July 29, 2019

2904 words 14 mins read

Paper Group AWR 80

Supervised Saliency Map Driven Segmentation of the Lesions in Dermoscopic Images. Variational Sequential Monte Carlo. A Two-Step Disentanglement Method. Sentence Simplification with Deep Reinforcement Learning. “Parallel Training Considered Harmful?": Comparing series-parallel and parallel feedforward network training. Improved Text Language Identi …

Supervised Saliency Map Driven Segmentation of the Lesions in Dermoscopic Images


Title	Supervised Saliency Map Driven Segmentation of the Lesions in Dermoscopic Images
Authors	Mostafa Jahanifar, Neda Zamani Tajeddin, Babak Mohammadzadeh Asl, Ali Gooya
Abstract	Lesion segmentation is the first step in most automatic melanoma recognition systems. Deficiencies and difficulties in dermoscopic images such as color inconstancy, hair occlusion, dark corners and color charts make lesion segmentation an intricate task. In order to detect the lesion in the presence of these problems, we propose a supervised saliency detection method tailored for dermoscopic images based on the discriminative regional feature integration (DRFI). DRFI method incorporates multi-level segmentation, regional contrast, property, background descriptors, and a random forest regressor to create saliency scores for each region in the image. In our improved saliency detection method, mDRFI, we have added some new features to regional property descriptors. Also, in order to achieve more robust regional background descriptors, a thresholding algorithm is proposed to obtain a new pseudo-background region. Findings reveal that mDRFI is superior to DRFI in detecting the lesion as the salient object in dermoscopic images. The proposed overall lesion segmentation framework uses detected saliency map to construct an initial mask of the lesion through thresholding and post-processing operations. The initial mask is then evolving in a level set framework to fit better on the lesion’s boundaries. The results of evaluation tests on three public datasets show that our proposed segmentation method outperforms the other conventional state-of-the-art segmentation algorithms and its performance is comparable with most recent approaches that are based on deep convolutional neural networks.
Tasks	Lesion Segmentation, Saliency Detection
Published	2017-02-28
URL	http://arxiv.org/abs/1703.00087v4
PDF	http://arxiv.org/pdf/1703.00087v4.pdf
PWC	https://paperswithcode.com/paper/supervised-saliency-map-driven-segmentation
Repo	https://github.com/mjahanifar/mDRFI_matlab
Framework	none

Variational Sequential Monte Carlo


Title	Variational Sequential Monte Carlo
Authors	Christian A. Naesseth, Scott W. Linderman, Rajesh Ranganath, David M. Blei
Abstract	Many recent advances in large scale probabilistic inference rely on variational methods. The success of variational approaches depends on (i) formulating a flexible parametric family of distributions, and (ii) optimizing the parameters to find the member of this family that most closely approximates the exact posterior. In this paper we present a new approximating family of distributions, the variational sequential Monte Carlo (VSMC) family, and show how to optimize it in variational inference. VSMC melds variational inference (VI) and sequential Monte Carlo (SMC), providing practitioners with flexible, accurate, and powerful Bayesian inference. The VSMC family is a variational family that can approximate the posterior arbitrarily well, while still allowing for efficient optimization of its parameters. We demonstrate its utility on state space models, stochastic volatility models for financial data, and deep Markov models of brain neural circuits.
Tasks	Bayesian Inference
Published	2017-05-31
URL	http://arxiv.org/abs/1705.11140v2
PDF	http://arxiv.org/pdf/1705.11140v2.pdf
PWC	https://paperswithcode.com/paper/variational-sequential-monte-carlo
Repo	https://github.com/blei-lab/variational-smc
Framework	none

A Two-Step Disentanglement Method


Title	A Two-Step Disentanglement Method
Authors	Naama Hadad, Lior Wolf, Moni Shahar
Abstract	We address the problem of disentanglement of factors that generate a given data into those that are correlated with the labeling and those that are not. Our solution is simpler than previous solutions and employs adversarial training. First, the part of the data that is correlated with the labels is extracted by training a classifier. Then, the other part is extracted such that it enables the reconstruction of the original data but does not contain label information. The utility of the new method is demonstrated on visual datasets as well as on financial data. Our code is available at https://github.com/naamahadad/A-Two-Step-Disentanglement-Method
Tasks
Published	2017-09-01
URL	https://arxiv.org/abs/1709.00199v2
PDF	https://arxiv.org/pdf/1709.00199v2.pdf
PWC	https://paperswithcode.com/paper/two-step-disentanglement-for-financial-data
Repo	https://github.com/naamahadad/A-Two-Step-Disentanglement-Method
Framework	none

Sentence Simplification with Deep Reinforcement Learning


Title	Sentence Simplification with Deep Reinforcement Learning
Authors	Xingxing Zhang, Mirella Lapata
Abstract	Sentence simplification aims to make sentences easier to read and understand. Most recent approaches draw on insights from machine translation to learn simplification rewrites from monolingual corpora of complex and simple sentences. We address the simplification problem with an encoder-decoder model coupled with a deep reinforcement learning framework. Our model, which we call {\sc Dress} (as shorthand for {\bf D}eep {\bf RE}inforcement {\bf S}entence {\bf S}implification), explores the space of possible simplifications while learning to optimize a reward function that encourages outputs which are simple, fluent, and preserve the meaning of the input. Experiments on three datasets demonstrate that our model outperforms competitive simplification systems.
Tasks	Machine Translation, Sentence Compression
Published	2017-03-31
URL	http://arxiv.org/abs/1703.10931v2
PDF	http://arxiv.org/pdf/1703.10931v2.pdf
PWC	https://paperswithcode.com/paper/sentence-simplification-with-deep
Repo	https://github.com/XingxingZhang/dress
Framework	torch

“Parallel Training Considered Harmful?": Comparing series-parallel and parallel feedforward network training


Title	“Parallel Training Considered Harmful?": Comparing series-parallel and parallel feedforward network training
Authors	Antônio H. Ribeiro, Luis A. Aguirre
Abstract	Neural network models for dynamic systems can be trained either in parallel or in series-parallel configurations. Influenced by early arguments, several papers justify the choice of series-parallel rather than parallel configuration claiming it has a lower computational cost, better stability properties during training and provides more accurate results. Other published results, on the other hand, defend parallel training as being more robust and capable of yielding more accu- rate long-term predictions. The main contribution of this paper is to present a study comparing both methods under the same unified framework. We focus on three aspects: i) robustness of the estimation in the presence of noise; ii) computational cost; and, iii) convergence. A unifying mathematical framework and simulation studies show situations where each training method provides better validation results, being parallel training better in what is believed to be more realistic scenarios. An example using measured data seems to reinforce such claim. We also show, with a novel complexity analysis and numerical examples, that both methods have similar computational cost, being series series-parallel training, however, more amenable to parallelization. Some informal discussion about stability and convergence properties is presented and explored in the examples.
Tasks
Published	2017-06-21
URL	http://arxiv.org/abs/1706.07119v3
PDF	http://arxiv.org/pdf/1706.07119v3.pdf
PWC	https://paperswithcode.com/paper/parallel-training-considered-harmful
Repo	https://github.com/antonior92/ParallelTrainingNN.jl
Framework	none

Improved Text Language Identification for the South African Languages


Title	Improved Text Language Identification for the South African Languages
Authors	Bernardt Duvenhage, Mfundo Ntini, Phala Ramonyai
Abstract	Virtual assistants and text chatbots have recently been gaining popularity. Given the short message nature of text-based chat interactions, the language identification systems of these bots might only have 15 or 20 characters to make a prediction. However, accurate text language identification is important, especially in the early stages of many multilingual natural language processing pipelines. This paper investigates the use of a naive Bayes classifier, to accurately predict the language family that a piece of text belongs to, combined with a lexicon based classifier to distinguish the specific South African language that the text is written in. This approach leads to a 31% reduction in the language detection error. In the spirit of reproducible research the training and testing datasets as well as the code are published on github. Hopefully it will be useful to create a text language identification shared task for South African languages.
Tasks	Language Identification
Published	2017-11-01
URL	http://arxiv.org/abs/1711.00247v1
PDF	http://arxiv.org/pdf/1711.00247v1.pdf
PWC	https://paperswithcode.com/paper/improved-text-language-identification-for-the
Repo	https://github.com/praekelt/feersum-lid-shared-task
Framework	none

A General-Purpose Tagger with Convolutional Neural Networks


Title	A General-Purpose Tagger with Convolutional Neural Networks
Authors	Xiang Yu, Agnieszka Faleńska, Ngoc Thang Vu
Abstract	We present a general-purpose tagger based on convolutional neural networks (CNN), used for both composing word vectors and encoding context information. The CNN tagger is robust across different tagging tasks: without task-specific tuning of hyper-parameters, it achieves state-of-the-art results in part-of-speech tagging, morphological tagging and supertagging. The CNN tagger is also robust against the out-of-vocabulary problem, it performs well on artificially unnormalized texts.
Tasks	Morphological Tagging, Part-Of-Speech Tagging
Published	2017-06-06
URL	http://arxiv.org/abs/1706.01723v1
PDF	http://arxiv.org/pdf/1706.01723v1.pdf
PWC	https://paperswithcode.com/paper/a-general-purpose-tagger-with-convolutional
Repo	https://github.com/EggplantElf/sclem2017-tagger
Framework	none

Situation Recognition with Graph Neural Networks


Title	Situation Recognition with Graph Neural Networks
Authors	Ruiyu Li, Makarand Tapaswi, Renjie Liao, Jiaya Jia, Raquel Urtasun, Sanja Fidler
Abstract	We address the problem of recognizing situations in images. Given an image, the task is to predict the most salient verb (action), and fill its semantic roles such as who is performing the action, what is the source and target of the action, etc. Different verbs have different roles (e.g. attacking has weapon), and each role can take on many possible values (nouns). We propose a model based on Graph Neural Networks that allows us to efficiently capture joint dependencies between roles using neural networks defined on a graph. Experiments with different graph connectivities show that our approach that propagates information between roles significantly outperforms existing work, as well as multiple baselines. We obtain roughly 3-5% improvement over previous work in predicting the full situation. We also provide a thorough qualitative analysis of our model and influence of different roles in the verbs.
Tasks
Published	2017-08-14
URL	http://arxiv.org/abs/1708.04320v1
PDF	http://arxiv.org/pdf/1708.04320v1.pdf
PWC	https://paperswithcode.com/paper/situation-recognition-with-graph-neural
Repo	https://github.com/thilinicooray/context-aware-reasoning-for-sr
Framework	pytorch

Open Evaluation Tool for Layout Analysis of Document Images


Title	Open Evaluation Tool for Layout Analysis of Document Images
Authors	Michele Alberti, Manuel Bouillon, Rolf Ingold, Marcus Liwicki
Abstract	This paper presents an open tool for standardizing the evaluation process of the layout analysis task of document images at pixel level. We introduce a new evaluation tool that is both available as a standalone Java application and as a RESTful web service. This evaluation tool is free and open-source in order to be a common tool that anyone can use and contribute to. It aims at providing as many metrics as possible to investigate layout analysis predictions, and also provide an easy way of visualizing the results. This tool evaluates document segmentation at pixel level, and support multi-labeled pixel ground truth. Finally, this tool has been successfully used for the ICDAR2017 competition on Layout Analysis for Challenging Medieval Manuscripts.
Tasks
Published	2017-11-23
URL	http://arxiv.org/abs/1712.01656v1
PDF	http://arxiv.org/pdf/1712.01656v1.pdf
PWC	https://paperswithcode.com/paper/open-evaluation-tool-for-layout-analysis-of
Repo	https://github.com/DIVA-DIA/LayoutAnalysisEvaluator
Framework	none

Learning Proximal Operators: Using Denoising Networks for Regularizing Inverse Imaging Problems


Title	Learning Proximal Operators: Using Denoising Networks for Regularizing Inverse Imaging Problems
Authors	Tim Meinhardt, Michael Moeller, Caner Hazirbas, Daniel Cremers
Abstract	While variational methods have been among the most powerful tools for solving linear inverse problems in imaging, deep (convolutional) neural networks have recently taken the lead in many challenging benchmarks. A remaining drawback of deep learning approaches is their requirement for an expensive retraining whenever the specific problem, the noise level, noise type, or desired measure of fidelity changes. On the contrary, variational methods have a plug-and-play nature as they usually consist of separate data fidelity and regularization terms. In this paper we study the possibility of replacing the proximal operator of the regularization used in many convex energy minimization algorithms by a denoising neural network. The latter therefore serves as an implicit natural image prior, while the data term can still be chosen independently. Using a fixed denoising neural network in exemplary problems of image deconvolution with different blur kernels and image demosaicking, we obtain state-of-the-art reconstruction results. These indicate the high generalizability of our approach and a reduction of the need for problem-specific training. Additionally, we discuss novel results on the analysis of possible optimization algorithms to incorporate the network into, as well as the choices of algorithm parameters and their relation to the noise level the neural network is trained on.
Tasks	Demosaicking, Denoising, Image Deconvolution
Published	2017-04-11
URL	http://arxiv.org/abs/1704.03488v2
PDF	http://arxiv.org/pdf/1704.03488v2.pdf
PWC	https://paperswithcode.com/paper/learning-proximal-operators-using-denoising
Repo	https://github.com/tum-vision/learn_prox_ops
Framework	tf

Learning a Single Convolutional Super-Resolution Network for Multiple Degradations


Title	Learning a Single Convolutional Super-Resolution Network for Multiple Degradations
Authors	Kai Zhang, Wangmeng Zuo, Lei Zhang
Abstract	Recent years have witnessed the unprecedented success of deep convolutional neural networks (CNNs) in single image super-resolution (SISR). However, existing CNN-based SISR methods mostly assume that a low-resolution (LR) image is bicubicly downsampled from a high-resolution (HR) image, thus inevitably giving rise to poor performance when the true degradation does not follow this assumption. Moreover, they lack scalability in learning a single model to non-blindly deal with multiple degradations. To address these issues, we propose a general framework with dimensionality stretching strategy that enables a single convolutional super-resolution network to take two key factors of the SISR degradation process, i.e., blur kernel and noise level, as input. Consequently, the super-resolver can handle multiple and even spatially variant degradations, which significantly improves the practicability. Extensive experimental results on synthetic and real LR images show that the proposed convolutional super-resolution network not only can produce favorable results on multiple degradations but also is computationally efficient, providing a highly effective and scalable solution to practical SISR applications.
Tasks	Image Super-Resolution, Super-Resolution
Published	2017-12-17
URL	http://arxiv.org/abs/1712.06116v2
PDF	http://arxiv.org/pdf/1712.06116v2.pdf
PWC	https://paperswithcode.com/paper/learning-a-single-convolutional-super
Repo	https://github.com/cszn/SRMD
Framework	pytorch

DAC-h3: A Proactive Robot Cognitive Architecture to Acquire and Express Knowledge About the World and the Self


Title	DAC-h3: A Proactive Robot Cognitive Architecture to Acquire and Express Knowledge About the World and the Self
Authors	Clément Moulin-Frier, Tobias Fischer, Maxime Petit, Grégoire Pointeau, Jordi-Ysard Puigbo, Ugo Pattacini, Sock Ching Low, Daniel Camilleri, Phuong Nguyen, Matej Hoffmann, Hyung Jin Chang, Martina Zambelli, Anne-Laure Mealier, Andreas Damianou, Giorgio Metta, Tony J. Prescott, Yiannis Demiris, Peter Ford Dominey, Paul F. M. J. Verschure
Abstract	This paper introduces a cognitive architecture for a humanoid robot to engage in a proactive, mixed-initiative exploration and manipulation of its environment, where the initiative can originate from both the human and the robot. The framework, based on a biologically-grounded theory of the brain and mind, integrates a reactive interaction engine, a number of state-of-the-art perceptual and motor learning algorithms, as well as planning abilities and an autobiographical memory. The architecture as a whole drives the robot behavior to solve the symbol grounding problem, acquire language capabilities, execute goal-oriented behavior, and express a verbal narrative of its own experience in the world. We validate our approach in human-robot interaction experiments with the iCub humanoid robot, showing that the proposed cognitive architecture can be applied in real time within a realistic scenario and that it can be used with naive users.
Tasks
Published	2017-06-12
URL	http://arxiv.org/abs/1706.03661v2
PDF	http://arxiv.org/pdf/1706.03661v2.pdf
PWC	https://paperswithcode.com/paper/dac-h3-a-proactive-robot-cognitive
Repo	https://github.com/robotology/wysiwyd
Framework	none

Fusing Multiple Multiband Images


Title	Fusing Multiple Multiband Images
Authors	Reza Arablouei
Abstract	We consider the problem of fusing an arbitrary number of multiband, i.e., panchromatic, multispectral, or hyperspectral, images belonging to the same scene. We use the well-known forward observation and linear mixture models with Gaussian perturbations to formulate the maximum-likelihood estimator of the endmember abundance matrix of the fused image. We calculate the Fisher information matrix for this estimator and examine the conditions for the uniqueness of the estimator. We use a vector total-variation penalty term together with nonnegativity and sum-to-one constraints on the endmember abundances to regularize the derived maximum-likelihood estimation problem. The regularization facilitates exploiting the prior knowledge that natural images are mostly composed of piecewise smooth regions with limited abrupt changes, i.e., edges, as well as coping with potential ill-posedness of the fusion problem. We solve the resultant convex optimization problem using the alternating direction method of multipliers. We utilize the circular convolution theorem in conjunction with the fast Fourier transform to alleviate the computational complexity of the proposed algorithm. Experiments with multiband images constructed from real hyperspectral datasets reveal the superior performance of the proposed algorithm in comparison with the state-of-the-art algorithms, which need to be used in tandem to fuse more than two multiband images.
Tasks	Infrared And Visible Image Fusion
Published	2017-12-13
URL	http://arxiv.org/abs/1712.04575v2
PDF	http://arxiv.org/pdf/1712.04575v2.pdf
PWC	https://paperswithcode.com/paper/fusing-multiple-multiband-images
Repo	https://github.com/Reza219/Multiple-multiband-image-fusion
Framework	none

Learning to Generate Samples from Noise through Infusion Training


Title	Learning to Generate Samples from Noise through Infusion Training
Authors	Florian Bordes, Sina Honari, Pascal Vincent
Abstract	In this work, we investigate a novel training procedure to learn a generative model as the transition operator of a Markov chain, such that, when applied repeatedly on an unstructured random noise sample, it will denoise it into a sample that matches the target distribution from the training set. The novel training procedure to learn this progressive denoising operation involves sampling from a slightly different chain than the model chain used for generation in the absence of a denoising target. In the training chain we infuse information from the training target example that we would like the chains to reach with a high probability. The thus learned transition operator is able to produce quality and varied samples in a small number of steps. Experiments show competitive results compared to the samples generated with a basic Generative Adversarial Net
Tasks	Denoising
Published	2017-03-20
URL	http://arxiv.org/abs/1703.06975v1
PDF	http://arxiv.org/pdf/1703.06975v1.pdf
PWC	https://paperswithcode.com/paper/learning-to-generate-samples-from-noise
Repo	https://github.com/bordesf/Infusion
Framework	none

Neural networks for topology optimization


Title	Neural networks for topology optimization
Authors	Ivan Sosnovik, Ivan Oseledets
Abstract	In this research, we propose a deep learning based approach for speeding up the topology optimization methods. The problem we seek to solve is the layout problem. The main novelty of this work is to state the problem as an image segmentation task. We leverage the power of deep learning methods as the efficient pixel-wise image labeling technique to perform the topology optimization. We introduce convolutional encoder-decoder architecture and the overall approach of solving the above-described problem with high performance. The conducted experiments demonstrate the significant acceleration of the optimization process. The proposed approach has excellent generalization properties. We demonstrate the ability of the application of the proposed model to other problems. The successful results, as well as the drawbacks of the current method, are discussed.
Tasks	Semantic Segmentation
Published	2017-09-27
URL	http://arxiv.org/abs/1709.09578v1
PDF	http://arxiv.org/pdf/1709.09578v1.pdf
PWC	https://paperswithcode.com/paper/neural-networks-for-topology-optimization
Repo	https://github.com/ISosnovik/top
Framework	none