July 27, 2019

2779 words 14 mins read

Paper Group ANR 539

Experimental Analysis of Design Elements of Scalarizing Functions-based Multiobjective Evolutionary Algorithms. Phylogenetic Convolutional Neural Networks in Metagenomics. Towards a Visual Privacy Advisor: Understanding and Predicting Privacy Risks in Images. Bayesian Compressive Sensing Using Normal Product Priors. Multitask training with unlabele …

Experimental Analysis of Design Elements of Scalarizing Functions-based Multiobjective Evolutionary Algorithms


Title	Experimental Analysis of Design Elements of Scalarizing Functions-based Multiobjective Evolutionary Algorithms
Authors	Mansoureh Aghabeig, Andrzej Jaszkiewicz
Abstract	In this paper we systematically study the importance, i.e., the influence on performance, of the main design elements that differentiate scalarizing functions-based multiobjective evolutionary algorithms (MOEAs). This class of MOEAs includes Multiobjecitve Genetic Local Search (MOGLS) and Multiobjective Evolutionary Algorithm Based on Decomposition (MOEA/D) and proved to be very successful in multiple computational experiments and practical applications. The two algorithms share the same common structure and differ only in two main aspects. Using three different multiobjective combinatorial optimization problems, i.e., the multiobjective symmetric traveling salesperson problem, the traveling salesperson problem with profits, and the multiobjective set covering problem, we show that the main differentiating design element is the mechanism for parent selection, while the selection of weight vectors, either random or uniformly distributed, is practically negligible if the number of uniform weight vectors is sufficiently large.
Tasks	Combinatorial Optimization
Published	2017-03-28
URL	http://arxiv.org/abs/1703.09469v1
PDF	http://arxiv.org/pdf/1703.09469v1.pdf
PWC	https://paperswithcode.com/paper/experimental-analysis-of-design-elements-of
Repo
Framework

Phylogenetic Convolutional Neural Networks in Metagenomics


Title	Phylogenetic Convolutional Neural Networks in Metagenomics
Authors	Diego Fioravanti, Ylenia Giarratano, Valerio Maggio, Claudio Agostinelli, Marco Chierici, Giuseppe Jurman, Cesare Furlanello
Abstract	Background: Convolutional Neural Networks can be effectively used only when data are endowed with an intrinsic concept of neighbourhood in the input space, as is the case of pixels in images. We introduce here Ph-CNN, a novel deep learning architecture for the classification of metagenomics data based on the Convolutional Neural Networks, with the patristic distance defined on the phylogenetic tree being used as the proximity measure. The patristic distance between variables is used together with a sparsified version of MultiDimensional Scaling to embed the phylogenetic tree in a Euclidean space. Results: Ph-CNN is tested with a domain adaptation approach on synthetic data and on a metagenomics collection of gut microbiota of 38 healthy subjects and 222 Inflammatory Bowel Disease patients, divided in 6 subclasses. Classification performance is promising when compared to classical algorithms like Support Vector Machines and Random Forest and a baseline fully connected neural network, e.g. the Multi-Layer Perceptron. Conclusion: Ph-CNN represents a novel deep learning approach for the classification of metagenomics data. Operatively, the algorithm has been implemented as a custom Keras layer taking care of passing to the following convolutional layer not only the data but also the ranked list of neighbourhood of each sample, thus mimicking the case of image data, transparently to the user. Keywords: Metagenomics; Deep learning; Convolutional Neural Networks; Phylogenetic trees
Tasks	Domain Adaptation
Published	2017-09-06
URL	http://arxiv.org/abs/1709.02268v1
PDF	http://arxiv.org/pdf/1709.02268v1.pdf
PWC	https://paperswithcode.com/paper/phylogenetic-convolutional-neural-networks-in
Repo
Framework

Towards a Visual Privacy Advisor: Understanding and Predicting Privacy Risks in Images


Title	Towards a Visual Privacy Advisor: Understanding and Predicting Privacy Risks in Images
Authors	Tribhuvanesh Orekondy, Bernt Schiele, Mario Fritz
Abstract	With an increasing number of users sharing information online, privacy implications entailing such actions are a major concern. For explicit content, such as user profile or GPS data, devices (e.g. mobile phones) as well as web services (e.g. Facebook) offer to set privacy settings in order to enforce the users’ privacy preferences. We propose the first approach that extends this concept to image content in the spirit of a Visual Privacy Advisor. First, we categorize personal information in images into 68 image attributes and collect a dataset, which allows us to train models that predict such information directly from images. Second, we run a user study to understand the privacy preferences of different users w.r.t. such attributes. Third, we propose models that predict user specific privacy score from images in order to enforce the users’ privacy preferences. Our model is trained to predict the user specific privacy risk and even outperforms the judgment of the users, who often fail to follow their own privacy preferences on image data.
Tasks
Published	2017-03-30
URL	http://arxiv.org/abs/1703.10660v2
PDF	http://arxiv.org/pdf/1703.10660v2.pdf
PWC	https://paperswithcode.com/paper/towards-a-visual-privacy-advisor
Repo
Framework

Bayesian Compressive Sensing Using Normal Product Priors


Title	Bayesian Compressive Sensing Using Normal Product Priors
Authors	Zhou Zhou, Kaihui Liu, Jun Fang
Abstract	In this paper, we introduce a new sparsity-promoting prior, namely, the “normal product” prior, and develop an efficient algorithm for sparse signal recovery under the Bayesian framework. The normal product distribution is the distribution of a product of two normally distributed variables with zero means and possibly different variances. Like other sparsity-encouraging distributions such as the Student’s $t$-distribution, the normal product distribution has a sharp peak at origin, which makes it a suitable prior to encourage sparse solutions. A two-stage normal product-based hierarchical model is proposed. We resort to the variational Bayesian (VB) method to perform the inference. Simulations are conducted to illustrate the effectiveness of our proposed algorithm as compared with other state-of-the-art compressed sensing algorithms.
Tasks	Compressive Sensing
Published	2017-08-24
URL	http://arxiv.org/abs/1708.07450v1
PDF	http://arxiv.org/pdf/1708.07450v1.pdf
PWC	https://paperswithcode.com/paper/bayesian-compressive-sensing-using-normal
Repo
Framework

Multitask training with unlabeled data for end-to-end sign language fingerspelling recognition


Title	Multitask training with unlabeled data for end-to-end sign language fingerspelling recognition
Authors	Bowen Shi, Karen Livescu
Abstract	We address the problem of automatic American Sign Language fingerspelling recognition from video. Prior work has largely relied on frame-level labels, hand-crafted features, or other constraints, and has been hampered by the scarcity of data for this task. We introduce a model for fingerspelling recognition that addresses these issues. The model consists of an auto-encoder-based feature extractor and an attention-based neural encoder-decoder, which are trained jointly. The model receives a sequence of image frames and outputs the fingerspelled word, without relying on any frame-level training labels or hand-crafted features. In addition, the auto-encoder subcomponent makes it possible to leverage unlabeled data to improve the feature learning. The model achieves 11.6% and 4.4% absolute letter accuracy improvement respectively in signer-independent and signer-adapted fingerspelling recognition over previous approaches that required frame-level training labels.
Tasks
Published	2017-10-09
URL	http://arxiv.org/abs/1710.03255v2
PDF	http://arxiv.org/pdf/1710.03255v2.pdf
PWC	https://paperswithcode.com/paper/multitask-training-with-unlabeled-data-for
Repo
Framework

Detection of Face using Viola Jones and Recognition using Back Propagation Neural Network


Title	Detection of Face using Viola Jones and Recognition using Back Propagation Neural Network
Authors	Smriti Tikoo, Nitin Malik
Abstract	Detection and recognition of the facial images of people is an intricate problem which has garnered much attention during recent years due to its ever increasing applications in numerous fields. It continues to pose a challenge in finding a robust solution to it. Its scope extends to catering the security, commercial and law enforcement applications. Research for moreover a decade on this subject has brought about remarkable development with the modus operandi like human computer interaction, biometric analysis and content based coding of images, videos and surveillance. A trivial task for brain but cumbersome to be imitated artificially. The commonalities in faces does pose a problem on various grounds but features such as skin color, gender differentiate a person from the other. In this paper the facial detection has been carried out using Viola-Jones algorithm and recognition of face has been done using Back Propagation Neural Network (BPNN).
Tasks
Published	2017-01-28
URL	http://arxiv.org/abs/1701.08257v1
PDF	http://arxiv.org/pdf/1701.08257v1.pdf
PWC	https://paperswithcode.com/paper/detection-of-face-using-viola-jones-and
Repo
Framework

Flexible statistical inference for mechanistic models of neural dynamics


Title	Flexible statistical inference for mechanistic models of neural dynamics
Authors	Jan-Matthis Lueckmann, Pedro J. Goncalves, Giacomo Bassetto, Kaan Öcal, Marcel Nonnenmacher, Jakob H. Macke
Abstract	Mechanistic models of single-neuron dynamics have been extensively studied in computational neuroscience. However, identifying which models can quantitatively reproduce empirically measured data has been challenging. We propose to overcome this limitation by using likelihood-free inference approaches (also known as Approximate Bayesian Computation, ABC) to perform full Bayesian inference on single-neuron models. Our approach builds on recent advances in ABC by learning a neural network which maps features of the observed data to the posterior distribution over parameters. We learn a Bayesian mixture-density network approximating the posterior over multiple rounds of adaptively chosen simulations. Furthermore, we propose an efficient approach for handling missing features and parameter settings for which the simulator fails, as well as a strategy for automatically learning relevant features using recurrent neural networks. On synthetic data, our approach efficiently estimates posterior distributions and recovers ground-truth parameters. On in-vitro recordings of membrane voltages, we recover multivariate posteriors over biophysical parameters, which yield model-predicted voltage traces that accurately match empirical data. Our approach will enable neuroscientists to perform Bayesian inference on complex neuron models without having to design model-specific algorithms, closing the gap between mechanistic and statistical approaches to single-neuron modelling.
Tasks	Bayesian Inference
Published	2017-11-06
URL	http://arxiv.org/abs/1711.01861v1
PDF	http://arxiv.org/pdf/1711.01861v1.pdf
PWC	https://paperswithcode.com/paper/flexible-statistical-inference-for
Repo
Framework

Selective Classification for Deep Neural Networks


Title	Selective Classification for Deep Neural Networks
Authors	Yonatan Geifman, Ran El-Yaniv
Abstract	Selective classification techniques (also known as reject option) have not yet been considered in the context of deep neural networks (DNNs). These techniques can potentially significantly improve DNNs prediction performance by trading-off coverage. In this paper we propose a method to construct a selective classifier given a trained neural network. Our method allows a user to set a desired risk level. At test time, the classifier rejects instances as needed, to grant the desired risk (with high probability). Empirical results over CIFAR and ImageNet convincingly demonstrate the viability of our method, which opens up possibilities to operate DNNs in mission-critical applications. For example, using our method an unprecedented 2% error in top-5 ImageNet classification can be guaranteed with probability 99.9%, and almost 60% test coverage.
Tasks
Published	2017-05-23
URL	http://arxiv.org/abs/1705.08500v2
PDF	http://arxiv.org/pdf/1705.08500v2.pdf
PWC	https://paperswithcode.com/paper/selective-classification-for-deep-neural
Repo
Framework

Accelerating GMM-based patch priors for image restoration: Three ingredients for a 100$\times$ speed-up


Title	Accelerating GMM-based patch priors for image restoration: Three ingredients for a 100$\times$ speed-up
Authors	Shibin Parameswaran, Charles-Alban Deledalle, Loïc Denis, Truong Q. Nguyen
Abstract	Image restoration methods aim to recover the underlying clean image from corrupted observations. The Expected Patch Log-likelihood (EPLL) algorithm is a powerful image restoration method that uses a Gaussian mixture model (GMM) prior on the patches of natural images. Although it is very effective for restoring images, its high runtime complexity makes EPLL ill-suited for most practical applications. In this paper, we propose three approximations to the original EPLL algorithm. The resulting algorithm, which we call the fast-EPLL (FEPLL), attains a dramatic speed-up of two orders of magnitude over EPLL while incurring a negligible drop in the restored image quality (less than 0.5 dB). We demonstrate the efficacy and versatility of our algorithm on a number of inverse problems such as denoising, deblurring, super-resolution, inpainting and devignetting. To the best of our knowledge, FEPLL is the first algorithm that can competitively restore a 512x512 pixel image in under 0.5s for all the degradations mentioned above without specialized code optimizations such as CPU parallelization or GPU implementation.
Tasks	Deblurring, Denoising, Image Restoration, Super-Resolution
Published	2017-10-23
URL	http://arxiv.org/abs/1710.08124v1
PDF	http://arxiv.org/pdf/1710.08124v1.pdf
PWC	https://paperswithcode.com/paper/accelerating-gmm-based-patch-priors-for-image
Repo
Framework

Spelling Correction as a Foreign Language


Title	Spelling Correction as a Foreign Language
Authors	Yingbo Zhou, Utkarsh Porwal, Roberto Konow
Abstract	In this paper, we reformulated the spell correction problem as a machine translation task under the encoder-decoder framework. This reformulation enabled us to use a single model for solving the problem that is traditionally formulated as learning a language model and an error model. This model employs multi-layer recurrent neural networks as an encoder and a decoder. We demonstrate the effectiveness of this model using an internal dataset, where the training data is automatically obtained from user logs. The model offers competitive performance as compared to the state of the art methods but does not require any feature engineering nor hand tuning between models.
Tasks	Feature Engineering, Language Modelling, Machine Translation, Spelling Correction
Published	2017-05-21
URL	https://arxiv.org/abs/1705.07371v2
PDF	https://arxiv.org/pdf/1705.07371v2.pdf
PWC	https://paperswithcode.com/paper/spelling-correction-as-a-foreign-language
Repo
Framework

Unsupervised Histopathology Image Synthesis


Title	Unsupervised Histopathology Image Synthesis
Authors	Le Hou, Ayush Agarwal, Dimitris Samaras, Tahsin M. Kurc, Rajarsi R. Gupta, Joel H. Saltz
Abstract	Hematoxylin and Eosin stained histopathology image analysis is essential for the diagnosis and study of complicated diseases such as cancer. Existing state-of-the-art approaches demand extensive amount of supervised training data from trained pathologists. In this work we synthesize in an unsupervised manner, large histopathology image datasets, suitable for supervised training tasks. We propose a unified pipeline that: a) generates a set of initial synthetic histopathology images with paired information about the nuclei such as segmentation masks; b) refines the initial synthetic images through a Generative Adversarial Network (GAN) to reference styles; c) trains a task-specific CNN and boosts the performance of the task-specific CNN with on-the-fly generated adversarial examples. Our main contribution is that the synthetic images are not only realistic, but also representative (in reference styles) and relatively challenging for training task-specific CNNs. We test our method for nucleus segmentation using images from four cancer types. When no supervised data exists for a cancer type, our method without supervision cost significantly outperforms supervised methods which perform across-cancer generalization. Even when supervised data exists for all cancer types, our approach without supervision cost performs better than supervised methods.
Tasks	Image Generation
Published	2017-12-13
URL	http://arxiv.org/abs/1712.05021v1
PDF	http://arxiv.org/pdf/1712.05021v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-histopathology-image-synthesis
Repo
Framework

Together We Know How to Achieve: An Epistemic Logic of Know-How


Title	Together We Know How to Achieve: An Epistemic Logic of Know-How
Authors	Pavel Naumov, Jia Tao
Abstract	The existence of a coalition strategy to achieve a goal does not necessarily mean that the coalition has enough information to know how to follow the strategy. Neither does it mean that the coalition knows that such a strategy exists. The article studies an interplay between the distributed knowledge, coalition strategies, and coalition “know-how” strategies. The main technical result is a sound and complete trimodal logical system that describes the properties of this interplay.
Tasks
Published	2017-05-25
URL	http://arxiv.org/abs/1705.09349v2
PDF	http://arxiv.org/pdf/1705.09349v2.pdf
PWC	https://paperswithcode.com/paper/together-we-know-how-to-achieve-an-epistemic
Repo
Framework

A multi-layer network based on Sparse Ternary Codes for universal vector compression


Title	A multi-layer network based on Sparse Ternary Codes for universal vector compression
Authors	Sohrab Ferdowsi, Slava Voloshynovskiy, Dimche Kostadinov
Abstract	We present the multi-layer extension of the Sparse Ternary Codes (STC) for fast similarity search where we focus on the reconstruction of the database vectors from the ternary codes. To consider the trade-offs between the compactness of the STC and the quality of the reconstructed vectors, we study the rate-distortion behavior of these codes under different setups. We show that a single-layer code cannot achieve satisfactory results at high rates. Therefore, we extend the concept of STC to multiple layers and design the ML-STC, a codebook-free system that successively refines the reconstruction of the residuals of previous layers. While the ML-STC keeps the sparse ternary structure of the single-layer STC and hence is suitable for fast similarity search in large-scale databases, we show its superior rate-distortion performance on both model-based synthetic data and public large-scale databases, as compared to several binary hashing methods.
Tasks
Published	2017-10-31
URL	http://arxiv.org/abs/1710.11510v1
PDF	http://arxiv.org/pdf/1710.11510v1.pdf
PWC	https://paperswithcode.com/paper/a-multi-layer-network-based-on-sparse-ternary
Repo
Framework

Lock-Free Parallel Perceptron for Graph-based Dependency Parsing


Title	Lock-Free Parallel Perceptron for Graph-based Dependency Parsing
Authors	Xu Sun, Shuming Ma
Abstract	Dependency parsing is an important NLP task. A popular approach for dependency parsing is structured perceptron. Still, graph-based dependency parsing has the time complexity of $O(n^3)$, and it suffers from slow training. To deal with this problem, we propose a parallel algorithm called parallel perceptron. The parallel algorithm can make full use of a multi-core computer which saves a lot of training time. Based on experiments we observe that dependency parsing with parallel perceptron can achieve 8-fold faster training speed than traditional structured perceptron methods when using 10 threads, and with no loss at all in accuracy.
Tasks	Dependency Parsing
Published	2017-03-02
URL	http://arxiv.org/abs/1703.00782v1
PDF	http://arxiv.org/pdf/1703.00782v1.pdf
PWC	https://paperswithcode.com/paper/lock-free-parallel-perceptron-for-graph-based
Repo
Framework

An Improved Neural Segmentation Method Based on U-NET


Title	An Improved Neural Segmentation Method Based on U-NET
Authors	Chenyang Xu, Mengxin Li
Abstract	Neural segmentation has a great impact on the smooth implementation of local anesthesia surgery. At present, the network for the segmentation includes U-NET [1] and SegNet [2]. U-NET network has short training time and less training parameters, but the depth is not deep enough. SegNet network has deeper structure, but it needs longer training time, and more training samples. In this paper, we propose an improved U-NET neural network for the segmentation. This network deepens the original structure through importing residual network. Compared with U-NET and SegNet, the improved U-NET network has fewer training parameters, shorter training time and get a great improvement in segmentation effect. The improved U-NET network structure has a good application scene in neural segmentation.
Tasks
Published	2017-08-16
URL	http://arxiv.org/abs/1708.04747v1
PDF	http://arxiv.org/pdf/1708.04747v1.pdf
PWC	https://paperswithcode.com/paper/an-improved-neural-segmentation-method-based
Repo
Framework