October 19, 2019

3029 words 15 mins read

Paper Group ANR 199

Learning Deep Models for Face Anti-Spoofing: Binary or Auxiliary Supervision. Event Forecasting with Pattern Markov Chains. Using Known Information to Accelerate HyperParameters Optimization Based on SMBO. Hardware-Efficient Guided Image Filtering For Multi-Label Problem. Secure Federated Transfer Learning. Learning Discriminative Representation wi …

Learning Deep Models for Face Anti-Spoofing: Binary or Auxiliary Supervision


Title	Learning Deep Models for Face Anti-Spoofing: Binary or Auxiliary Supervision
Authors	Yaojie Liu, Amin Jourabloo, Xiaoming Liu
Abstract	Face anti-spoofing is the crucial step to prevent face recognition systems from a security breach. Previous deep learning approaches formulate face anti-spoofing as a binary classification problem. Many of them struggle to grasp adequate spoofing cues and generalize poorly. In this paper, we argue the importance of auxiliary supervision to guide the learning toward discriminative and generalizable cues. A CNN-RNN model is learned to estimate the face depth with pixel-wise supervision, and to estimate rPPG signals with sequence-wise supervision. Then we fuse the estimated depth and rPPG to distinguish live vs. spoof faces. In addition, we introduce a new face anti-spoofing database that covers a large range of illumination, subject, and pose variations. Experimental results show that our model achieves the state-of-the-art performance on both intra-database and cross-database testing.
Tasks	Face Anti-Spoofing, Face Recognition
Published	2018-03-29
URL	http://arxiv.org/abs/1803.11097v1
PDF	http://arxiv.org/pdf/1803.11097v1.pdf
PWC	https://paperswithcode.com/paper/learning-deep-models-for-face-anti-spoofing
Repo
Framework

Event Forecasting with Pattern Markov Chains


Title	Event Forecasting with Pattern Markov Chains
Authors	Elias Alevizos, Alexander Artikis, Georgios Paliouras
Abstract	We present a system for online probabilistic event forecasting. We assume that a user is interested in detecting and forecasting event patterns, given in the form of regular expressions. Our system can consume streams of events and forecast when the pattern is expected to be fully matched. As more events are consumed, the system revises its forecasts to reflect possible changes in the state of the pattern. The framework of Pattern Markov Chains is used in order to learn a probabilistic model for the pattern, with which forecasts with guaranteed precision may be produced, in the form of intervals within which a full match is expected. Experimental results from real-world datasets are shown and the quality of the produced forecasts is explored, using both precision scores and two other metrics: spread, which refers to the “focusing resolution” of a forecast (interval length), and distance, which captures how early a forecast is reported.
Tasks
Published	2018-04-27
URL	http://arxiv.org/abs/1804.10388v1
PDF	http://arxiv.org/pdf/1804.10388v1.pdf
PWC	https://paperswithcode.com/paper/event-forecasting-with-pattern-markov-chains
Repo
Framework

Using Known Information to Accelerate HyperParameters Optimization Based on SMBO


Title	Using Known Information to Accelerate HyperParameters Optimization Based on SMBO
Authors	Cheng Daning, Zhang Hanping, Xia Fen, Li Shigang, Zhang Yunquan
Abstract	Automl is the key technology for machine learning problem. Current state of art hyperparameter optimization methods are based on traditional black-box optimization methods like SMBO (SMAC, TPE). The objective function of black-box optimization is non-smooth, or time-consuming to evaluate, or in some way noisy. Recent years, many researchers offered the work about the properties of hyperparameters. However, traditional hyperparameter optimization methods do not take those information into consideration. In this paper, we use gradient information and machine learning model analysis information to accelerate traditional hyperparameter optimization methods SMBO. In our L2 norm experiments, our method yielded state-of-the-art performance, and in many cases outperformed the previous best configuration approach.
Tasks	AutoML, Hyperparameter Optimization
Published	2018-11-08
URL	https://arxiv.org/abs/1811.03322v2
PDF	https://arxiv.org/pdf/1811.03322v2.pdf
PWC	https://paperswithcode.com/paper/using-known-information-to-accelerate
Repo
Framework

Hardware-Efficient Guided Image Filtering For Multi-Label Problem


Title	Hardware-Efficient Guided Image Filtering For Multi-Label Problem
Authors	Longquan Dai, Mengke Yuan, Zechao Li, Xiaopeng Zhang, Jinhui Tang
Abstract	The Guided Filter (GF) is well-known for its linear complexity. However, when filtering an image with an n-channel guidance, GF needs to invert an n x n matrix for each pixel. To the best of our knowledge existing matrix inverse algorithms are inefficient on current hardwares. This shortcoming limits applications of multichannel guidance in computation intensive system such as multi-label system. We need a new GF-like filter that can perform fast multichannel image guided filtering. Since the optimal linear complexity of GF cannot be minimized further, the only way thus is to bring all potentialities of current parallel computing hardwares into full play. In this paper we propose a hardware-efficient Guided Filter (HGF), which solves the efficiency problem of multichannel guided image filtering and yields competent results when applying it to multi-label problems with synthesized polynomial multichannel guidance. Specifically, in order to boost the filtering performance, HGF takes a new matrix inverse algorithm which only involves two hardware-efficient operations: element-wise arithmetic calculations and box filtering. In order to break the linear model restriction, HGF synthesizes a polynomial multichannel guidance to introduce nonlinearity. Benefiting from our polynomial guidance and hardware-efficient matrix inverse algorithm, HGF not only is more sensitive to the underlying structure of guidance but also achieves the fastest computing speed. Due to these merits, HGF obtains state-of-the-art results in terms of accuracy and efficiency in the computation intensive multi-label
Tasks
Published	2018-02-28
URL	http://arxiv.org/abs/1803.00005v1
PDF	http://arxiv.org/pdf/1803.00005v1.pdf
PWC	https://paperswithcode.com/paper/hardware-efficient-guided-image-filtering-for
Repo
Framework

Secure Federated Transfer Learning


Title	Secure Federated Transfer Learning
Authors	Yang Liu, Tianjian Chen, Qiang Yang
Abstract	Machine learning relies on the availability of a vast amount of data for training. However, in reality, most data are scattered across different organizations and cannot be easily integrated under many legal and practical constraints. In this paper, we introduce a new technique and framework, known as federated transfer learning (FTL), to improve statistical models under a data federation. The federation allows knowledge to be shared without compromising user privacy, and enables complimentary knowledge to be transferred in the network. As a result, a target-domain party can build more flexible and powerful models by leveraging rich labels from a source-domain party. A secure transfer cross validation approach is also proposed to guard the FTL performance under the federation. The framework requires minimal modifications to the existing model structure and provides the same level of accuracy as the non-privacy-preserving approach. This framework is very flexible and can be effectively adapted to various secure multi-party machine learning tasks.
Tasks	Transfer Learning
Published	2018-12-08
URL	http://arxiv.org/abs/1812.03337v1
PDF	http://arxiv.org/pdf/1812.03337v1.pdf
PWC	https://paperswithcode.com/paper/secure-federated-transfer-learning
Repo
Framework

Learning Discriminative Representation with Signed Laplacian Restricted Boltzmann Machine


Title	Learning Discriminative Representation with Signed Laplacian Restricted Boltzmann Machine
Authors	Dongdong Chen, Jiancheng Lv, Mike E. Davies
Abstract	We investigate the potential of a restricted Boltzmann Machine (RBM) for discriminative representation learning. By imposing the class information preservation constraints on the hidden layer of the RBM, we propose a Signed Laplacian Restricted Boltzmann Machine (SLRBM) for supervised discriminative representation learning. The model utilizes the label information and preserves the global data locality of data points simultaneously. Experimental results on the benchmark data set show the effectiveness of our method.
Tasks	Representation Learning
Published	2018-08-28
URL	http://arxiv.org/abs/1808.09389v1
PDF	http://arxiv.org/pdf/1808.09389v1.pdf
PWC	https://paperswithcode.com/paper/learning-discriminative-representation-with
Repo
Framework

Payoff Control in the Iterated Prisoner’s Dilemma


Title	Payoff Control in the Iterated Prisoner’s Dilemma
Authors	Dong Hao, Kai Li, Tao Zhou
Abstract	Repeated game has long been the touchstone model for agents’ long-run relationships. Previous results suggest that it is particularly difficult for a repeated game player to exert an autocratic control on the payoffs since they are jointly determined by all participants. This work discovers that the scale of a player’s capability to unilaterally influence the payoffs may have been much underestimated. Under the conventional iterated prisoner’s dilemma, we develop a general framework for controlling the feasible region where the players’ payoff pairs lie. A control strategy player is able to confine the payoff pairs in her objective region, as long as this region has feasible linear boundaries. With this framework, many well-known existing strategies can be categorized and various new strategies with nice properties can be further identified. We show that the control strategies perform well either in a tournament or against a human-like opponent.
Tasks
Published	2018-07-17
URL	http://arxiv.org/abs/1807.06666v1
PDF	http://arxiv.org/pdf/1807.06666v1.pdf
PWC	https://paperswithcode.com/paper/payoff-control-in-the-iterated-prisoners
Repo
Framework

Large-scale Interactive Recommendation with Tree-structured Policy Gradient


Title	Large-scale Interactive Recommendation with Tree-structured Policy Gradient
Authors	Haokun Chen, Xinyi Dai, Han Cai, Weinan Zhang, Xuejian Wang, Ruiming Tang, Yuzhou Zhang, Yong Yu
Abstract	Reinforcement learning (RL) has recently been introduced to interactive recommender systems (IRS) because of its nature of learning from dynamic interactions and planning for long-run performance. As IRS is always with thousands of items to recommend (i.e., thousands of actions), most existing RL-based methods, however, fail to handle such a large discrete action space problem and thus become inefficient. The existing work that tries to deal with the large discrete action space problem by utilizing the deep deterministic policy gradient framework suffers from the inconsistency between the continuous action representation (the output of the actor network) and the real discrete action. To avoid such inconsistency and achieve high efficiency and recommendation effectiveness, in this paper, we propose a Tree-structured Policy Gradient Recommendation (TPGR) framework, where a balanced hierarchical clustering tree is built over the items and picking an item is formulated as seeking a path from the root to a certain leaf of the tree. Extensive experiments on carefully-designed environments based on two real-world datasets demonstrate that our model provides superior recommendation performance and significant efficiency improvement over state-of-the-art methods.
Tasks	Recommendation Systems
Published	2018-11-14
URL	http://arxiv.org/abs/1811.05869v1
PDF	http://arxiv.org/pdf/1811.05869v1.pdf
PWC	https://paperswithcode.com/paper/large-scale-interactive-recommendation-with
Repo
Framework

Annotation-Free and One-Shot Learning for Instance Segmentation of Homogeneous Object Clusters


Title	Annotation-Free and One-Shot Learning for Instance Segmentation of Homogeneous Object Clusters
Authors	Zheng Wu, Ruiheng Chang, Jiaxu Ma, Cewu Lu, Chi-Keung Tang
Abstract	We propose a novel approach for instance segmen- tation given an image of homogeneous object clus- ter (HOC). Our learning approach is one-shot be- cause a single video of an object instance is cap- tured and it requires no human annotation. Our in- tuition is that images of homogeneous objects can be effectively synthesized based on structure and illumination priors derived from real images. A novel solver is proposed that iteratively maximizes our structured likelihood to generate realistic im- ages of HOC. Illumination transformation scheme is applied to make the real and synthetic images share the same illumination condition. Extensive experiments and comparisons are performed to ver- ify our method. We build a dataset consisting of pixel-level annotated images of HOC. The dataset and code will be published with the paper.
Tasks	Instance Segmentation, One-Shot Learning, Semantic Segmentation
Published	2018-02-01
URL	http://arxiv.org/abs/1802.00383v2
PDF	http://arxiv.org/pdf/1802.00383v2.pdf
PWC	https://paperswithcode.com/paper/annotation-free-and-one-shot-learning-for
Repo
Framework

SymmSLIC: Symmetry Aware Superpixel Segmentation and its Applications


Title	SymmSLIC: Symmetry Aware Superpixel Segmentation and its Applications
Authors	Rajendra Nagar, Shanmuganathan Raman
Abstract	Over-segmentation of an image into superpixels has become a useful tool for solving various problems in image processing and computer vision. Reflection symmetry is quite prevalent in both natural and man-made objects and is an essential cue in understanding and grouping the objects in natural scenes. Existing algorithms for estimating superpixels do not preserve the reflection symmetry of an object which leads to different sizes and shapes of superpixels across the symmetry axis. In this work, we propose an algorithm to over-segment an image through the propagation of reflection symmetry evident at the pixel level to superpixel boundaries. In order to achieve this goal, we first find the reflection symmetry in the image and represent it by a set of pairs of pixels which are mirror reflections of each other. We partition the image into superpixels while preserving this reflection symmetry through an iterative algorithm. We compare the proposed method with state-of-the-art superpixel generation methods and show the effectiveness in preserving the size and shape of superpixel boundaries across the reflection symmetry axes. We also present two applications, symmetry axes detection and unsupervised symmetric object segmentation, to illustrate the effectiveness of the proposed approach.
Tasks	Semantic Segmentation
Published	2018-05-23
URL	http://arxiv.org/abs/1805.09232v2
PDF	http://arxiv.org/pdf/1805.09232v2.pdf
PWC	https://paperswithcode.com/paper/symmslic-symmetry-aware-superpixel
Repo
Framework

SMPLR: Deep SMPL reverse for 3D human pose and shape recovery


Title	SMPLR: Deep SMPL reverse for 3D human pose and shape recovery
Authors	Meysam Madadi, Hugo Bertiche, Sergio Escalera
Abstract	Current state-of-the-art in 3D human pose and shape recovery relies on deep neural networks and statistical morphable body models, such as the Skinned Multi-Person Linear model (SMPL). However, regardless of the advantages of having both body pose and shape, SMPL-based solutions have shown difficulties to predict 3D bodies accurately. This is mainly due to the unconstrained nature of SMPL, which may generate unrealistic body meshes. Because of this, regression of SMPL parameters is a difficult task, often addressed with complex regularization terms. In this paper we propose to embed SMPL within a deep model to accurately estimate 3D pose and shape from a still RGB image. We use CNN-based 3D joint predictions as an intermediate representation to regress SMPL pose and shape parameters. Later, 3D joints are reconstructed again in the SMPL output. This module can be seen as an autoencoder where the encoder is a deep neural network and the decoder is SMPL model. We refer to this as SMPL reverse (SMPLR). By implementing SMPLR as an encoder-decoder we avoid the need of complex constraints on pose and shape. Furthermore, given that in-the-wild datasets usually lack accurate 3D annotations, it is desirable to lift 2D joints to 3D without pairing 3D annotations with RGB images. Therefore, we also propose a denoising autoencoder (DAE) module between CNN and SMPLR, able to lift 2D joints to 3D and partially recover from structured error. We evaluate our method on SURREAL and Human3.6M datasets, showing improvement over SMPL-based state-of-the-art alternatives by about 4 and 25 millimeters, respectively.
Tasks	Denoising
Published	2018-12-27
URL	https://arxiv.org/abs/1812.10766v2
PDF	https://arxiv.org/pdf/1812.10766v2.pdf
PWC	https://paperswithcode.com/paper/smplr-deep-smpl-reverse-for-3d-human-pose-and
Repo
Framework

Computational Complexity Analysis of Genetic Programming


Title	Computational Complexity Analysis of Genetic Programming
Authors	Andrei Lissovoi, Pietro S. Oliveto
Abstract	Genetic programming (GP) is an evolutionary computation technique to solve problems in an automated, domain-independent way. Rather than identifying the optimum of a function as in more traditional evolutionary optimization, the aim of GP is to evolve computer programs with a given functionality. While many GP applications have produced human competitive results, the theoretical understanding of what problem characteristics and algorithm properties allow GP to be effective is comparatively limited. Compared with traditional evolutionary algorithms for function optimization, GP applications are further complicated by two additional factors: the variable-length representation of candidate programs, and the difficulty of evaluating their quality efficiently. Such difficulties considerably impact the runtime analysis of GP, where space complexity also comes into play. As a result, initial complexity analyses of GP have focused on restricted settings such as the evolution of trees with given structures or the estimation of solution quality using only a small polynomial number of input/output examples. However, the first computational complexity analyses of GP for evolving proper functions with defined input/output behavior have recently appeared. In this chapter, we present an overview of the state of the art.
Tasks
Published	2018-11-11
URL	https://arxiv.org/abs/1811.04465v2
PDF	https://arxiv.org/pdf/1811.04465v2.pdf
PWC	https://paperswithcode.com/paper/computational-complexity-analysis-of-genetic
Repo
Framework

Intracranial Error Detection via Deep Learning


Title	Intracranial Error Detection via Deep Learning
Authors	Martin Völker, Jiří Hammer, Robin T. Schirrmeister, Joos Behncke, Lukas D. J. Fiederer, Andreas Schulze-Bonhage, Petr Marusič, Wolfram Burgard, Tonio Ball
Abstract	Deep learning techniques have revolutionized the field of machine learning and were recently successfully applied to various classification problems in noninvasive electroencephalography (EEG). However, these methods were so far only rarely evaluated for use in intracranial EEG. We employed convolutional neural networks (CNNs) to classify and characterize the error-related brain response as measured in 24 intracranial EEG recordings. Decoding accuracies of CNNs were significantly higher than those of a regularized linear discriminant analysis. Using time-resolved deep decoding, it was possible to classify errors in various regions in the human brain, and further to decode errors over 200 ms before the actual erroneous button press, e.g., in the precentral gyrus. Moreover, deeper networks performed better than shallower networks in distinguishing correct from error trials in all-channel decoding. In single recordings, up to 100 % decoding accuracy was achieved. Visualization of the networks’ learned features indicated that multivariate decoding on an ensemble of channels yields related, albeit non-redundant information compared to single-channel decoding. In summary, here we show the usefulness of deep learning for both intracranial error decoding and mapping of the spatio-temporal structure of the human error processing network.
Tasks	EEG
Published	2018-05-04
URL	http://arxiv.org/abs/1805.01667v3
PDF	http://arxiv.org/pdf/1805.01667v3.pdf
PWC	https://paperswithcode.com/paper/intracranial-error-detection-via-deep
Repo
Framework

Bayesian Neural Networks


Title	Bayesian Neural Networks
Authors	Vikram Mullachery, Aniruddh Khera, Amir Husain
Abstract	This paper describes and discusses Bayesian Neural Network (BNN). The paper showcases a few different applications of them for classification and regression problems. BNNs are comprised of a Probabilistic Model and a Neural Network. The intent of such a design is to combine the strengths of Neural Networks and Stochastic modeling. Neural Networks exhibit continuous function approximator capabilities. Stochastic models allow direct specification of a model with known interaction between parameters to generate data. During the prediction phase, stochastic models generate a complete posterior distribution and produce probabilistic guarantees on the predictions. Thus BNNs are a unique combination of neural network and stochastic models with the stochastic model forming the core of this integration. BNNs can then produce probabilistic guarantees on it’s predictions and also generate the distribution of parameters that it has learnt from the observations. That means, in the parameter space, one can deduce the nature and shape of the neural network’s learnt parameters. These two characteristics makes them highly attractive to theoreticians as well as practitioners. Recently there has been a lot of activity in this area, with the advent of numerous probabilistic programming libraries such as: PyMC3, Edward, Stan etc. Further this area is rapidly gaining ground as a standard machine learning approach for numerous problems
Tasks	Probabilistic Programming
Published	2018-01-23
URL	http://arxiv.org/abs/1801.07710v2
PDF	http://arxiv.org/pdf/1801.07710v2.pdf
PWC	https://paperswithcode.com/paper/bayesian-neural-networks
Repo
Framework

Imaginary Kinematics


Title	Imaginary Kinematics
Authors	Sabina Marchetti, Alessandro Antonucci
Abstract	We introduce a novel class of adjustment rules for a collection of beliefs. This is an extension of Lewis’ imaging to absorb probabilistic evidence in generalized settings. Unlike standard tools for belief revision, our proposal may be used when information is inconsistent with an agent’s belief base. We show that the functionals we introduce are based on the imaginary counterpart of probability kinematics for standard belief revision, and prove that, under certain conditions, all standard postulates for belief revision are satisfied.
Tasks
Published	2018-08-01
URL	http://arxiv.org/abs/1808.00329v1
PDF	http://arxiv.org/pdf/1808.00329v1.pdf
PWC	https://paperswithcode.com/paper/imaginary-kinematics
Repo
Framework