October 18, 2019

3462 words 17 mins read

Paper Group ANR 659

Image Inpainting using Block-wise Procedural Training with Annealed Adversarial Counterpart. A geometric characterisation of sensitivity analysis in monomial models. Multi-label Learning Based Deep Transfer Neural Network for Facial Attribute Classification. Dual approach for object tracking based on optical flow and swarm intelligence. Artificial …

Image Inpainting using Block-wise Procedural Training with Annealed Adversarial Counterpart


Title	Image Inpainting using Block-wise Procedural Training with Annealed Adversarial Counterpart
Authors	Chao Yang, Yuhang Song, Xiaofeng Liu, Qingming Tang, C. -C. Jay Kuo
Abstract	Recent advances in deep generative models have shown promising potential in image inpanting, which refers to the task of predicting missing pixel values of an incomplete image using the known context. However, existing methods can be slow or generate unsatisfying results with easily detectable flaws. In addition, there is often perceivable discontinuity near the holes and require further post-processing to blend the results. We present a new approach to address the difficulty of training a very deep generative model to synthesize high-quality photo-realistic inpainting. Our model uses conditional generative adversarial networks (conditional GANs) as the backbone, and we introduce a novel block-wise procedural training scheme to stabilize the training while we increase the network depth. We also propose a new strategy called adversarial loss annealing to reduce the artifacts. We further describe several losses specifically designed for inpainting and show their effectiveness. Extensive experiments and user-study show that our approach outperforms existing methods in several tasks such as inpainting, face completion and image harmonization. Finally, we show our framework can be easily used as a tool for interactive guided inpainting, demonstrating its practical value to solve common real-world challenges.
Tasks	Facial Inpainting, Image Inpainting
Published	2018-03-23
URL	http://arxiv.org/abs/1803.08943v2
PDF	http://arxiv.org/pdf/1803.08943v2.pdf
PWC	https://paperswithcode.com/paper/image-inpainting-using-block-wise-procedural
Repo
Framework

A geometric characterisation of sensitivity analysis in monomial models


Title	A geometric characterisation of sensitivity analysis in monomial models
Authors	Manuele Leonelli, Eva Riccomagno
Abstract	Sensitivity analysis in probabilistic discrete graphical models is usually conducted by varying one probability value at a time and observing how this affects output probabilities of interest. When one probability is varied then others are proportionally covaried to respect the sum-to-one condition of probability laws. The choice of proportional covariation is justified by a variety of optimality conditions, under which the original and the varied distributions are as close as possible under different measures of closeness. For variations of more than one parameter at a time proportional covariation is justified in some special cases only. In this work, for the large class of discrete statistical models entertaining a regular monomial parametrisation, we demonstrate the optimality of newly defined proportional multi-way schemes with respect to an optimality criterion based on the notion of I-divergence. We demonstrate that there are varying parameters choices for which proportional covariation is not optimal and identify the sub-family of model distributions where the distance between the original distribution and the one where probabilities are covaried proportionally is minimum. This is shown by adopting a new formal, geometric characterization of sensitivity analysis in monomial models, which include a wide array of probabilistic graphical models. We also demonstrate the optimality of proportional covariation for multi-way analyses in Naive Bayes classifiers.
Tasks
Published	2018-12-18
URL	http://arxiv.org/abs/1901.02058v1
PDF	http://arxiv.org/pdf/1901.02058v1.pdf
PWC	https://paperswithcode.com/paper/a-geometric-characterisation-of-sensitivity
Repo
Framework

Multi-label Learning Based Deep Transfer Neural Network for Facial Attribute Classification


Title	Multi-label Learning Based Deep Transfer Neural Network for Facial Attribute Classification
Authors	Ni Zhuang, Yan Yan, Si Chen, Hanzi Wang, Chunhua Shen
Abstract	Deep Neural Network (DNN) has recently achieved outstanding performance in a variety of computer vision tasks, including facial attribute classification. The great success of classifying facial attributes with DNN often relies on a massive amount of labelled data. However, in real-world applications, labelled data are only provided for some commonly used attributes (such as age, gender); whereas, unlabelled data are available for other attributes (such as attraction, hairline). To address the above problem, we propose a novel deep transfer neural network method based on multi-label learning for facial attribute classification, termed FMTNet, which consists of three sub-networks: the Face detection Network (FNet), the Multi-label learning Network (MNet) and the Transfer learning Network (TNet). Firstly, based on the Faster Region-based Convolutional Neural Network (Faster R-CNN), FNet is fine-tuned for face detection. Then, MNet is fine-tuned by FNet to predict multiple attributes with labelled data, where an effective loss weight scheme is developed to explicitly exploit the correlation between facial attributes based on attribute grouping. Finally, based on MNet, TNet is trained by taking advantage of unsupervised domain adaptation for unlabelled facial attribute classification. The three sub-networks are tightly coupled to perform effective facial attribute classification. A distinguishing characteristic of the proposed FMTNet method is that the three sub-networks (FNet, MNet and TNet) are constructed in a similar network structure. Extensive experimental results on challenging face datasets demonstrate the effectiveness of our proposed method compared with several state-of-the-art methods.
Tasks	Domain Adaptation, Face Detection, Facial Attribute Classification, Multi-Label Learning, Transfer Learning, Unsupervised Domain Adaptation
Published	2018-05-03
URL	http://arxiv.org/abs/1805.01282v1
PDF	http://arxiv.org/pdf/1805.01282v1.pdf
PWC	https://paperswithcode.com/paper/multi-label-learning-based-deep-transfer
Repo
Framework

Dual approach for object tracking based on optical flow and swarm intelligence


Title	Dual approach for object tracking based on optical flow and swarm intelligence
Authors	Rajesh Misra, Kumar S. Ray
Abstract	In Computer Vision,object tracking is a very old and complex problem.Though there are several existing algorithms for object tracking, still there are several challenges remain to be solved. For instance, variation of illumination of light, noise, occlusion, sudden start and stop of moving object, shading etc,make the object tracking a complex problem not only for dynamic background but also for static background. In this paper we propose a dual approach for object tracking based on optical flow and swarm Intelligence.The optical flow based KLT(Kanade-Lucas-Tomasi) tracker, tracks the dominant points of the target object from first frame to last frame of a video sequence;whereas swarm Intelligence based PSO (Particle Swarm Optimization) tracker simultaneously tracks the boundary information of the target object from second frame to last frame of the same video sequence.This dual function of tracking makes the trackers very much robust with respect to the above stated problems. The flexibility of our approach is that it can be successfully applicable in variable background as well as static background.We compare the performance of the proposed dual tracking algorithm with several benchmark datasets and obtain very competitive results in general and in most of the cases we obtained superior results using dual tracking algorithm. We also compare the performance of the proposed dual tracker with some existing PSO based algorithms for tracking and achieved better results.
Tasks	Object Tracking, Optical Flow Estimation
Published	2018-08-15
URL	http://arxiv.org/abs/1808.08186v1
PDF	http://arxiv.org/pdf/1808.08186v1.pdf
PWC	https://paperswithcode.com/paper/dual-approach-for-object-tracking-based-on
Repo
Framework

Artificial neural network based modelling approach for municipal solid waste gasification in a fluidized bed reactor


Title	Artificial neural network based modelling approach for municipal solid waste gasification in a fluidized bed reactor
Authors	Daya Shankar Pandey, Saptarshi Das, Indranil Pan, James J. Leahy, Witold Kwapinski
Abstract	In this paper, multi-layer feed forward neural networks are used to predict the lower heating value of gas (LHV), lower heating value of gasification products including tars and entrained char (LHVp) and syngas yield during gasification of municipal solid waste (MSW) during gasification in a fluidized bed reactor. These artificial neural networks (ANNs) with different architectures are trained using the Levenberg-Marquardt (LM) back-propagation algorithm and a cross validation is also performed to ensure that the results generalise to other unseen datasets. A rigorous study is carried out on optimally choosing the number of hidden layers, number of neurons in the hidden layer and activation function in a network using multiple Monte Carlo runs. Nine input and three output parameters are used to train and test various neural network architectures in both multiple output and single output prediction paradigms using the available experimental datasets. The model selection procedure is carried out to ascertain the best network architecture in terms of predictive accuracy. The simulation results show that the ANN based methodology is a viable alternative which can be used to predict the performance of a fluidized bed gasifier.
Tasks	Model Selection
Published	2018-02-05
URL	http://arxiv.org/abs/1803.04813v1
PDF	http://arxiv.org/pdf/1803.04813v1.pdf
PWC	https://paperswithcode.com/paper/artificial-neural-network-based-modelling
Repo
Framework

Multi-Cohort Intelligence Algorithm: An Intra- and Inter-group Learning Behavior based Socio-inspired Optimization Methodology


Title	Multi-Cohort Intelligence Algorithm: An Intra- and Inter-group Learning Behavior based Socio-inspired Optimization Methodology
Authors	Apoorva S Shastri, Anand J Kulkarni
Abstract	A Multi-Cohort Intelligence (Multi-CI) metaheuristic algorithm in emerging socio-inspired optimization domain is proposed. The algorithm implements intra-group and inter-group learning mechanisms. It focusses on the interaction amongst different cohorts. The performance of the algorithm is validated by solving 75 unconstrained test problems with dimensions up to 30. The solutions were comparing with several recent algorithms such as Particle Swarm Optimization, Covariance Matrix Adaptation Evolution Strategy, Artificial Bee Colony, Self-adaptive differential evolution algorithm, Comprehensive Learning Particle Swarm Optimization, Backtracking Search Optimization Algorithm and Ideology Algorithm. The Wilcoxon signed rank test was carried out for the statistical analysis and verification of the performance. The proposed Multi-CI outperformed these algorithms in terms of the solution quality including objective function value and computational cost, i.e. computational time and functional evaluations. The prominent feature of the Multi-CI algorithm along with the limitations are discussed as well. In addition, an illustrative example is also solved and every detail is provided.
Tasks
Published	2018-05-01
URL	http://arxiv.org/abs/1806.01681v1
PDF	http://arxiv.org/pdf/1806.01681v1.pdf
PWC	https://paperswithcode.com/paper/multi-cohort-intelligence-algorithm-an-intra
Repo
Framework

Optimization by Pairwise Linkage Detection, Incremental Linkage Set, and Restricted / Back Mixing: DSMGA-II


Title	Optimization by Pairwise Linkage Detection, Incremental Linkage Set, and Restricted / Back Mixing: DSMGA-II
Authors	Shih-Huan Hsu, Tian-Li Yu
Abstract	This paper proposes a new evolutionary algorithm, called DSMGA-II, to efficiently solve optimization problems via exploiting problem substructures. The proposed algorithm adopts pairwise linkage detection and stores the information in the form of dependency structure matrix (DSM). A new linkage model, called the incremental linkage set, is then constructed by using the DSM. Inspired by the idea of optimal mixing, the restricted mixing and the back mixing are proposed. The former aims at efficient exploration under certain constrains. The latter aims at exploitation by refining the DSM so as to reduce unnecessary evaluations. Experimental results show that DSMGA-II outperforms LT-GOMEA and hBOA in terms of number of function evaluations on the concatenated/folded/cyclic trap problems, NK-landscape problems with various degrees of overlapping, 2D Ising spin-glass problems, and MAX-SAT. The investigation of performance comparison with P3 is also included.
Tasks	Efficient Exploration
Published	2018-07-31
URL	http://arxiv.org/abs/1807.11669v1
PDF	http://arxiv.org/pdf/1807.11669v1.pdf
PWC	https://paperswithcode.com/paper/optimization-by-pairwise-linkage-detection
Repo
Framework

Polynomial-based rotation invariant features


Title	Polynomial-based rotation invariant features
Authors	Jarek Duda
Abstract	One of basic difficulties of machine learning is handling unknown rotations of objects, for example in image recognition. A related problem is evaluation of similarity of shapes, for example of two chemical molecules, for which direct approach requires costly pairwise rotation alignment and comparison. Rotation invariants are useful tools for such purposes, allowing to extract features describing shape up to rotation, which can be used for example to search for similar rotated patterns, or fast evaluation of similarity of shapes e.g. for virtual screening, or machine learning including features directly describing shape. A standard approach are rotationally invariant cylindrical or spherical harmonics, which can be seen as based on polynomials on sphere, however, they provide very few invariants - only one per degree of polynomial. There will be discussed a general approach to construct arbitrarily large sets of rotation invariants of polynomials, for degree $D$ in $\mathbb{R}^n$ up to $O(n^D)$ independent invariants instead of $O(D)$ offered by standard approaches, possibly also a complete set: providing not only necessary, but also sufficient condition for differing only by rotation (and reflectional symmetry).
Tasks
Published	2018-01-03
URL	http://arxiv.org/abs/1801.01058v1
PDF	http://arxiv.org/pdf/1801.01058v1.pdf
PWC	https://paperswithcode.com/paper/polynomial-based-rotation-invariant-features
Repo
Framework

Learning to Interrupt: A Hierarchical Deep Reinforcement Learning Framework for Efficient Exploration


Title	Learning to Interrupt: A Hierarchical Deep Reinforcement Learning Framework for Efficient Exploration
Authors	Tingguang Li, Jin Pan, Delong Zhu, Max Q. -H. Meng
Abstract	To achieve scenario intelligence, humans must transfer knowledge to robots by developing goal-oriented algorithms, which are sometimes insensitive to dynamically changing environments. While deep reinforcement learning achieves significant success recently, it is still extremely difficult to be deployed in real robots directly. In this paper, we propose a hybrid structure named Option-Interruption in which human knowledge is embedded into a hierarchical reinforcement learning framework. Our architecture has two key components: options, represented by existing human-designed methods, can significantly speed up the training process and interruption mechanism, based on learnable termination functions, enables our system to quickly respond to the external environment. To implement this architecture, we derive a set of update rules based on policy gradient methods and present a complete training process. In the experiment part, our method is evaluated in Four-room navigation and exploration task, which shows the efficiency and flexibility of our framework.
Tasks	Efficient Exploration, Hierarchical Reinforcement Learning, Policy Gradient Methods
Published	2018-07-30
URL	http://arxiv.org/abs/1807.11150v1
PDF	http://arxiv.org/pdf/1807.11150v1.pdf
PWC	https://paperswithcode.com/paper/learning-to-interrupt-a-hierarchical-deep
Repo
Framework

X-GANs: Image Reconstruction Made Easy for Extreme Cases


Title	X-GANs: Image Reconstruction Made Easy for Extreme Cases
Authors	Longfei Liu, Sheng Li, Yisong Chen, Guoping Wang
Abstract	Image reconstruction including image restoration and denoising is a challenging problem in the field of image computing. We present a new method, called X-GANs, for reconstruction of arbitrary corrupted resource based on a variant of conditional generative adversarial networks (conditional GANs). In our method, a novel generator and multi-scale discriminators are proposed, as well as the combined adversarial losses, which integrate a VGG perceptual loss, an adversarial perceptual loss, and an elaborate corresponding point loss together based on the analysis of image feature. Our conditional GANs have enabled a variety of applications in image reconstruction, including image denoising, image restoration from quite a sparse sampling, image inpainting, image recovery from the severely polluted block or even color-noise dominated images, which are extreme cases and haven’t been addressed in the status quo. We have significantly improved the accuracy and quality of image reconstruction. Extensive perceptual experiments on datasets ranging from human faces to natural scenes demonstrate that images reconstructed by the presented approach are considerably more realistic than alternative work. Our method can also be extended to handle high-ratio image compression.
Tasks	Denoising, Image Compression, Image Denoising, Image Inpainting, Image Reconstruction, Image Restoration
Published	2018-08-06
URL	http://arxiv.org/abs/1808.04432v1
PDF	http://arxiv.org/pdf/1808.04432v1.pdf
PWC	https://paperswithcode.com/paper/x-gans-image-reconstruction-made-easy-for
Repo
Framework

A multi-class structured dictionary learning method using discriminant atom selection


Title	A multi-class structured dictionary learning method using discriminant atom selection
Authors	R. E. Rolón, L. E. Di Persia, R. D. Spies, H. L. Rufiner
Abstract	In the last decade, traditional dictionary learning methods have been successfully applied to various pattern classification tasks. Although these methods produce sparse representations of signals which are robust against distortions and missing data, such representations quite often turn out to be unsuitable if the final objective is signal classification. In order to overcome or at least to attenuate such a weakness, several new methods which incorporate discriminative information into sparse-inducing models have emerged in recent years. In particular, methods for discriminative dictionary learning have shown to be more accurate (in terms of signal classification) than the traditional ones, which are only focused on minimizing the total representation error. In this work, we present both a novel multi-class discriminative measure and an innovative dictionary learning method. For a given dictionary, this new measure, which takes into account not only when a particular atom is used for representing signals coming from a certain class and the magnitude of its corresponding representation coefficient, but also the effect that such an atom has in the total representation error, is capable of efficiently quantifying the degree of discriminability of each one of the atoms. On the other hand, the new dictionary construction method yields dictionaries which are highly suitable for multi-class classification tasks. Our method was tested with a widely used database for handwritten digit recognition and compared with three state-of-the-art classification methods. The results show that our method significantly outperforms the other three achieving good recognition rates and additionally, reducing the computational cost of the classifier.
Tasks	Dictionary Learning, Handwritten Digit Recognition
Published	2018-12-04
URL	http://arxiv.org/abs/1812.01389v1
PDF	http://arxiv.org/pdf/1812.01389v1.pdf
PWC	https://paperswithcode.com/paper/a-multi-class-structured-dictionary-learning
Repo
Framework

Assessing four Neural Networks on Handwritten Digit Recognition Dataset (MNIST)


Title	Assessing four Neural Networks on Handwritten Digit Recognition Dataset (MNIST)
Authors	Feiyang Chen, Nan Chen, Hanyang Mao, Hanlin Hu
Abstract	Although the image recognition has been a research topic for many years, many researchers still have a keen interest in it[1]. In some papers[2][3][4], however, there is a tendency to compare models only on one or two datasets, either because of time restraints or because the model is tailored to a specific task. Accordingly, it is hard to understand how well a certain model generalizes across image recognition field[6]. In this paper, we compare four neural networks on MNIST dataset[5] with different division. Among them, three are Convolutional Neural Networks (CNN)[7], Deep Residual Network (ResNet)[2] and Dense Convolutional Network (DenseNet)[3] respectively, and the other is our improvement on CNN baseline through introducing Capsule Network (CapsNet)[1] to image recognition area. We show that the previous models despite do a quite good job in this area, our retrofitting can be applied to get a better performance. The result obtained by CapsNet is an accuracy rate of 99.75%, and it is the best result published so far. Another inspiring result is that CapsNet only needs a small amount of data to get excellent performance. Finally, we will apply CapsNet’s ability to generalize in other image recognition field in the future.
Tasks	Handwritten Digit Recognition
Published	2018-11-16
URL	https://arxiv.org/abs/1811.08278v2
PDF	https://arxiv.org/pdf/1811.08278v2.pdf
PWC	https://paperswithcode.com/paper/assessing-four-neural-networks-on-handwritten
Repo
Framework

Semi-parametric Image Inpainting


Title	Semi-parametric Image Inpainting
Authors	Karim Iskakov
Abstract	This paper introduces a semi-parametric approach to image inpainting for irregular holes. The nonparametric part consists of an external image database. During test time database is used to retrieve a supplementary image, similar to the input masked picture, and utilize it as auxiliary information for the deep neural network. Further, we propose a novel method of generating masks with irregular holes and present public dataset with such masks. Experiments on CelebA-HQ dataset show that our semi-parametric method yields more realistic results than previous approaches, which is confirmed by the user study.
Tasks	Image Inpainting
Published	2018-07-08
URL	http://arxiv.org/abs/1807.02855v2
PDF	http://arxiv.org/pdf/1807.02855v2.pdf
PWC	https://paperswithcode.com/paper/semi-parametric-image-inpainting
Repo
Framework

Deep Echo State Networks for Diagnosis of Parkinson’s Disease


Title	Deep Echo State Networks for Diagnosis of Parkinson’s Disease
Authors	Claudio Gallicchio, Alessio Micheli, Luca Pedrelli
Abstract	In this paper, we introduce a novel approach for diagnosis of Parkinson’s Disease (PD) based on deep Echo State Networks (ESNs). The identification of PD is performed by analyzing the whole time-series collected from a tablet device during the sketching of spiral tests, without the need for feature extraction and data preprocessing. We evaluated the proposed approach on a public dataset of spiral tests. The results of experimental analysis show that DeepESNs perform significantly better than shallow ESN model. Overall, the proposed approach obtains state-of-the-art results in the identification of PD on this kind of temporal data.
Tasks	Time Series
Published	2018-02-19
URL	http://arxiv.org/abs/1802.06708v1
PDF	http://arxiv.org/pdf/1802.06708v1.pdf
PWC	https://paperswithcode.com/paper/deep-echo-state-networks-for-diagnosis-of
Repo
Framework

A Markov-Switching Model Approach to Heart Sound Segmentation and Classification


Title	A Markov-Switching Model Approach to Heart Sound Segmentation and Classification
Authors	Fuad Noman, Sh-Hussain Salleh, Chee-Ming Ting, S. Balqis Samdin, Hernando Ombao, Hadri Hussain
Abstract	Objective: This paper considers challenges in developing algorithms for accurate segmentation and classification of heart sound (HS) signals. Methods: We propose an approach based on Markov switching autoregressive model (MSAR) to segmenting the HS into four fundamental components each with distinct second-order structure. The identified boundaries are then utilized for automated classification of pathological HS using the continuous density hidden Markov model (CD-HMM). The MSAR formulated in a state-space form is able to capture simultaneously both the continuous hidden dynamics in HS, and the regime switching in the dynamics using a discrete Markov chain. This overcomes the limitation of HMM which uses a single-layer of discrete states. We introduce three schemes for model estimation: (1.) switching Kalman filter (SKF); (2.) refined SKF; (3.) fusion of SKF and the duration-dependent Viterbi algorithm (SKF-Viterbi). Results: The proposed methods are evaluated on Physionet/CinC Challenge 2016 database. The SKF-Viterbi significantly outperforms SKF by improvement of segmentation accuracy from 71% to 84.2%. The use of CD-HMM as a classifier and Mel-frequency cepstral coefficients (MFCCs) as features can characterize not only the normal and abnormal morphologies of HS signals but also morphologies considered as unclassifiable (denoted as X-Factor). It gives classification rates with best gross F1 score of 90.19 (without X-Factor) and 82.7 (with X-Factor) for abnormal beats. Conclusion: The proposed MSAR approach for automatic localization and detection of pathological HS shows a noticeable performance on large HS dataset. Significance: It has potential applications in heart monitoring systems to assist cardiologists for pre-screening of heart pathologies.
Tasks
Published	2018-09-10
URL	http://arxiv.org/abs/1809.03395v1
PDF	http://arxiv.org/pdf/1809.03395v1.pdf
PWC	https://paperswithcode.com/paper/a-markov-switching-model-approach-to-heart
Repo
Framework