January 29, 2020

3060 words 15 mins read

Paper Group ANR 690

Adversarial View-Consistent Learning for Monocular Depth Estimation. Supervised Deep Neural Networks (DNNs) for Pricing/Calibration of Vanilla/Exotic Options Under Various Different Processes. Redistribution Mechanism on Networks. A Novel Multi-layer Framework for Tiny Obstacle Discovery. Solving Online Threat Screening Games using Constrained Acti …

Adversarial View-Consistent Learning for Monocular Depth Estimation


Title	Adversarial View-Consistent Learning for Monocular Depth Estimation
Authors	Yixuan Liu, Yuwang Wang, Shengjin Wang
Abstract	This paper addresses the problem of Monocular Depth Estimation (MDE). Existing approaches on MDE usually model it as a pixel-level regression problem, ignoring the underlying geometry property. We empirically find this may result in sub-optimal solution: while the predicted depth map presents small loss value in one specific view, it may exhibit large loss if viewed in different directions. In this paper, inspired by multi-view stereo (MVS), we propose an Adversarial View-Consistent Learning (AVCL) framework to force the estimated depth map to be all reasonable viewed from multiple views. To this end, we first design a differentiable depth map warping operation, which is end-to-end trainable, and then propose a pose generator to generate novel views for a given image in an adversarial manner. Collaborating with the differentiable depth map warping operation, the pose generator encourages the depth estimation network to learn from hard views, hence produce view-consistent depth maps . We evaluate our method on NYU Depth V2 dataset and the experimental results show promising performance gain upon state-of-the-art MDE approaches.
Tasks	Depth Estimation, Monocular Depth Estimation
Published	2019-08-04
URL	https://arxiv.org/abs/1908.01301v1
PDF	https://arxiv.org/pdf/1908.01301v1.pdf
PWC	https://paperswithcode.com/paper/adversarial-view-consistent-learning-for
Repo
Framework

Supervised Deep Neural Networks (DNNs) for Pricing/Calibration of Vanilla/Exotic Options Under Various Different Processes


Title	Supervised Deep Neural Networks (DNNs) for Pricing/Calibration of Vanilla/Exotic Options Under Various Different Processes
Authors	Ali Hirsa, Tugce Karatas, Amir Oskoui
Abstract	We apply supervised deep neural networks (DNNs) for pricing and calibration of both vanilla and exotic options under both diffusion and pure jump processes with and without stochastic volatility. We train our neural network models under different number of layers, neurons per layer, and various different activation functions in order to find which combinations work better empirically. For training, we consider various different loss functions and optimization routines. We demonstrate that deep neural networks exponentially expedite option pricing compared to commonly used option pricing methods which consequently make calibration and parameter estimation super fast.
Tasks	Calibration
Published	2019-02-15
URL	http://arxiv.org/abs/1902.05810v1
PDF	http://arxiv.org/pdf/1902.05810v1.pdf
PWC	https://paperswithcode.com/paper/supervised-deep-neural-networks-dnns-for
Repo
Framework

Redistribution Mechanism on Networks


Title	Redistribution Mechanism on Networks
Authors	Wen Zhang, Dengji Zhao, Hanyu Chen
Abstract	Redistribution mechanisms have been proposed for more efficient resource allocation but not for profit. We consider redistribution mechanism design in a setting where participants are connected and the resource owner is only connected to some of them. In this setting, to make the resource allocation more efficient, the resource owner has to inform the others who are not her neighbours, but her neighbours do not want more participants to compete with them. Hence, the goal is to design a redistribution mechanism such that participants are incentivized to invite more participants and the resource owner does not earn or lose much money from the allocation. We first show that existing redistribution mechanisms cannot be directly applied in the network setting and prove the impossibility to achieve efficiency without a deficit. Then we propose a novel network-based redistribution mechanism such that all participants on the network are invited, the allocation is more efficient and the resource owner has no deficit.
Tasks
Published	2019-10-21
URL	https://arxiv.org/abs/1910.09335v2
PDF	https://arxiv.org/pdf/1910.09335v2.pdf
PWC	https://paperswithcode.com/paper/redistribution-mechanism-design-on-networks
Repo
Framework

A Novel Multi-layer Framework for Tiny Obstacle Discovery


Title	A Novel Multi-layer Framework for Tiny Obstacle Discovery
Authors	Feng Xue, Anlong Ming, Menghan Zhou, Yu Zhou
Abstract	For tiny obstacle discovery in a monocular image, edge is a fundamental visual element. Nevertheless, because of various reasons, e.g., noise and similar color distribution with background, it is still difficult to detect the edges of tiny obstacles at long distance. In this paper, we propose an obstacle-aware discovery method to recover the missing contours of these obstacles, which helps to obtain obstacle proposals as much as possible. First, by using visual cues in monocular images, several multi-layer regions are elaborately inferred to reveal the distances from the camera. Second, several novel obstacle-aware occlusion edge maps are constructed to well capture the contours of tiny obstacles, which combines cues from each layer. Third, to ensure the existence of the tiny obstacle proposals, the maps from all layers are used for proposals extraction. Finally, based on these proposals containing tiny obstacles, a novel obstacle-aware regressor is proposed to generate an obstacle occupied probability map with high confidence. The convincing experimental results with comparisons on the Lost and Found dataset demonstrate the effectiveness of our approach, achieving around 9.5% improvement on the accuracy than FPHT and PHT, it even gets comparable performance to MergeNet. Moreover, our method outperforms the state-of-the-art algorithms and significantly improves the discovery ability for tiny obstacles at long distance.
Tasks
Published	2019-04-23
URL	https://arxiv.org/abs/1904.10161v3
PDF	https://arxiv.org/pdf/1904.10161v3.pdf
PWC	https://paperswithcode.com/paper/a-novel-multi-layer-framework-for-tiny
Repo
Framework

Solving Online Threat Screening Games using Constrained Action Space Reinforcement Learning


Title	Solving Online Threat Screening Games using Constrained Action Space Reinforcement Learning
Authors	Sanket Shah, Arunesh Sinha, Pradeep Varakantham, Andrew Perrault, Milind Tambe
Abstract	Large-scale screening for potential threats with limited resources and capacity for screening is a problem of interest at airports, seaports, and other ports of entry. Adversaries can observe screening procedures and arrive at a time when there will be gaps in screening due to limited resource capacities. To capture this game between ports and adversaries, this problem has been previously represented as a Stackelberg game, referred to as a Threat Screening Game (TSG). Given the significant complexity associated with solving TSGs and uncertainty in arrivals of customers, existing work has assumed that screenees arrive and are allocated security resources at the beginning of the time window. In practice, screenees such as airport passengers arrive in bursts correlated with flight time and are not bound by fixed time windows. To address this, we propose an online threat screening model in which screening strategy is determined adaptively as a passenger arrives while satisfying a hard bound on acceptable risk of not screening a threat. To solve the online problem with a hard bound on risk, we formulate it as a Reinforcement Learning (RL) problem with constraints on the action space (hard bound on risk). We provide a novel way to efficiently enforce linear inequality constraints on the action output in Deep Reinforcement Learning. We show that our solution allows us to significantly reduce screenee wait time while guaranteeing a bound on risk.
Tasks
Published	2019-11-20
URL	https://arxiv.org/abs/1911.08799v1
PDF	https://arxiv.org/pdf/1911.08799v1.pdf
PWC	https://paperswithcode.com/paper/solving-online-threat-screening-games-using
Repo
Framework

Copulas as High-Dimensional Generative Models: Vine Copula Autoencoders


Title	Copulas as High-Dimensional Generative Models: Vine Copula Autoencoders
Authors	Natasa Tagasovska, Damien Ackerer, Thibault Vatter
Abstract	We introduce the vine copula autoencoder (VCAE), a flexible generative model for high-dimensional distributions built in a straightforward three-step procedure. First, an autoencoder (AE) compresses the data into a lower dimensional representation. Second, the multivariate distribution of the encoded data is estimated with vine copulas. Third, a generative model is obtained by combining the estimated distribution with the decoder part of the AE. As such, the proposed approach can transform any already trained AE into a flexible generative model at a low computational cost. This is an advantage over existing generative models such as adversarial networks and variational AEs which can be difficult to train and can impose strong assumptions on the latent space. Experiments on MNIST, Street View House Numbers and Large-Scale CelebFaces Attributes datasets show that VCAEs can achieve competitive results to standard baselines.
Tasks
Published	2019-06-12
URL	https://arxiv.org/abs/1906.05423v2
PDF	https://arxiv.org/pdf/1906.05423v2.pdf
PWC	https://paperswithcode.com/paper/copulas-as-high-dimensional-generative-models
Repo
Framework

On-board Deep Q-Network for UAV-assisted Online Power Transfer and Data Collection


Title	On-board Deep Q-Network for UAV-assisted Online Power Transfer and Data Collection
Authors	Kai Li, Wei Ni, Eduardo Tovar
Abstract	Unmanned Aerial Vehicles (UAVs) with Microwave Power Transfer (MPT) capability provide a practical means to deploy a large number of wireless powered sensing devices into areas with no access to persistent power supplies. The UAV can charge the sensing devices remotely and harvest their data. A key challenge is online MPT and data collection in the presence of on-board control of a UAV (e.g., patrolling velocity) for preventing battery drainage and data queue overflow of the sensing devices, while up-to-date knowledge on battery level and data queue of the devices is not available at the UAV. In this paper, an on-board deep Q-network is developed to minimize the overall data packet loss of the sensing devices, by optimally deciding the device to be charged and interrogated for data collection, and the instantaneous patrolling velocity of the UAV. Specifically, we formulate a Markov Decision Process (MDP) with the states of battery level and data queue length of sensing devices, channel conditions, and waypoints given the trajectory of the UAV; and solve it optimally with Q-learning. Furthermore, we propose the on-board deep Q-network that can enlarge the state space of the MDP, and a deep reinforcement learning based scheduling algorithm that asymptotically derives the optimal solution online, even when the UAV has only outdated knowledge on the MDP states. Numerical results demonstrate that the proposed deep reinforcement learning algorithm reduces the packet loss by at least 69.2%, as compared to existing non-learning greedy algorithms.
Tasks	Q-Learning
Published	2019-06-04
URL	https://arxiv.org/abs/1906.07064v1
PDF	https://arxiv.org/pdf/1906.07064v1.pdf
PWC	https://paperswithcode.com/paper/on-board-deep-q-network-for-uav-assisted
Repo
Framework

Kernel Truncated Randomized Ridge Regression: Optimal Rates and Low Noise Acceleration


Title	Kernel Truncated Randomized Ridge Regression: Optimal Rates and Low Noise Acceleration
Authors	Kwang-Sung Jun, Ashok Cutkosky, Francesco Orabona
Abstract	In this paper, we consider the nonparametric least square regression in a Reproducing Kernel Hilbert Space (RKHS). We propose a new randomized algorithm that has optimal generalization error bounds with respect to the square loss, closing a long-standing gap between upper and lower bounds. Moreover, we show that our algorithm has faster finite-time and asymptotic rates on problems where the Bayes risk with respect to the square loss is small. We state our results using standard tools from the theory of least square regression in RKHSs, namely, the decay of the eigenvalues of the associated integral operator and the complexity of the optimal predictor measured through the integral operator.
Tasks
Published	2019-05-25
URL	https://arxiv.org/abs/1905.10680v1
PDF	https://arxiv.org/pdf/1905.10680v1.pdf
PWC	https://paperswithcode.com/paper/kernel-truncated-randomized-ridge-regression
Repo
Framework

An Application of Manifold Learning in Global Shape Descriptors


Title	An Application of Manifold Learning in Global Shape Descriptors
Authors	Fereshteh S. Bashiri, Reihaneh Rostami, Peggy Peissig, Roshan M. D’Souza, Zeyun Yu
Abstract	With the rapid expansion of applied 3D computational vision, shape descriptors have become increasingly important for a wide variety of applications and objects from molecules to planets. Appropriate shape descriptors are critical for accurate (and efficient) shape retrieval and 3D model classification. Several spectral-based shape descriptors have been introduced by solving various physical equations over a 3D surface model. In this paper, for the first time, we incorporate a specific group of techniques in statistics and machine learning, known as manifold learning, to develop a global shape descriptor in the computer graphics domain. The proposed descriptor utilizes the Laplacian Eigenmap technique in which the Laplacian eigenvalue problem is discretized using an exponential weighting scheme. As a result, our descriptor eliminates the limitations tied to the existing spectral descriptors, namely dependency on triangular mesh representation and high intra-class quality of 3D models. We also present a straightforward normalization method to obtain a scale-invariant descriptor. The extensive experiments performed in this study show that the present contribution provides a highly discriminative and robust shape descriptor under the presence of a high level of noise, random scale variations, and low sampling rate, in addition to the known isometric-invariance property of the Laplace-Beltrami operator. The proposed method significantly outperforms state-of-the-art algorithms on several non-rigid shape retrieval benchmarks.
Tasks
Published	2019-01-08
URL	http://arxiv.org/abs/1901.02508v1
PDF	http://arxiv.org/pdf/1901.02508v1.pdf
PWC	https://paperswithcode.com/paper/an-application-of-manifold-learning-in-global
Repo
Framework

A Deeper Look at Facial Expression Dataset Bias


Title	A Deeper Look at Facial Expression Dataset Bias
Authors	Shan Li, Weihong Deng
Abstract	Datasets play an important role in the progress of facial expression recognition algorithms, but they may suffer from obvious biases caused by different cultures and collection conditions. To look deeper into this bias, we first conduct comprehensive experiments on dataset recognition and crossdataset generalization tasks, and for the first time explore the intrinsic causes of the dataset discrepancy. The results quantitatively verify that current datasets have a strong buildin bias and corresponding analyses indicate that the conditional probability distributions between source and target datasets are different. However, previous researches are mainly based on shallow features with limited discriminative ability under the assumption that the conditional distribution remains unchanged across domains. To address these issues, we further propose a novel deep Emotion-Conditional Adaption Network (ECAN) to learn domain-invariant and discriminative feature representations, which can match both the marginal and the conditional distributions across domains simultaneously. In addition, the largely ignored expression class distribution bias is also addressed by a learnable re-weighting parameter, so that the training and testing domains can share similar class distribution. Extensive cross-database experiments on both lab-controlled datasets (CK+, JAFFE, MMI and Oulu-CASIA) and real-world databases (AffectNet, FER2013, RAF-DB 2.0 and SFEW 2.0) demonstrate that our ECAN can yield competitive performances across various facial expression transfer tasks and outperform the state-of-theart methods.
Tasks	Facial Expression Recognition
Published	2019-04-25
URL	http://arxiv.org/abs/1904.11150v1
PDF	http://arxiv.org/pdf/1904.11150v1.pdf
PWC	https://paperswithcode.com/paper/a-deeper-look-at-facial-expression-dataset
Repo
Framework

Real-time Hair Segmentation and Recoloring on Mobile GPUs


Title	Real-time Hair Segmentation and Recoloring on Mobile GPUs
Authors	Andrei Tkachenka, Gregory Karpiak, Andrey Vakunov, Yury Kartynnik, Artsiom Ablavatski, Valentin Bazarevsky, Siargey Pisarchyk
Abstract	We present a novel approach for neural network-based hair segmentation from a single camera input specifically designed for real-time, mobile application. Our relatively small neural network produces a high-quality hair segmentation mask that is well suited for AR effects, e.g. virtual hair recoloring. The proposed model achieves real-time inference speed on mobile GPUs (30-100+ FPS, depending on the device) with high accuracy. We also propose a very realistic hair recoloring scheme. Our method has been deployed in major AR application and is used by millions of users.
Tasks
Published	2019-07-15
URL	https://arxiv.org/abs/1907.06740v1
PDF	https://arxiv.org/pdf/1907.06740v1.pdf
PWC	https://paperswithcode.com/paper/real-time-hair-segmentation-and-recoloring-on
Repo
Framework

Evaluation of the Spatio-Temporal features and GAN for Micro-expression Recognition System


Title	Evaluation of the Spatio-Temporal features and GAN for Micro-expression Recognition System
Authors	Sze-Teng Liong, Y. S. Gan, Danna Zheng, Shu-Meng Lic, Hao-Xuan Xua, Han-Zhe Zhang, Ran-Ke Lyu, Kun-Hong Liu
Abstract	Owing to the development and advancement of artificial intelligence, numerous works were established in the human facial expression recognition system. Meanwhile, the detection and classification of micro-expressions are attracting attentions from various research communities in the recent few years. In this paper, we first review the processes of a conventional optical-flow-based recognition system, which comprised of facial landmarks annotations, optical flow guided images computation, features extraction and emotion class categorization. Secondly, a few approaches have been proposed to improve the feature extraction part, such as exploiting GAN to generate more image samples. Particularly, several variations of optical flow are computed in order to generate optimal images to lead to high recognition accuracy. Next, GAN, a combination of Generator and Discriminator, is utilized to generate new “fake” images to increase the sample size. Thirdly, a modified state-of-the-art Convolutional neural networks is proposed. To verify the effectiveness of the the proposed method, the results are evaluated on spontaneous micro-expression databases, namely SMIC, CASME II and SAMM. Both the F1-score and accuracy performance metrics are reported in this paper.
Tasks	Facial Expression Recognition, Optical Flow Estimation
Published	2019-04-03
URL	http://arxiv.org/abs/1904.01748v1
PDF	http://arxiv.org/pdf/1904.01748v1.pdf
PWC	https://paperswithcode.com/paper/evaluation-of-the-spatio-temporal-features
Repo
Framework

CU-Net: Cascaded U-Net with Loss Weighted Sampling for Brain Tumor Segmentation


Title	CU-Net: Cascaded U-Net with Loss Weighted Sampling for Brain Tumor Segmentation
Authors	Hongying Liu, Xiongjie Shen, Fanhua Shang, Fei Wang
Abstract	This paper proposes a novel cascaded U-Net for brain tumor segmentation. Inspired by the distinct hierarchical structure of brain tumor, we design a cascaded deep network framework, in which the whole tumor is segmented firstly and then the tumor internal substructures are further segmented. Considering that the increase of the network depth brought by cascade structures leads to a loss of accurate localization information in deeper layers, we construct many skip connections to link features at the same resolution and transmit detailed information from shallow layers to the deeper layers. Then we present a loss weighted sampling (LWS) scheme to eliminate the issue of imbalanced data during training the network. Experimental results on BraTS 2017 data show that our architecture framework outperforms the state-of-the-art segmentation algorithms, especially in terms of segmentation sensitivity.
Tasks	Brain Tumor Segmentation
Published	2019-07-17
URL	https://arxiv.org/abs/1907.07677v1
PDF	https://arxiv.org/pdf/1907.07677v1.pdf
PWC	https://paperswithcode.com/paper/cu-net-cascaded-u-net-with-loss-weighted
Repo
Framework

Generalization Bounds For Unsupervised and Semi-Supervised Learning With Autoencoders


Title	Generalization Bounds For Unsupervised and Semi-Supervised Learning With Autoencoders
Authors	Baruch Epstein, Ron Meir
Abstract	Autoencoders are widely used for unsupervised learning and as a regularization scheme in semi-supervised learning. However, theoretical understanding of their generalization properties and of the manner in which they can assist supervised learning has been lacking. We utilize recent advances in the theory of deep learning generalization, together with a novel reconstruction loss, to provide generalization bounds for autoencoders. To the best of our knowledge, this is the first such bound. We further show that, under appropriate assumptions, an autoencoder with good generalization properties can improve any semi-supervised learning scheme. We support our theoretical results with empirical demonstrations.
Tasks
Published	2019-02-04
URL	http://arxiv.org/abs/1902.01449v1
PDF	http://arxiv.org/pdf/1902.01449v1.pdf
PWC	https://paperswithcode.com/paper/generalization-bounds-for-unsupervised-and
Repo
Framework

Ontologies for the Virtual Materials Marketplace


Title	Ontologies for the Virtual Materials Marketplace
Authors	Martin Thomas Horsch, Silvia Chiacchiera, Michael A. Seaton, Ilian T. Todorov, Karel Šindelka, Martin Lísal, Barbara Andreon, Esteban Bayro Kaiser, Gabriele Mogni, Gerhard Goldbeck, Ralf Kunze, Georg Summer, Andreas Fiseni, Hauke Brüning, Peter Schiffels, Welchy Leite Cavalcanti
Abstract	The Virtual Materials Marketplace (VIMMP) project, which develops an open platform for providing and accessing services related to materials modelling, is presented with a focus on its ontology development and data technology aspects. Within VIMMP, a system of marketplace-level ontologies is developed to characterize services, models, and interactions between users; the European Materials and Modelling Ontology (EMMO) is employed as a top-level ontology. The ontologies are used to annotate data that are stored in the ZONTAL Space component of VIMMP and to support the ingest and retrieval of data and metadata at the VIMMP marketplace frontend.
Tasks
Published	2019-12-03
URL	https://arxiv.org/abs/1912.01519v2
PDF	https://arxiv.org/pdf/1912.01519v2.pdf
PWC	https://paperswithcode.com/paper/ontologies-for-the-virtual-materials
Repo
Framework