges, the robot needs to learn how to assist the human operator in a preferred/intuitive way, which must provide effective assistance that the operator needs yet still accommodate human inputs, so the operator feels in control of the system (i.e., not counter-intuitive to the operator). Toward this goal, we develop novel data-driven approaches to stably learn what assistance is preferred from high data variance caused by the ambiguous nature of human operators. To avoid an extensive robot-specific training process, methods to transfer this assistance knowledge between different robot hands are discussed. Experiments were conducted to telemanipulate a cup for three principal tasks: usage, move, and handover by remotely controlling a 3-finger gripper and 2-finger gripper. Results demonstrated that the proposed model effectively learned the knowledge of preferred assistance, and knowledge transfer between robots allows this semi-autonomous telemanipulation strategy to be scaled up with less training efforts.
Tasks	Transfer Learning
Published	2020-03-07
URL	https://arxiv.org/abs/2003.03516v1
PDF	https://arxiv.org/pdf/2003.03516v1.pdf
PWC	https://paperswithcode.com/paper/learn-and-transfer-knowledge-of-preferred
Repo
Framework

Learning bounded subsets of $L_p$


Title	Learning bounded subsets of $L_p$
Authors	Shahar Mendelson
Abstract	We study learning problems in which the underlying class is a bounded subset of $L_p$ and the target $Y$ belongs to $L_p$. Previously, minimax sample complexity estimates were known under such boundedness assumptions only when $p=\infty$. We present a sharp sample complexity estimate that holds for any $p > 4$. It is based on a learning procedure that is suited for heavy-tailed problems.
Tasks
Published	2020-02-04
URL	https://arxiv.org/abs/2002.01182v1
PDF	https://arxiv.org/pdf/2002.01182v1.pdf
PWC	https://paperswithcode.com/paper/learning-bounded-subsets-of-l_p
Repo
Framework

Online Similarity Learning with Feedback for Invoice Line Item Matching


Title	Online Similarity Learning with Feedback for Invoice Line Item Matching
Authors	Chandresh Kumar Maurya, Neelamadhav Gantayat, Sampath Dechu, Tomas Horvath
Abstract	The procure to pay process (P2P) in large enterprises is a back-end business process which deals with the procurement of products and services for enterprise operations. Procurement is done by issuing purchase orders to impaneled vendors and invoices submitted by vendors are paid after they go through a rigorous validation process. Agents orchestrating P2P process often encounter the problem of matching a product or service descriptions in the invoice to those in purchase order and verify if the ordered items are what have been supplied or serviced. For example, the description in the invoice and purchase order could be TRES 739mL CD KER Smooth and TRES 0.739L CD KER Smth which look different at word level but refer to the same item. In a typical P2P process, agents are asked to manually select the products which are similar before invoices are posted for payment. This step in the business process is manual, repetitive, cumbersome, and costly. Since descriptions are not well-formed sentences, we cannot apply existing semantic and syntactic text similarity approaches directly. In this paper, we present two approaches to solve the above problem using various types of available agent’s recorded feedback data. If the agent’s feedback is in the form of a relative ranking between descriptions, we use similarity ranking algorithm. If the agent’s feedback is absolute such as match or no-match, we use classification similarity algorithm. We also present the threats to the validity of our approach and present a possible remedy making use of product taxonomy and catalog. We showcase the comparative effectiveness and efficiency of the proposed approaches over many benchmarks and real-world data sets.
Tasks
Published	2020-01-02
URL	https://arxiv.org/abs/2001.00288v2
PDF	https://arxiv.org/pdf/2001.00288v2.pdf
PWC	https://paperswithcode.com/paper/online-similarity-learning-with-feedback-for
Repo
Framework

Computing Valid p-value for Optimal Changepoint by Selective Inference using Dynamic Programming


Title	Computing Valid p-value for Optimal Changepoint by Selective Inference using Dynamic Programming
Authors	Vo Nguyen Le Duy, Hiroki Toda, Ryota Sugiyama, Ichiro Takeuchi
Abstract	There is a vast body of literature related to methods for detecting changepoints (CP). However, less attention has been paid to assessing the statistical reliability of the detected CPs. In this paper, we introduce a novel method to perform statistical inference on the significance of the CPs, estimated by a Dynamic Programming (DP)-based optimal CP detection algorithm. Based on the selective inference (SI) framework, we propose an exact (non-asymptotic) approach to compute valid p-values for testing the significance of the CPs. Although it is well-known that SI has low statistical power because of over-conditioning, we address this disadvantage by introducing parametric programming techniques. Then, we propose an efficient method to conduct SI with the minimum amount of conditioning, leading to high statistical power. We conduct experiments on both synthetic and real-world datasets, through which we offer evidence that our proposed method is more powerful than existing methods, has decent performance in terms of computational efficiency, and provides good results in many practical applications.
Tasks
Published	2020-02-21
URL	https://arxiv.org/abs/2002.09132v1
PDF	https://arxiv.org/pdf/2002.09132v1.pdf
PWC	https://paperswithcode.com/paper/computing-valid-p-value-for-optimal
Repo
Framework

Constructing Deep Neural Networks with a Priori Knowledge of Wireless Tasks


Title	Constructing Deep Neural Networks with a Priori Knowledge of Wireless Tasks
Authors	Jia Guo, Chenyang Yang
Abstract	Deep neural networks (DNNs) have been employed for designing wireless systems in many aspects, say transceiver design, resource optimization, and information prediction. Existing works either use the fully-connected DNN or the DNNs with particular architectures developed in other domains. While generating labels for supervised learning and gathering training samples are time-consuming or cost-prohibitive, how to develop DNNs with wireless priors for reducing training complexity remains open. In this paper, we show that two kinds of permutation invariant properties widely existed in wireless tasks can be harnessed to reduce the number of model parameters and hence the sample and computational complexity for training. We find special architecture of DNNs whose input-output relationships satisfy the properties, called permutation invariant DNN (PINN), and augment the data with the properties. By learning the impact of the scale of a wireless system, the size of the constructed PINNs can flexibly adapt to the input data dimension. We take predictive resource allocation and interference coordination as examples to show how the PINNs can be employed for learning the optimal policy with unsupervised and supervised learning. Simulations results demonstrate a dramatic gain of the proposed PINNs in terms of reducing training complexity.
Tasks
Published	2020-01-29
URL	https://arxiv.org/abs/2001.11355v1
PDF	https://arxiv.org/pdf/2001.11355v1.pdf
PWC	https://paperswithcode.com/paper/constructing-deep-neural-networks-with-a
Repo
Framework

Machine learning and AI-based approaches for bioactive ligand discovery and GPCR-ligand recognition


Title	Machine learning and AI-based approaches for bioactive ligand discovery and GPCR-ligand recognition
Authors	Sebastian Raschka, Benjamin Kaufman
Abstract	In the last decade, machine learning and artificial intelligence applications have received a significant boost in performance and attention in both academic research and industry. The success behind most of the recent state-of-the-art methods can be attributed to the latest developments in deep learning. When applied to various scientific domains that are concerned with the processing of non-tabular data, for example, image or text, deep learning has been shown to outperform not only conventional machine learning but also highly specialized tools developed by domain experts. This review aims to summarize AI-based research for GPCR bioactive ligand discovery with a particular focus on the most recent achievements and research trends. To make this article accessible to a broad audience of computational scientists, we provide instructive explanations of the underlying methodology, including overviews of the most commonly used deep learning architectures and feature representations of molecular data. We highlight the latest AI-based research that has led to the successful discovery of GPCR bioactive ligands. However, an equal focus of this review is on the discussion of machine learning-based technology that has been applied to ligand discovery in general and has the potential to pave the way for successful GPCR bioactive ligand discovery in the future. This review concludes with a brief outlook highlighting the recent research trends in deep learning, such as active learning and semi-supervised learning, which have great potential for advancing bioactive ligand discovery.
Tasks	Active Learning
Published	2020-01-17
URL	https://arxiv.org/abs/2001.06545v2
PDF	https://arxiv.org/pdf/2001.06545v2.pdf
PWC	https://paperswithcode.com/paper/machine-learning-and-ai-based-approaches-for
Repo
Framework

Rapidly Personalizing Mobile Health Treatment Policies with Limited Data


Title	Rapidly Personalizing Mobile Health Treatment Policies with Limited Data
Authors	Sabina Tomkins, Peng Liao, Predrag Klasnja, Serena Yeung, Susan Murphy
Abstract	In mobile health (mHealth), reinforcement learning algorithms that adapt to one’s context without learning personalized policies might fail to distinguish between the needs of individuals. Yet the high amount of noise due to the in situ delivery of mHealth interventions can cripple the ability of an algorithm to learn when given access to only a single user’s data, making personalization challenging. We present IntelligentPooling, which learns personalized policies via an adaptive, principled use of other users’ data. We show that IntelligentPooling achieves an average of 26% lower regret than state-of-the-art across all generative models. Additionally, we inspect the behavior of this approach in a live clinical trial, demonstrating its ability to learn from even a small group of users.
Tasks
Published	2020-02-23
URL	https://arxiv.org/abs/2002.09971v1
PDF	https://arxiv.org/pdf/2002.09971v1.pdf
PWC	https://paperswithcode.com/paper/rapidly-personalizing-mobile-health-treatment
Repo
Framework

A Deep Reinforcement Learning Approach to Concurrent Bilateral Negotiation


Title	A Deep Reinforcement Learning Approach to Concurrent Bilateral Negotiation
Authors	Pallavi Bagga, Nicola Paoletti, Bedour Alrayes, Kostas Stathis
Abstract	We present a novel negotiation model that allows an agent to learn how to negotiate during concurrent bilateral negotiations in unknown and dynamic e-markets. The agent uses an actor-critic architecture with model-free reinforcement learning to learn a strategy expressed as a deep neural network. We pre-train the strategy by supervision from synthetic market data, thereby decreasing the exploration time required for learning during negotiation. As a result, we can build automated agents for concurrent negotiations that can adapt to different e-market settings without the need to be pre-programmed. Our experimental evaluation shows that our deep reinforcement learning-based agents outperform two existing well-known negotiation strategies in one-to-many concurrent bilateral negotiations for a range of e-market settings.
Tasks
Published	2020-01-31
URL	https://arxiv.org/abs/2001.11785v2
PDF	https://arxiv.org/pdf/2001.11785v2.pdf
PWC	https://paperswithcode.com/paper/a-deep-reinforcement-learning-approach-to-1
Repo
Framework

Patient Specific Biomechanics Are Clinically Significant In Accurate Computer Aided Surgical Image Guidance


Title	Patient Specific Biomechanics Are Clinically Significant In Accurate Computer Aided Surgical Image Guidance
Authors	Michael Barrow, Alice Chao, Qizhi He, Sonia Ramamoorthy, Claude Sirlin, Ryan Kastner
Abstract	Augmented Reality is used in Image Guided surgery (AR IG) to fuse surgical landmarks from preoperative images into a video overlay. Physical simulation is essential to maintaining accurate position of the landmarks as surgery progresses and ensuring patient safety by avoiding accidental damage to vessels etc. In liver procedures, AR IG simulation accuracy is hampered by an inability to model stiffness variations unique to the patients disease. We introduce a novel method to account for patient specific stiffness variation based on Magnetic Resonance Elastography (MRE) data. To the best of our knowledge we are the first to demonstrate the use of in-vivo biomechanical data for AR IG landmark placement. In this early work, a comparative evaluation of our MRE data driven simulation and the traditional method shows clinically significant differences in accuracy during landmark placement and motivates further animal model trials.
Tasks
Published	2020-01-29
URL	https://arxiv.org/abs/2001.10717v1
PDF	https://arxiv.org/pdf/2001.10717v1.pdf
PWC	https://paperswithcode.com/paper/patient-specific-biomechanics-are-clinically
Repo
Framework

STC-Flow: Spatio-temporal Context-aware Optical Flow Estimation


Title	STC-Flow: Spatio-temporal Context-aware Optical Flow Estimation
Authors	Xiaolin Song, Yuyang Zhao, Jingyu Yang, Cuiling Lan, Wenjun Zeng, Jiahao Li
Abstract	In this paper, we propose a spatio-temporal contextual network, STC-Flow, for optical flow estimation. Unlike previous optical flow estimation approaches with local pyramid feature extraction and multi-level correlation, we propose a contextual relation exploration architecture by capturing rich long-range dependencies in spatial and temporal dimensions. Specifically, STC-Flow contains three key context modules - pyramidal spatial context module, temporal context correlation module and recurrent residual contextual upsampling module, to build the relationship in each stage of feature extraction, correlation, and flow reconstruction, respectively. Experimental results indicate that the proposed scheme achieves the state-of-the-art performance of two-frame based methods on the Sintel dataset and the KITTI 2012/2015 datasets.
Tasks	Optical Flow Estimation
Published	2020-03-01
URL	https://arxiv.org/abs/2003.00434v1
PDF	https://arxiv.org/pdf/2003.00434v1.pdf
PWC	https://paperswithcode.com/paper/stc-flow-spatio-temporal-context-aware
Repo
Framework

ScopeFlow: Dynamic Scene Scoping for Optical Flow


Title	ScopeFlow: Dynamic Scene Scoping for Optical Flow
Authors	Aviram Bar-Haim, Lior Wolf
Abstract	We propose to modify the common training protocols of optical flow, leading to sizable accuracy improvements without adding to the computational complexity of the training process. The improvement is based on observing the bias in sampling challenging data that exists in the current training protocol, and improving the sampling process. In addition, we find that both regularization and augmentation should decrease during the training protocol. Using a low parameters off-the-shelf model, the method is ranked first on the MPI Sintel benchmark among all other methods, improving the best two frames method accuracy by more than 10%. The method also surpasses all similar architecture variants by more than 12% and 19.7% on the KITTI benchmarks, achieving the lowest Average End-Point Error on KITTI2012 among two-frame methods, without using extra datasets.
Tasks	Optical Flow Estimation
Published	2020-02-25
URL	https://arxiv.org/abs/2002.10770v1
PDF	https://arxiv.org/pdf/2002.10770v1.pdf
PWC	https://paperswithcode.com/paper/scopeflow-dynamic-scene-scoping-for-optical
Repo
Framework