January 25, 2020

3369 words 16 mins read

Paper Group ANR 1757

A posteriori Trading-inspired Model-free Time Series Segmentation. Structured Modeling of Joint Deep Feature and Prediction Refinement for Salient Object Detection. Solar-Sail Trajectory Design for Multiple Near Earth Asteroid Exploration Based on Deep Neural Networks. An Interval-Valued Utility Theory for Decision Making with Dempster-Shafer Belie …

A posteriori Trading-inspired Model-free Time Series Segmentation


Title	A posteriori Trading-inspired Model-free Time Series Segmentation
Authors	Mogens Graf Plessen
Abstract	Within the context of multivariate time series segmentation this paper proposes a method inspired by a posteriori optimal trading. After a normalization step time series are treated channel-wise as surrogate stock prices that can be traded optimally a posteriori in a virtual portfolio holding either stock or cash. Linear transaction costs are interpreted as hyperparameters for noise filtering. Resulting trading signals as well as resulting trading signals obtained on the reversed time series are used for unsupervised labeling, before a consensus over channels is reached that determines segmentation time instants. The method is model-free such that no model prescriptions for segments are made. Benefits of proposed approach include simplicity, computational efficiency and adaptability to a wide range of different shapes of time series. Performance is demonstrated on synthetic and real-world data, including a large-scale dataset comprising a multivariate time series of dimension 1000 and length 2709. Proposed method is compared to a popular model-based bottom-up approach fitting piecewise affine models and to a recent model-based top-down approach fitting Gaussian models, and found to be consistently faster while producing more intuitive results.
Tasks	Time Series
Published	2019-12-16
URL	https://arxiv.org/abs/1912.06708v1
PDF	https://arxiv.org/pdf/1912.06708v1.pdf
PWC	https://paperswithcode.com/paper/a-posteriori-trading-inspired-model-free-time
Repo
Framework


Title	Structured Modeling of Joint Deep Feature and Prediction Refinement for Salient Object Detection
Authors	Yingyue Xu, Dan Xu, Xiaopeng Hong, Wanli Ouyang, Rongrong Ji, Min Xu, Guoying Zhao
Abstract	Recent saliency models extensively explore to incorporate multi-scale contextual information from Convolutional Neural Networks (CNNs). Besides direct fusion strategies, many approaches introduce message-passing to enhance CNN features or predictions. However, the messages are mainly transmitted in two ways, by feature-to-feature passing, and by prediction-to-prediction passing. In this paper, we add message-passing between features and predictions and propose a deep unified CRF saliency model . We design a novel cascade CRFs architecture with CNN to jointly refine deep features and predictions at each scale and progressively compute a final refined saliency map. We formulate the CRF graphical model that involves message-passing of feature-feature, feature-prediction, and prediction-prediction, from the coarse scale to the finer scale, to update the features and the corresponding predictions. Also, we formulate the mean-field updates for joint end-to-end model training with CNN through back propagation. The proposed deep unified CRF saliency model is evaluated over six datasets and shows highly competitive performance among the state of the arts.
Tasks	Object Detection, Salient Object Detection
Published	2019-09-10
URL	https://arxiv.org/abs/1909.04366v1
PDF	https://arxiv.org/pdf/1909.04366v1.pdf
PWC	https://paperswithcode.com/paper/structured-modeling-of-joint-deep-feature-and
Repo
Framework

Solar-Sail Trajectory Design for Multiple Near Earth Asteroid Exploration Based on Deep Neural Networks


Title	Solar-Sail Trajectory Design for Multiple Near Earth Asteroid Exploration Based on Deep Neural Networks
Authors	Yu Song, Shengping Gong
Abstract	In the preliminary trajectory design of the multi-target rendezvous problem, a model that can quickly estimate the cost of the orbital transfer is essential. The estimation of the transfer time using solar sail between two arbitrary orbits is difficult and usually requires to solve an optimal control problem. Inspired by the successful applications of the deep neural network in nonlinear regression, this work explores the possibility and effectiveness of mapping the transfer time for solar sail from the orbital characteristics using the deep neural network. Furthermore, the Monte Carlo Tree Search method is investigated and used to search the optimal sequence considering a multi-asteroid exploration problem. The obtained sequences from preliminary design will be solved and verified by sequentially solving the optimal control problem. Two examples of different application backgrounds validate the effectiveness of the proposed approach.
Tasks
Published	2019-01-08
URL	http://arxiv.org/abs/1901.02172v3
PDF	http://arxiv.org/pdf/1901.02172v3.pdf
PWC	https://paperswithcode.com/paper/solar-sail-trajectory-design-of-multiple-near
Repo
Framework

An Interval-Valued Utility Theory for Decision Making with Dempster-Shafer Belief Functions


Title	An Interval-Valued Utility Theory for Decision Making with Dempster-Shafer Belief Functions
Authors	Thierry Denoeux, Prakash P. Shenoy
Abstract	The main goal of this paper is to describe an axiomatic utility theory for Dempster-Shafer belief function lotteries. The axiomatic framework used is analogous to von Neumann-Morgenstern’s utility theory for probabilistic lotteries as described by Luce and Raiffa. Unlike the probabilistic case, our axiomatic framework leads to interval-valued utilities, and therefore, to a partial (incomplete) preference order on the set of all belief function lotteries. If the belief function reference lotteries we use are Bayesian belief functions, then our representation theorem coincides with Jaffray’s representation theorem for his linear utility theory for belief functions. We illustrate our framework using some examples discussed in the literature, and we propose a simple model based on an interval-valued pessimism index representing a decision-maker’s attitude to ambiguity and indeterminacy. Finally, we compare our decision theory with those proposed by Jaffray, Smets, Dubois et al., Giang and Shenoy, and Shafer.
Tasks	Decision Making
Published	2019-12-13
URL	https://arxiv.org/abs/1912.06594v1
PDF	https://arxiv.org/pdf/1912.06594v1.pdf
PWC	https://paperswithcode.com/paper/an-interval-valued-utility-theory-for
Repo
Framework

LGAN: Lung Segmentation in CT Scans Using Generative Adversarial Network


Title	LGAN: Lung Segmentation in CT Scans Using Generative Adversarial Network
Authors	Jiaxing Tan, Longlong Jing, Yumei Huo, Yingli Tian, Oguz Akin
Abstract	Lung segmentation in computerized tomography (CT) images is an important procedure in various lung disease diagnosis. Most of the current lung segmentation approaches are performed through a series of procedures with manually empirical parameter adjustments in each step. Pursuing an automatic segmentation method with fewer steps, in this paper, we propose a novel deep learning Generative Adversarial Network (GAN) based lung segmentation schema, which we denote as LGAN. Our proposed schema can be generalized to different kinds of neural networks for lung segmentation in CT images and is evaluated on a dataset containing 220 individual CT scans with two metrics: segmentation quality and shape similarity. Also, we compared our work with current state of the art methods. The results obtained with this study demonstrate that the proposed LGAN schema can be used as a promising tool for automatic lung segmentation due to its simplified procedure as well as its good performance.
Tasks
Published	2019-01-11
URL	http://arxiv.org/abs/1901.03473v1
PDF	http://arxiv.org/pdf/1901.03473v1.pdf
PWC	https://paperswithcode.com/paper/lgan-lung-segmentation-in-ct-scans-using
Repo
Framework

Distributed estimation of the inverse Hessian by determinantal averaging


Title	Distributed estimation of the inverse Hessian by determinantal averaging
Authors	Michał Dereziński, Michael W. Mahoney
Abstract	In distributed optimization and distributed numerical linear algebra, we often encounter an inversion bias: if we want to compute a quantity that depends on the inverse of a sum of distributed matrices, then the sum of the inverses does not equal the inverse of the sum. An example of this occurs in distributed Newton’s method, where we wish to compute (or implicitly work with) the inverse Hessian multiplied by the gradient. In this case, locally computed estimates are biased, and so taking a uniform average will not recover the correct solution. To address this, we propose determinantal averaging, a new approach for correcting the inversion bias. This approach involves reweighting the local estimates of the Newton’s step proportionally to the determinant of the local Hessian estimate, and then averaging them together to obtain an improved global estimate. This method provides the first known distributed Newton step that is asymptotically consistent, i.e., it recovers the exact step in the limit as the number of distributed partitions grows to infinity. To show this, we develop new expectation identities and moment bounds for the determinant and adjugate of a random matrix. Determinantal averaging can be applied not only to Newton’s method, but to computing any quantity that is a linear tranformation of a matrix inverse, e.g., taking a trace of the inverse covariance matrix, which is used in data uncertainty quantification.
Tasks	Distributed Optimization
Published	2019-05-28
URL	https://arxiv.org/abs/1905.11546v1
PDF	https://arxiv.org/pdf/1905.11546v1.pdf
PWC	https://paperswithcode.com/paper/distributed-estimation-of-the-inverse-hessian
Repo
Framework

ARCHANGEL: Tamper-proofing Video Archives using Temporal Content Hashes on the Blockchain


Title	ARCHANGEL: Tamper-proofing Video Archives using Temporal Content Hashes on the Blockchain
Authors	Tu Bui, Daniel Cooper, John Collomosse, Mark Bell, Alex Green, John Sheridan, Jez Higgins, Arindra Das, Jared Keller, Olivier Thereaux, Alan Brown
Abstract	We present ARCHANGEL; a novel distributed ledger based system for assuring the long-term integrity of digital video archives. First, we describe a novel deep network architecture for computing compact temporal content hashes (TCHs) from audio-visual streams with durations of minutes or hours. Our TCHs are sensitive to accidental or malicious content modification (tampering) but invariant to the codec used to encode the video. This is necessary due to the curatorial requirement for archives to format shift video over time to ensure future accessibility. Second, we describe how the TCHs (and the models used to derive them) are secured via a proof-of-authority blockchain distributed across multiple independent archives. We report on the efficacy of ARCHANGEL within the context of a trial deployment in which the national government archives of the United Kingdom, Estonia and Norway participated.
Tasks
Published	2019-04-26
URL	http://arxiv.org/abs/1904.12059v1
PDF	http://arxiv.org/pdf/1904.12059v1.pdf
PWC	https://paperswithcode.com/paper/archangel-tamper-proofing-video-archives
Repo
Framework

Uncertainty-aware performance assessment of optical imaging modalities with invertible neural networks


Title	Uncertainty-aware performance assessment of optical imaging modalities with invertible neural networks
Authors	Tim J. Adler, Lynton Ardizzone, Anant Vemuri, Leonardo Ayala, Janek Gröhl, Thomas Kirchner, Sebastian Wirkert, Jakob Kruse, Carsten Rother, Ullrich Köthe, Lena Maier-Hein
Abstract	Purpose: Optical imaging is evolving as a key technique for advanced sensing in the operating room. Recent research has shown that machine learning algorithms can be used to address the inverse problem of converting pixel-wise multispectral reflectance measurements to underlying tissue parameters, such as oxygenation. Assessment of the specific hardware used in conjunction with such algorithms, however, has not properly addressed the possibility that the problem may be ill-posed. Methods: We present a novel approach to the assessment of optical imaging modalities, which is sensitive to the different types of uncertainties that may occur when inferring tissue parameters. Based on the concept of invertible neural networks, our framework goes beyond point estimates and maps each multispectral measurement to a full posterior probability distribution which is capable of representing ambiguity in the solution via multiple modes. Performance metrics for a hardware setup can then be computed from the characteristics of the posteriors. Results: Application of the assessment framework to the specific use case of camera selection for physiological parameter estimation yields the following insights: (1) Estimation of tissue oxygenation from multispectral images is a well-posed problem, while (2) blood volume fraction may not be recovered without ambiguity. (3) In general, ambiguity may be reduced by increasing the number of spectral bands in the camera. Conclusion: Our method could help to optimize optical camera design in an application-specific manner.
Tasks
Published	2019-03-08
URL	http://arxiv.org/abs/1903.03441v1
PDF	http://arxiv.org/pdf/1903.03441v1.pdf
PWC	https://paperswithcode.com/paper/uncertainty-aware-performance-assessment-of
Repo
Framework

A Variational Bayes Approach to Adaptive Radio Tomography


Title	A Variational Bayes Approach to Adaptive Radio Tomography
Authors	Donghoon Lee, Georgios B. Giannakis
Abstract	Radio tomographic imaging (RTI) is an emerging technology for localization of physical objects in a geographical area covered by wireless networks. With attenuation measurements collected at spatially distributed sensors, RTI capitalizes on spatial loss fields (SLFs) measuring the absorption of radio frequency waves at spatial locations along the propagation path. These SLFs can be utilized for interference management in wireless communication networks, environmental monitoring, and survivor localization after natural disasters such as earthquakes. Key to the success of RTI is to accurately model shadowing as the weighted line integral of the SLF. To learn the SLF exhibiting statistical heterogeneity induced by spatially diverse environments, the present work develops a Bayesian framework entailing a piecewise homogeneous SLF with an underlying hidden Markov random field model. Utilizing variational Bayes techniques, the novel approach yields efficient field estimators at affordable complexity. A data-adaptive sensor selection strategy is also introduced to collect informative measurements for effective reconstruction of the SLF. Numerical tests using synthetic and real datasets demonstrate the capabilities of the proposed approach to radio tomography and channel-gain estimation.
Tasks
Published	2019-09-05
URL	https://arxiv.org/abs/1909.03892v1
PDF	https://arxiv.org/pdf/1909.03892v1.pdf
PWC	https://paperswithcode.com/paper/a-variational-bayes-approach-to-adaptive
Repo
Framework

FLAT: Few-Shot Learning via Autoencoding Transformation Regularizers


Title	FLAT: Few-Shot Learning via Autoencoding Transformation Regularizers
Authors	Haohang Xu, Hongkai Xiong, Guojun Qi
Abstract	One of the most significant challenges facing a few-shot learning task is the generalizability of the (meta-)model from the base to the novel categories. Most of existing few-shot learning models attempt to address this challenge by either learning the meta-knowledge from multiple simulated tasks on the base categories, or resorting to data augmentation by applying various transformations to training examples. However, the supervised nature of model training in these approaches limits their ability of exploring variations across different categories, thus restricting their cross-category generalizability in modeling novel concepts. To this end, we present a novel regularization mechanism by learning the change of feature representations induced by a distribution of transformations without using the labels of data examples. We expect this regularizer could expand the semantic space of base categories to cover that of novel categories through the transformation of feature representations. It could minimize the risk of overfitting into base categories by inspecting the transformation-augmented variations at the encoded feature level. This results in the proposed FLAT (Few-shot Learning via Autoencoding Transformations) approach by autoencoding the applied transformations. The experiment results show the superior performances to the current state-of-the-art methods in literature.
Tasks	Data Augmentation, Few-Shot Learning
Published	2019-12-29
URL	https://arxiv.org/abs/1912.12674v1
PDF	https://arxiv.org/pdf/1912.12674v1.pdf
PWC	https://paperswithcode.com/paper/flat-few-shot-learning-via-autoencoding
Repo
Framework

Looking Ahead: Anticipating Pedestrians Crossing with Future Frames Prediction


Title	Looking Ahead: Anticipating Pedestrians Crossing with Future Frames Prediction
Authors	Mohamed Chaabane, Ameni Trabelsi, Nathaniel Blanchard, Ross Beveridge
Abstract	In this paper, we present an end-to-end future-prediction model that focuses on pedestrian safety. Specifically, our model uses previous video frames, recorded from the perspective of the vehicle, to predict if a pedestrian will cross in front of the vehicle. The long term goal of this work is to design a fully autonomous system that acts and reacts as a defensive human driver would — predicting future events and reacting to mitigate risk. We focus on pedestrian-vehicle interactions because of the high risk of harm to the pedestrian if their actions are miss-predicted. Our end-to-end model consists of two stages: the first stage is an encoder/decoder network that learns to predict future video frames. The second stage is a deep spatio-temporal network that utilizes the predicted frames of the first stage to predict the pedestrian’s future action. Our system achieves state-of-the-art accuracy on pedestrian behavior prediction and future frames prediction on the Joint Attention for Autonomous Driving (JAAD) dataset.
Tasks	Action Recognition In Videos, Activity Recognition In Videos, Autonomous Driving, Future prediction, Predict Future Video Frames, Video Prediction
Published	2019-10-20
URL	https://arxiv.org/abs/1910.09077v2
PDF	https://arxiv.org/pdf/1910.09077v2.pdf
PWC	https://paperswithcode.com/paper/looking-ahead-anticipating-pedestrians
Repo
Framework

A Meta-Learning Framework for Generalized Zero-Shot Learning


Title	A Meta-Learning Framework for Generalized Zero-Shot Learning
Authors	Vinay Kumar Verma, Dhanajit Brahma, Piyush Rai
Abstract	Learning to classify unseen class samples at test time is popularly referred to as zero-shot learning (ZSL). If test samples can be from training (seen) as well as unseen classes, it is a more challenging problem due to the existence of strong bias towards seen classes. This problem is generally known as \emph{generalized} zero-shot learning (GZSL). Thanks to the recent advances in generative models such as VAEs and GANs, sample synthesis based approaches have gained considerable attention for solving this problem. These approaches are able to handle the problem of class bias by synthesizing unseen class samples. However, these ZSL/GZSL models suffer due to the following key limitations: $(i)$ Their training stage learns a class-conditioned generator using only \emph{seen} class data and the training stage does not \emph{explicitly} learn to generate the unseen class samples; $(ii)$ They do not learn a generic optimal parameter which can easily generalize for both seen and unseen class generation; and $(iii)$ If we only have access to a very few samples per seen class, these models tend to perform poorly. In this paper, we propose a meta-learning based generative model that naturally handles these limitations. The proposed model is based on integrating model-agnostic meta learning with a Wasserstein GAN (WGAN) to handle $(i)$ and $(iii)$, and uses a novel task distribution to handle $(ii)$. Our proposed model yields significant improvements on standard ZSL as well as more challenging GZSL setting. In ZSL setting, our model yields 4.5%, 6.0%, 9.8%, and 27.9% relative improvements over the current state-of-the-art on CUB, AWA1, AWA2, and aPY datasets, respectively.
Tasks	Meta-Learning, Zero-Shot Learning
Published	2019-09-10
URL	https://arxiv.org/abs/1909.04344v1
PDF	https://arxiv.org/pdf/1909.04344v1.pdf
PWC	https://paperswithcode.com/paper/a-meta-learning-framework-for-generalized
Repo
Framework

DAC: The Double Actor-Critic Architecture for Learning Options


Title	DAC: The Double Actor-Critic Architecture for Learning Options
Authors	Shangtong Zhang, Shimon Whiteson
Abstract	We reformulate the option framework as two parallel augmented MDPs. Under this novel formulation, all policy optimization algorithms can be used off the shelf to learn intra-option policies, option termination conditions, and a master policy over options. We apply an actor-critic algorithm on each augmented MDP, yielding the Double Actor-Critic (DAC) architecture. Furthermore, we show that, when state-value functions are used as critics, one critic can be expressed in terms of the other, and hence only one critic is necessary. We conduct an empirical study on challenging robot simulation tasks. In a transfer learning setting, DAC outperforms both its hierarchy-free counterpart and previous gradient-based option learning algorithms.
Tasks	Transfer Learning
Published	2019-04-29
URL	https://arxiv.org/abs/1904.12691v7
PDF	https://arxiv.org/pdf/1904.12691v7.pdf
PWC	https://paperswithcode.com/paper/dac-the-double-actor-critic-architecture-for
Repo
Framework

GlassLoc: Plenoptic Grasp Pose Detection in Transparent Clutter


Title	GlassLoc: Plenoptic Grasp Pose Detection in Transparent Clutter
Authors	Zheming Zhou, Tianyang Pan, Shiyu Wu, Haonan Chang, Odest Chadwicke Jenkins
Abstract	Transparent objects are prevalent across many environments of interest for dexterous robotic manipulation. Such transparent material leads to considerable uncertainty for robot perception and manipulation, and remains an open challenge for robotics. This problem is exacerbated when multiple transparent objects cluster into piles of clutter. In household environments, for example, it is common to encounter piles of glassware in kitchens, dining rooms, and reception areas, which are essentially invisible to modern robots. We present the GlassLoc algorithm for grasp pose detection of transparent objects in transparent clutter using plenoptic sensing. GlassLoc classifies graspable locations in space informed by a Depth Likelihood Volume (DLV) descriptor. We extend the DLV to infer the occupancy of transparent objects over a given space from multiple plenoptic viewpoints. We demonstrate and evaluate the GlassLoc algorithm on a Michigan Progress Fetch mounted with a first-generation Lytro. The effectiveness of our algorithm is evaluated through experiments for grasp detection and execution with a variety of transparent glassware in minor clutter.
Tasks
Published	2019-09-10
URL	https://arxiv.org/abs/1909.04269v2
PDF	https://arxiv.org/pdf/1909.04269v2.pdf
PWC	https://paperswithcode.com/paper/glassloc-plenoptic-grasp-pose-detection-in
Repo
Framework

DeepMeshFlow: Content Adaptive Mesh Deformation for Robust Image Registration


Title	DeepMeshFlow: Content Adaptive Mesh Deformation for Robust Image Registration
Authors	Nianjin Ye, Chuan Wang, Shuaicheng Liu, Lanpeng Jia, Jue Wang, Yongqing Cui
Abstract	Image alignment by mesh warps, such as meshflow, is a fundamental task which has been widely applied in various vision applications(e.g., multi-frame HDR/denoising, video stabilization). Traditional mesh warp methods detect and match image features, where the quality of alignment highly depends on the quality of image features. However, the image features are not robust in occurrence of low-texture and low-light scenes. Deep homography methods, on the other hand, are free from such problem by learning deep features for robust performance. However, a homography is limited to plane motions. In this work, we present a deep meshflow motion model, which takes two images as input and output a sparse motion field with motions located at mesh vertexes. The deep meshflow enjoys the merics of meshflow that can describe nonlinear motions while also shares advantage of deep homography that is robust against challenging textureless scenarios. In particular, a new unsupervised network structure is presented with content-adaptive capability. On one hand, the image content that cannot be aligned under mesh representation are rejected by our learned mask, similar to the RANSAC procedure. On the other hand, we learn multiple mesh resolutions, combining to a non-uniform mesh division. Moreover, a comprehensive dataset is presented, covering various scenes for training and testing. The comparison between both traditional mesh warp methods and deep based methods show the effectiveness of our deep meshflow motion model.
Tasks	Denoising, Image Registration
Published	2019-12-11
URL	https://arxiv.org/abs/1912.05131v1
PDF	https://arxiv.org/pdf/1912.05131v1.pdf
PWC	https://paperswithcode.com/paper/deepmeshflow-content-adaptive-mesh
Repo
Framework