July 29, 2019

2915 words 14 mins read

Paper Group ANR 90

Improving Statistical Multimedia Information Retrieval Model by using Ontology. Image Registration Techniques: A Survey. Note on Attacking Object Detectors with Adversarial Stickers. Coordinating Collaborative Chat in Massive Open Online Courses. Bayesian model and dimension reduction for uncertainty propagation: applications in random media. Gener …

Improving Statistical Multimedia Information Retrieval Model by using Ontology


Title	Improving Statistical Multimedia Information Retrieval Model by using Ontology
Authors	Gagandeep Singh Narula, Vishal Jain
Abstract	A typical IR system that delivers and stores information is affected by problem of matching between user query and available content on web. Use of Ontology represents the extracted terms in form of network graph consisting of nodes, edges, index terms etc. The above mentioned IR approaches provide relevance thus satisfying users query. The paper also emphasis on analyzing multimedia documents and performs calculation for extracted terms using different statistical formulas. The proposed model developed reduces semantic gap and satisfies user needs efficiently.
Tasks	Information Retrieval
Published	2017-03-21
URL	http://arxiv.org/abs/1703.07381v1
PDF	http://arxiv.org/pdf/1703.07381v1.pdf
PWC	https://paperswithcode.com/paper/improving-statistical-multimedia-information
Repo
Framework

Image Registration Techniques: A Survey


Title	Image Registration Techniques: A Survey
Authors	Sayan Nag
Abstract	Image Registration is the process of aligning two or more images of the same scene with reference to a particular image. The images are captured from various sensors at different times and at multiple view-points. Thus to get a better picture of any change of a scene or object over a considerable period of time image registration is important. Image registration finds application in medical sciences, remote sensing and in computer vision. This paper presents a detailed review of several approaches which are classified accordingly along with their contributions and drawbacks. The main steps of an image registration procedure are also discussed. Different performance measures are presented that determine the registration quality and accuracy. The scope for the future research are presented as well.
Tasks	Image Registration
Published	2017-11-28
URL	http://arxiv.org/abs/1712.07540v1
PDF	http://arxiv.org/pdf/1712.07540v1.pdf
PWC	https://paperswithcode.com/paper/image-registration-techniques-a-survey
Repo
Framework

Note on Attacking Object Detectors with Adversarial Stickers


Title	Note on Attacking Object Detectors with Adversarial Stickers
Authors	Kevin Eykholt, Ivan Evtimov, Earlence Fernandes, Bo Li, Dawn Song, Tadayoshi Kohno, Amir Rahmati, Atul Prakash, Florian Tramer
Abstract	Deep learning has proven to be a powerful tool for computer vision and has seen widespread adoption for numerous tasks. However, deep learning algorithms are known to be vulnerable to adversarial examples. These adversarial inputs are created such that, when provided to a deep learning algorithm, they are very likely to be mislabeled. This can be problematic when deep learning is used to assist in safety critical decisions. Recent research has shown that classifiers can be attacked by physical adversarial examples under various physical conditions. Given the fact that state-of-the-art objection detection algorithms are harder to be fooled by the same set of adversarial examples, here we show that these detectors can also be attacked by physical adversarial examples. In this note, we briefly show both static and dynamic test results. We design an algorithm that produces physical adversarial inputs, which can fool the YOLO object detector and can also attack Faster-RCNN with relatively high success rate based on transferability. Furthermore, our algorithm can compress the size of the adversarial inputs to stickers that, when attached to the targeted object, result in the detector either mislabeling or not detecting the object a high percentage of the time. This note provides a small set of results. Our upcoming paper will contain a thorough evaluation on other object detectors, and will present the algorithm.
Tasks
Published	2017-12-21
URL	http://arxiv.org/abs/1712.08062v2
PDF	http://arxiv.org/pdf/1712.08062v2.pdf
PWC	https://paperswithcode.com/paper/note-on-attacking-object-detectors-with
Repo
Framework

Coordinating Collaborative Chat in Massive Open Online Courses


Title	Coordinating Collaborative Chat in Massive Open Online Courses
Authors	Gaurav Singh Tomar, Sreecharan Sankaranarayanan, Xu Wang, Carolyn Penstein Rosé
Abstract	An earlier study of a collaborative chat intervention in a Massive Open Online Course (MOOC) identified negative effects on attrition stemming from a requirement for students to be matched with exactly one partner prior to beginning the activity. That study raised questions about how to orchestrate a collaborative chat intervention in a MOOC context in order to provide the benefit of synchronous social engagement without the coordination difficulties. In this paper we present a careful analysis of an intervention designed to overcome coordination difficulties by welcoming students into the chat on a rolling basis as they arrive rather than requiring them to be matched with a partner before beginning. The results suggest the most positive impact when experiencing a chat with exactly one partner rather than more or less. A qualitative analysis of the chat data reveals differential experiences between these configurations that suggests a potential explanation for the effect and raises questions for future research.
Tasks
Published	2017-04-18
URL	http://arxiv.org/abs/1704.05543v1
PDF	http://arxiv.org/pdf/1704.05543v1.pdf
PWC	https://paperswithcode.com/paper/coordinating-collaborative-chat-in-massive
Repo
Framework

Bayesian model and dimension reduction for uncertainty propagation: applications in random media


Title	Bayesian model and dimension reduction for uncertainty propagation: applications in random media
Authors	Constantin Grigo, Phaedon-Stelios Koutsourelakis
Abstract	Well-established methods for the solution of stochastic partial differential equations (SPDEs) typically struggle in problems with high-dimensional inputs/outputs. Such difficulties are only amplified in large-scale applications where even a few tens of full-order model runs are impracticable. While dimensionality reduction can alleviate some of these issues, it is not known which and how many features of the (high-dimensional) input are actually predictive of the (high-dimensional) output. In this paper, we advocate a Bayesian formulation that is capable of performing simultaneous dimension and model-order reduction. It consists of a component that encodes the high-dimensional input into a low-dimensional set of feature functions by employing sparsity-enforcing priors and a decoding component that makes use of the solution of a coarse-grained model in order to reconstruct that of the full-order model. Both components are represented with latent variables in a probabilistic graphical model and are simultaneously trained using Stochastic Variational Inference methods. The model is capable of quantifying the predictive uncertainty due to the information loss that unavoidably takes place in any model-order/dimension reduction as well as the uncertainty arising from finite-sized training datasets. We demonstrate its capabilities in the context of random media where fine-scale fluctuations can give rise to random inputs with tens of thousands of variables. With a few tens of full-order model simulations, the proposed model is capable of identifying salient physical features and produce sharp predictions under different boundary conditions of the full output which itself consists of thousands of components.
Tasks	Dimensionality Reduction
Published	2017-11-07
URL	http://arxiv.org/abs/1711.02475v2
PDF	http://arxiv.org/pdf/1711.02475v2.pdf
PWC	https://paperswithcode.com/paper/bayesian-model-and-dimension-reduction-for
Repo
Framework

Generative Adversarial Trainer: Defense to Adversarial Perturbations with GAN


Title	Generative Adversarial Trainer: Defense to Adversarial Perturbations with GAN
Authors	Hyeungill Lee, Sungyeob Han, Jungwoo Lee
Abstract	We propose a novel technique to make neural network robust to adversarial examples using a generative adversarial network. We alternately train both classifier and generator networks. The generator network generates an adversarial perturbation that can easily fool the classifier network by using a gradient of each image. Simultaneously, the classifier network is trained to classify correctly both original and adversarial images generated by the generator. These procedures help the classifier network to become more robust to adversarial perturbations. Furthermore, our adversarial training framework efficiently reduces overfitting and outperforms other regularization methods such as Dropout. We applied our method to supervised learning for CIFAR datasets, and experimantal results show that our method significantly lowers the generalization error of the network. To the best of our knowledge, this is the first method which uses GAN to improve supervised learning.
Tasks
Published	2017-05-09
URL	http://arxiv.org/abs/1705.03387v2
PDF	http://arxiv.org/pdf/1705.03387v2.pdf
PWC	https://paperswithcode.com/paper/generative-adversarial-trainer-defense-to
Repo
Framework

Building Morphological Chains for Agglutinative Languages


Title	Building Morphological Chains for Agglutinative Languages
Authors	Serkan Ozen, Burcu Can
Abstract	In this paper, we build morphological chains for agglutinative languages by using a log-linear model for the morphological segmentation task. The model is based on the unsupervised morphological segmentation system called MorphoChains. We extend MorphoChains log linear model by expanding the candidate space recursively to cover more split points for agglutinative languages such as Turkish, whereas in the original model candidates are generated by considering only binary segmentation of each word. The results show that we improve the state-of-art Turkish scores by 12% having a F-measure of 72% and we improve the English scores by 3% having a F-measure of 74%. Eventually, the system outperforms both MorphoChains and other well-known unsupervised morphological segmentation systems. The results indicate that candidate generation plays an important role in such an unsupervised log-linear model that is learned using contrastive estimation with negative samples.
Tasks
Published	2017-05-05
URL	http://arxiv.org/abs/1705.02314v1
PDF	http://arxiv.org/pdf/1705.02314v1.pdf
PWC	https://paperswithcode.com/paper/building-morphological-chains-for
Repo
Framework

Optimizing Filter Size in Convolutional Neural Networks for Facial Action Unit Recognition


Title	Optimizing Filter Size in Convolutional Neural Networks for Facial Action Unit Recognition
Authors	Shizhong Han, Zibo Meng, Zhiyuan Li, James O’Reilly, Jie Cai, Xiaofeng Wang, Yan Tong
Abstract	Recognizing facial action units (AUs) during spontaneous facial displays is a challenging problem. Most recently, Convolutional Neural Networks (CNNs) have shown promise for facial AU recognition, where predefined and fixed convolution filter sizes are employed. In order to achieve the best performance, the optimal filter size is often empirically found by conducting extensive experimental validation. Such a training process suffers from expensive training cost, especially as the network becomes deeper. This paper proposes a novel Optimized Filter Size CNN (OFS-CNN), where the filter sizes and weights of all convolutional layers are learned simultaneously from the training data along with learning convolution filters. Specifically, the filter size is defined as a continuous variable, which is optimized by minimizing the training loss. Experimental results on two AU-coded spontaneous databases have shown that the proposed OFS-CNN is capable of estimating optimal filter size for varying image resolution and outperforms traditional CNNs with the best filter size obtained by exhaustive search. The OFS-CNN also beats the CNN using multiple filter sizes and more importantly, is much more efficient during testing with the proposed forward-backward propagation algorithm.
Tasks	Facial Action Unit Detection
Published	2017-07-26
URL	http://arxiv.org/abs/1707.08630v2
PDF	http://arxiv.org/pdf/1707.08630v2.pdf
PWC	https://paperswithcode.com/paper/optimizing-filter-size-in-convolutional
Repo
Framework

Automated Pruning for Deep Neural Network Compression


Title	Automated Pruning for Deep Neural Network Compression
Authors	Franco Manessi, Alessandro Rozza, Simone Bianco, Paolo Napoletano, Raimondo Schettini
Abstract	In this work we present a method to improve the pruning step of the current state-of-the-art methodology to compress neural networks. The novelty of the proposed pruning technique is in its differentiability, which allows pruning to be performed during the backpropagation phase of the network training. This enables an end-to-end learning and strongly reduces the training time. The technique is based on a family of differentiable pruning functions and a new regularizer specifically designed to enforce pruning. The experimental results show that the joint optimization of both the thresholds and the network weights permits to reach a higher compression rate, reducing the number of weights of the pruned network by a further 14% to 33% compared to the current state-of-the-art. Furthermore, we believe that this is the first study where the generalization capabilities in transfer learning tasks of the features extracted by a pruned network are analyzed. To achieve this goal, we show that the representations learned using the proposed pruning methodology maintain the same effectiveness and generality of those learned by the corresponding non-compressed network on a set of different recognition tasks.
Tasks	Neural Network Compression, Transfer Learning
Published	2017-12-05
URL	http://arxiv.org/abs/1712.01721v2
PDF	http://arxiv.org/pdf/1712.01721v2.pdf
PWC	https://paperswithcode.com/paper/automated-pruning-for-deep-neural-network
Repo
Framework

Towards Neural Speaker Modeling in Multi-Party Conversation: The Task, Dataset, and Models


Title	Towards Neural Speaker Modeling in Multi-Party Conversation: The Task, Dataset, and Models
Authors	Zhao Meng, Lili Mou, Zhi Jin
Abstract	Neural network-based dialog systems are attracting increasing attention in both academia and industry. Recently, researchers have begun to realize the importance of speaker modeling in neural dialog systems, but there lacks established tasks and datasets. In this paper, we propose speaker classification as a surrogate task for general speaker modeling, and collect massive data to facilitate research in this direction. We further investigate temporal-based and content-based models of speakers, and propose several hybrids of them. Experiments show that speaker classification is feasible, and that hybrid models outperform each single component.
Tasks
Published	2017-08-10
URL	http://arxiv.org/abs/1708.03152v2
PDF	http://arxiv.org/pdf/1708.03152v2.pdf
PWC	https://paperswithcode.com/paper/towards-neural-speaker-modeling-in-multi
Repo
Framework

Instance-Level Salient Object Segmentation


Title	Instance-Level Salient Object Segmentation
Authors	Guanbin Li, Yuan Xie, Liang Lin, Yizhou Yu
Abstract	Image saliency detection has recently witnessed rapid progress due to deep convolutional neural networks. However, none of the existing methods is able to identify object instances in the detected salient regions. In this paper, we present a salient instance segmentation method that produces a saliency mask with distinct object instance labels for an input image. Our method consists of three steps, estimating saliency map, detecting salient object contours and identifying salient object instances. For the first two steps, we propose a multiscale saliency refinement network, which generates high-quality salient region masks and salient object contours. Once integrated with multiscale combinatorial grouping and a MAP-based subset optimization framework, our method can generate very promising salient object instance segmentation results. To promote further research and evaluation of salient instance segmentation, we also construct a new database of 1000 images and their pixelwise salient instance annotations. Experimental results demonstrate that our proposed method is capable of achieving state-of-the-art performance on all public benchmarks for salient region detection as well as on our new dataset for salient instance segmentation.
Tasks	Instance Segmentation, Saliency Detection, Semantic Segmentation
Published	2017-04-12
URL	http://arxiv.org/abs/1704.03604v1
PDF	http://arxiv.org/pdf/1704.03604v1.pdf
PWC	https://paperswithcode.com/paper/instance-level-salient-object-segmentation
Repo
Framework

On Using Active Learning and Self-Training when Mining Performance Discussions on Stack Overflow


Title	On Using Active Learning and Self-Training when Mining Performance Discussions on Stack Overflow
Authors	Markus Borg, Iben Lennerstad, Rasmus Ros, Elizabeth Bjarnason
Abstract	Abundant data is the key to successful machine learning. However, supervised learning requires annotated data that are often hard to obtain. In a classification task with limited resources, Active Learning (AL) promises to guide annotators to examples that bring the most value for a classifier. AL can be successfully combined with self-training, i.e., extending a training set with the unlabelled examples for which a classifier is the most certain. We report our experiences on using AL in a systematic manner to train an SVM classifier for Stack Overflow posts discussing performance of software components. We show that the training examples deemed as the most valuable to the classifier are also the most difficult for humans to annotate. Despite carefully evolved annotation criteria, we report low inter-rater agreement, but we also propose mitigation strategies. Finally, based on one annotator’s work, we show that self-training can improve the classification accuracy. We conclude the paper by discussing implication for future text miners aspiring to use AL and self-training.
Tasks	Active Learning
Published	2017-04-26
URL	http://arxiv.org/abs/1705.02395v1
PDF	http://arxiv.org/pdf/1705.02395v1.pdf
PWC	https://paperswithcode.com/paper/on-using-active-learning-and-self-training
Repo
Framework

Crime prediction through urban metrics and statistical learning


Title	Crime prediction through urban metrics and statistical learning
Authors	Luiz G A Alves, Haroldo V Ribeiro, Francisco A Rodrigues
Abstract	Understanding the causes of crime is a longstanding issue in researcher’s agenda. While it is a hard task to extract causality from data, several linear models have been proposed to predict crime through the existing correlations between crime and urban metrics. However, because of non-Gaussian distributions and multicollinearity in urban indicators, it is common to find controversial conclusions about the influence of some urban indicators on crime. Machine learning ensemble-based algorithms can handle well such problems. Here, we use a random forest regressor to predict crime and quantify the influence of urban indicators on homicides. Our approach can have up to 97% of accuracy on crime prediction, and the importance of urban indicators is ranked and clustered in groups of equal influence, which are robust under slightly changes in the data sample analyzed. Our results determine the rank of importance of urban indicators to predict crime, unveiling that unemployment and illiteracy are the most important variables for describing homicides in Brazilian cities. We further believe that our approach helps in producing more robust conclusions regarding the effects of urban indicators on crime, having potential applications for guiding public policies for crime control.
Tasks	Crime Prediction
Published	2017-12-08
URL	http://arxiv.org/abs/1712.03834v2
PDF	http://arxiv.org/pdf/1712.03834v2.pdf
PWC	https://paperswithcode.com/paper/crime-prediction-through-urban-metrics-and
Repo
Framework

Stochastic variance reduced multiplicative update for nonnegative matrix factorization


Title	Stochastic variance reduced multiplicative update for nonnegative matrix factorization
Authors	Hiroyuki Kasai
Abstract	Nonnegative matrix factorization (NMF), a dimensionality reduction and factor analysis method, is a special case in which factor matrices have low-rank nonnegative constraints. Considering the stochastic learning in NMF, we specifically address the multiplicative update (MU) rule, which is the most popular, but which has slow convergence property. This present paper introduces on the stochastic MU rule a variance-reduced technique of stochastic gradient. Numerical comparisons suggest that our proposed algorithms robustly outperform state-of-the-art algorithms across different synthetic and real-world datasets.
Tasks	Dimensionality Reduction
Published	2017-10-30
URL	http://arxiv.org/abs/1710.10781v2
PDF	http://arxiv.org/pdf/1710.10781v2.pdf
PWC	https://paperswithcode.com/paper/stochastic-variance-reduced-multiplicative
Repo
Framework

Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representations


Title	Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representations
Authors	Eirikur Agustsson, Fabian Mentzer, Michael Tschannen, Lukas Cavigelli, Radu Timofte, Luca Benini, Luc Van Gool
Abstract	We present a new approach to learn compressible representations in deep architectures with an end-to-end training strategy. Our method is based on a soft (continuous) relaxation of quantization and entropy, which we anneal to their discrete counterparts throughout training. We showcase this method for two challenging applications: Image compression and neural network compression. While these tasks have typically been approached with different methods, our soft-to-hard quantization approach gives results competitive with the state-of-the-art for both.
Tasks	Image Compression, Neural Network Compression, Quantization
Published	2017-04-03
URL	http://arxiv.org/abs/1704.00648v2
PDF	http://arxiv.org/pdf/1704.00648v2.pdf
PWC	https://paperswithcode.com/paper/soft-to-hard-vector-quantization-for-end-to
Repo
Framework