October 19, 2019

3071 words 15 mins read

Paper Group ANR 285

Explaining First Impressions: Modeling, Recognizing, and Explaining Apparent Personality from Videos. The Variational Deficiency Bottleneck. A Deep Error Correction Network for Compressed Sensing MRI. Regional Priority Based Anomaly Detection using Autoencoders. Network Enhancement: a general method to denoise weighted biological networks. Dynamic …

Explaining First Impressions: Modeling, Recognizing, and Explaining Apparent Personality from Videos


Title	Explaining First Impressions: Modeling, Recognizing, and Explaining Apparent Personality from Videos
Authors	Hugo Jair Escalante, Heysem Kaya, Albert Ali Salah, Sergio Escalera, Yagmur Gucluturk, Umut Guclu, Xavier Baro, Isabelle Guyon, Julio Jacques Junior, Meysam Madadi, Stephane Ayache, Evelyne Viegas, Furkan Gurpinar, Achmadnoer Sukma Wicaksana, Cynthia C. S. Liem, Marcel A. J. van Gerven, Rob van Lier
Abstract	Explainability and interpretability are two critical aspects of decision support systems. Within computer vision, they are critical in certain tasks related to human behavior analysis such as in health care applications. Despite their importance, it is only recently that researchers are starting to explore these aspects. This paper provides an introduction to explainability and interpretability in the context of computer vision with an emphasis on looking at people tasks. Specifically, we review and study those mechanisms in the context of first impressions analysis. To the best of our knowledge, this is the first effort in this direction. Additionally, we describe a challenge we organized on explainability in first impressions analysis from video. We analyze in detail the newly introduced data set, the evaluation protocol, and summarize the results of the challenge. Finally, derived from our study, we outline research opportunities that we foresee will be decisive in the near future for the development of the explainable computer vision field.
Tasks
Published	2018-02-02
URL	https://arxiv.org/abs/1802.00745v3
PDF	https://arxiv.org/pdf/1802.00745v3.pdf
PWC	https://paperswithcode.com/paper/explaining-first-impressions-modeling
Repo
Framework

The Variational Deficiency Bottleneck


Title	The Variational Deficiency Bottleneck
Authors	Pradeep Kr. Banerjee, Guido Montúfar
Abstract	We introduce a bottleneck method for learning data representations based on information deficiency, rather than the more traditional information sufficiency. A variational upper bound allows us to implement this method efficiently. The bound itself is bounded above by the variational information bottleneck objective, and the two methods coincide in the regime of single-shot Monte Carlo approximations. The notion of deficiency provides a principled way of approximating complicated channels by relatively simpler ones. We show that the deficiency of one channel with respect to another has an operational interpretation in terms of the optimal risk gap of decision problems, capturing classification as a special case. Experiments demonstrate that the deficiency bottleneck can provide advantages in terms of minimal sufficiency as measured by information bottleneck curves, while retaining robust test performance in classification tasks.
Tasks
Published	2018-10-27
URL	https://arxiv.org/abs/1810.11677v2
PDF	https://arxiv.org/pdf/1810.11677v2.pdf
PWC	https://paperswithcode.com/paper/the-variational-deficiency-bottleneck
Repo
Framework

A Deep Error Correction Network for Compressed Sensing MRI


Title	A Deep Error Correction Network for Compressed Sensing MRI
Authors	Liyan Sun, Zhiwen Fan, Yue Huang, Xinghao Ding, John Paisley
Abstract	Compressed sensing for magnetic resonance imaging (CS-MRI) exploits image sparsity properties to reconstruct MRI from very few Fourier k-space measurements. The goal is to minimize any structural errors in the reconstruction that could have a negative impact on its diagnostic quality. To this end, we propose a deep error correction network (DECN) for CS-MRI. The DECN model consists of three parts, which we refer to as modules: a guide, or template, module, an error correction module, and a data fidelity module. Existing CS-MRI algorithms can serve as the template module for guiding the reconstruction. Using this template as a guide, the error correction module learns a convolutional neural network (CNN) to map the k-space data in a way that adjusts for the reconstruction error of the template image. Our experimental results show the proposed DECN CS-MRI reconstruction framework can considerably improve upon existing inversion algorithms by supplementing with an error-correcting CNN.
Tasks
Published	2018-03-23
URL	http://arxiv.org/abs/1803.08763v1
PDF	http://arxiv.org/pdf/1803.08763v1.pdf
PWC	https://paperswithcode.com/paper/a-deep-error-correction-network-for
Repo
Framework

Regional Priority Based Anomaly Detection using Autoencoders


Title	Regional Priority Based Anomaly Detection using Autoencoders
Authors	Shruti Mittal, Dattaraj Rao
Abstract	In the recent times, autoencoders, besides being used for compression, have been proven quite useful even for regenerating similar images or help in image denoising. They have also been explored for anomaly detection in a few cases. However, due to location invariance property of convolutional neural network, autoencoders tend to learn from or search for learned features in the complete image. This creates issues when all the items in the image are not equally important and their location matters. For such cases, a semi supervised solution - regional priority based autoencoder (RPAE) has been proposed. In this model, similar to object detection models, a region proposal network identifies the relevant areas in the images as belonging to one of the predefined categories and then those bounding boxes are fed into appropriate decoder based on the category they belong to. Finally, the error scores from all the decoders are combined based on their importance to provide total reconstruction error.
Tasks	Anomaly Detection, Denoising, Image Denoising, Object Detection
Published	2018-04-02
URL	http://arxiv.org/abs/1804.00492v1
PDF	http://arxiv.org/pdf/1804.00492v1.pdf
PWC	https://paperswithcode.com/paper/regional-priority-based-anomaly-detection
Repo
Framework

Network Enhancement: a general method to denoise weighted biological networks


Title	Network Enhancement: a general method to denoise weighted biological networks
Authors	Bo Wang, Armin Pourshafeie, Marinka Zitnik, Junjie Zhu, Carlos D. Bustamante, Serafim Batzoglou, Jure Leskovec
Abstract	Networks are ubiquitous in biology where they encode connectivity patterns at all scales of organization, from molecular to the biome. However, biological networks are noisy due to the limitations of measurement technology and inherent natural variation, which can hamper discovery of network patterns and dynamics. We propose Network Enhancement (NE), a method for improving the signal-to-noise ratio of undirected, weighted networks. NE uses a doubly stochastic matrix operator that induces sparsity and provides a closed-form solution that increases spectral eigengap of the input network. As a result, NE removes weak edges, enhances real connections, and leads to better downstream performance. Experiments show that NE improves gene function prediction by denoising tissue-specific interaction networks, alleviates interpretation of noisy Hi-C contact maps from the human genome, and boosts fine-grained identification accuracy of species. Our results indicate that NE is widely applicable for denoising biological networks.
Tasks	Denoising
Published	2018-05-09
URL	http://arxiv.org/abs/1805.03327v2
PDF	http://arxiv.org/pdf/1805.03327v2.pdf
PWC	https://paperswithcode.com/paper/network-enhancement-a-general-method-to
Repo
Framework

Dynamic Likelihood-free Inference via Ratio Estimation (DIRE)


Title	Dynamic Likelihood-free Inference via Ratio Estimation (DIRE)
Authors	Traiko Dinev, Michael U. Gutmann
Abstract	Parametric statistical models that are implicitly defined in terms of a stochastic data generating process are used in a wide range of scientific disciplines because they enable accurate modeling. However, learning the parameters from observed data is generally very difficult because their likelihood function is typically intractable. Likelihood-free Bayesian inference methods have been proposed which include the frameworks of approximate Bayesian computation (ABC), synthetic likelihood, and its recent generalization that performs likelihood-free inference by ratio estimation (LFIRE). A major difficulty in all these methods is choosing summary statistics that reduce the dimensionality of the data to facilitate inference. While several methods for choosing summary statistics have been proposed for ABC, the literature for synthetic likelihood and LFIRE is very thin to date. We here address this gap in the literature, focusing on the important special case of time-series models. We show that convolutional neural networks trained to predict the input parameters from the data provide suitable summary statistics for LFIRE. On a wide range of time-series models, a single neural network architecture produced equally or more accurate posteriors than alternative methods.
Tasks	Bayesian Inference, Time Series
Published	2018-10-23
URL	http://arxiv.org/abs/1810.09899v1
PDF	http://arxiv.org/pdf/1810.09899v1.pdf
PWC	https://paperswithcode.com/paper/dynamic-likelihood-free-inference-via-ratio
Repo
Framework

Annotating Electronic Medical Records for Question Answering


Title	Annotating Electronic Medical Records for Question Answering
Authors	Preethi Raghavan, Siddharth Patwardhan, Jennifer J. Liang, Murthy V. Devarakonda
Abstract	Our research is in the relatively unexplored area of question answering technologies for patient-specific questions over their electronic health records. A large dataset of human expert curated question and answer pairs is an important pre-requisite for developing, training and evaluating any question answering system that is powered by machine learning. In this paper, we describe a process for creating such a dataset of questions and answers. Our methodology is replicable, can be conducted by medical students as annotators, and results in high inter-annotator agreement (0.71 Cohen’s kappa). Over the course of 11 months, 11 medical students followed our annotation methodology, resulting in a question answering dataset of 5696 questions over 71 patient records, of which 1747 questions have corresponding answers generated by the medical students.
Tasks	Question Answering
Published	2018-05-17
URL	http://arxiv.org/abs/1805.06816v1
PDF	http://arxiv.org/pdf/1805.06816v1.pdf
PWC	https://paperswithcode.com/paper/annotating-electronic-medical-records-for
Repo
Framework

Building Footprint Generation Using Improved Generative Adversarial Networks


Title	Building Footprint Generation Using Improved Generative Adversarial Networks
Authors	Yilei Shi, Qingyu Li, Xiao Xiang Zhu
Abstract	Building footprint information is an essential ingredient for 3-D reconstruction of urban models. The automatic generation of building footprints from satellite images presents a considerable challenge due to the complexity of building shapes. In this work, we have proposed improved generative adversarial networks (GANs) for the automatic generation of building footprints from satellite images. We used a conditional GAN with a cost function derived from the Wasserstein distance and added a gradient penalty term. The achieved results indicated that the proposed method can significantly improve the quality of building footprint generation compared to conditional generative adversarial networks, the U-Net, and other networks. In addition, our method nearly removes all hyperparameters tuning.
Tasks
Published	2018-10-26
URL	http://arxiv.org/abs/1810.11224v1
PDF	http://arxiv.org/pdf/1810.11224v1.pdf
PWC	https://paperswithcode.com/paper/building-footprint-generation-using-improved
Repo
Framework

Adversarial Attacks on Face Detectors using Neural Net based Constrained Optimization


Title	Adversarial Attacks on Face Detectors using Neural Net based Constrained Optimization
Authors	Avishek Joey Bose, Parham Aarabi
Abstract	Adversarial attacks involve adding, small, often imperceptible, perturbations to inputs with the goal of getting a machine learning model to misclassifying them. While many different adversarial attack strategies have been proposed on image classification models, object detection pipelines have been much harder to break. In this paper, we propose a novel strategy to craft adversarial examples by solving a constrained optimization problem using an adversarial generator network. Our approach is fast and scalable, requiring only a forward pass through our trained generator network to craft an adversarial sample. Unlike in many attack strategies, we show that the same trained generator is capable of attacking new images without explicitly optimizing on them. We evaluate our attack on a trained Faster R-CNN face detector on the cropped 300-W face dataset where we manage to reduce the number of detected faces to $0.5%$ of all originally detected faces. In a different experiment, also on 300-W, we demonstrate the robustness of our attack to a JPEG compression based defense typical JPEG compression level of $75%$ reduces the effectiveness of our attack from only $0.5%$ of detected faces to a modest $5.0%$.
Tasks	Adversarial Attack, Image Classification, Object Detection
Published	2018-05-31
URL	http://arxiv.org/abs/1805.12302v1
PDF	http://arxiv.org/pdf/1805.12302v1.pdf
PWC	https://paperswithcode.com/paper/adversarial-attacks-on-face-detectors-using
Repo
Framework

Second Language Acquisition Modeling: An Ensemble Approach


Title	Second Language Acquisition Modeling: An Ensemble Approach
Authors	Anton Osika, Susanna Nilsson, Andrii Sydorchuk, Faruk Sahin, Anders Huss
Abstract	Accurate prediction of students knowledge is a fundamental building block of personalized learning systems. Here, we propose a novel ensemble model to predict student knowledge gaps. Applying our approach to student trace data from the online educational platform Duolingo we achieved highest score on both evaluation metrics for all three datasets in the 2018 Shared Task on Second Language Acquisition Modeling. We describe our model and discuss relevance of the task compared to how it would be setup in a production environment for personalized education.
Tasks	Language Acquisition
Published	2018-06-09
URL	http://arxiv.org/abs/1806.04525v1
PDF	http://arxiv.org/pdf/1806.04525v1.pdf
PWC	https://paperswithcode.com/paper/second-language-acquisition-modeling-an
Repo
Framework

Short-term Memory of Deep RNN


Title	Short-term Memory of Deep RNN
Authors	Claudio Gallicchio
Abstract	The extension of deep learning towards temporal data processing is gaining an increasing research interest. In this paper we investigate the properties of state dynamics developed in successive levels of deep recurrent neural networks (RNNs) in terms of short-term memory abilities. Our results reveal interesting insights that shed light on the nature of layering as a factor of RNN design. Noticeably, higher layers in a hierarchically organized RNN architecture results to be inherently biased towards longer memory spans even prior to training of the recurrent connections. Moreover, in the context of Reservoir Computing framework, our analysis also points out the benefit of a layered recurrent organization as an efficient approach to improve the memory skills of reservoir models.
Tasks
Published	2018-02-02
URL	http://arxiv.org/abs/1802.00748v1
PDF	http://arxiv.org/pdf/1802.00748v1.pdf
PWC	https://paperswithcode.com/paper/short-term-memory-of-deep-rnn
Repo
Framework

FAdeML: Understanding the Impact of Pre-Processing Noise Filtering on Adversarial Machine Learning


Title	FAdeML: Understanding the Impact of Pre-Processing Noise Filtering on Adversarial Machine Learning
Authors	Faiq Khalid, Muhammmad Abdullah Hanif, Semeen Rehman, Junaid Qadir, Muhammad Shafique
Abstract	Deep neural networks (DNN)-based machine learning (ML) algorithms have recently emerged as the leading ML paradigm particularly for the task of classification due to their superior capability of learning efficiently from large datasets. The discovery of a number of well-known attacks such as dataset poisoning, adversarial examples, and network manipulation (through the addition of malicious nodes) has, however, put the spotlight squarely on the lack of security in DNN-based ML systems. In particular, malicious actors can use these well-known attacks to cause random/targeted misclassification, or cause a change in the prediction confidence, by only slightly but systematically manipulating the environmental parameters, inference data, or the data acquisition block. Most of the prior adversarial attacks have, however, not accounted for the pre-processing noise filters commonly integrated with the ML-inference module. Our contribution in this work is to show that this is a major omission since these noise filters can render ineffective the majority of the existing attacks, which rely essentially on introducing adversarial noise. Apart from this, we also extend the state of the art by proposing a novel pre-processing noise Filter-aware Adversarial ML attack called FAdeML. To demonstrate the effectiveness of the proposed methodology, we generate an adversarial attack image by exploiting the “VGGNet” DNN trained for the “German Traffic Sign Recognition Benchmarks (GTSRB” dataset, which despite having no visual noise, can cause a classifier to misclassify even in the presence of pre-processing noise filters.
Tasks	Adversarial Attack, Traffic Sign Recognition
Published	2018-11-04
URL	http://arxiv.org/abs/1811.01444v1
PDF	http://arxiv.org/pdf/1811.01444v1.pdf
PWC	https://paperswithcode.com/paper/fademl-understanding-the-impact-of-pre
Repo
Framework

Interpretable Deep Learning under Fire


Title	Interpretable Deep Learning under Fire
Authors	Xinyang Zhang, Ningfei Wang, Hua Shen, Shouling Ji, Xiapu Luo, Ting Wang
Abstract	Providing explanations for deep neural network (DNN) models is crucial for their use in security-sensitive domains. A plethora of interpretation models have been proposed to help users understand the inner workings of DNNs: how does a DNN arrive at a specific decision for a given input? The improved interpretability is believed to offer a sense of security by involving human in the decision-making process. Yet, due to its data-driven nature, the interpretability itself is potentially susceptible to malicious manipulations, about which little is known thus far. Here we bridge this gap by conducting the first systematic study on the security of interpretable deep learning systems (IDLSes). We show that existing \imlses are highly vulnerable to adversarial manipulations. Specifically, we present ADV^2, a new class of attacks that generate adversarial inputs not only misleading target DNNs but also deceiving their coupled interpretation models. Through empirical evaluation against four major types of IDLSes on benchmark datasets and in security-critical applications (e.g., skin cancer diagnosis), we demonstrate that with ADV^2 the adversary is able to arbitrarily designate an input’s prediction and interpretation. Further, with both analytical and empirical evidence, we identify the prediction-interpretation gap as one root cause of this vulnerability – a DNN and its interpretation model are often misaligned, resulting in the possibility of exploiting both models simultaneously. Finally, we explore potential countermeasures against ADV^2, including leveraging its low transferability and incorporating it in an adversarial training framework. Our findings shed light on designing and operating IDLSes in a more secure and informative fashion, leading to several promising research directions.
Tasks	Decision Making
Published	2018-12-03
URL	https://arxiv.org/abs/1812.00891v3
PDF	https://arxiv.org/pdf/1812.00891v3.pdf
PWC	https://paperswithcode.com/paper/interpretable-deep-learning-under-fire
Repo
Framework

Trajectory-based Learning for Ball-in-Maze Games


Title	Trajectory-based Learning for Ball-in-Maze Games
Authors	Sujoy Paul, Jeroen van Baar
Abstract	Deep Reinforcement Learning has shown tremendous success in solving several games and tasks in robotics. However, unlike humans, it generally requires a lot of training instances. Trajectories imitating to solve the task at hand can help to increase sample-efficiency of deep RL methods. In this paper, we present a simple approach to use such trajectories, applied to the challenging Ball-in-Maze Games, recently introduced in the literature. We show that in spite of not using human-generated trajectories and just using the simulator as a model to generate a limited number of trajectories, we can get a speed-up of about 2-3x in the learning process. We also discuss some challenges we observed while using trajectory-based learning for very sparse reward functions.
Tasks
Published	2018-11-28
URL	http://arxiv.org/abs/1811.11441v2
PDF	http://arxiv.org/pdf/1811.11441v2.pdf
PWC	https://paperswithcode.com/paper/trajectory-based-learning-for-ball-in-maze
Repo
Framework

Power efficient Spiking Neural Network Classifier based on memristive crossbar network for spike sorting application


Title	Power efficient Spiking Neural Network Classifier based on memristive crossbar network for spike sorting application
Authors	Anand Kumar Mukhopadhyay, Indrajit Chakrabarti, Arindam Basu, Mrigank Sharad
Abstract	In this paper authors have presented a power efficient scheme for implementing a spike sorting module. Spike sorting is an important application in the field of neural signal acquisition for implantable biomedical systems whose function is to map the Neural-spikes (N-spikes) correctly to the neurons from which it originates. The accurate classification is a pre-requisite for the succeeding systems needed in Brain-Machine-Interfaces (BMIs) to give better performance. The primary design constraint to be satisfied for the spike sorter module is low power with good accuracy. There lies a trade-off in terms of power consumption between the on-chip and off-chip training of the N-spike features. In the former case care has to be taken to make the computational units power efficient whereas in the later the data rate of wireless transmission should be minimized to reduce the power consumption due to the transceivers. In this work a 2-step shared training scheme involving a K-means sorter and a Spiking Neural Network (SNN) is elaborated for on-chip training and classification. Also, a low power SNN classifier scheme using memristive crossbar type architecture is compared with a fully digital implementation. The advantage of the former classifier is that it is power efficient while providing comparable accuracy as that of the digital implementation due to the robustness of the SNN training algorithm which has a good tolerance for variation in memristance.
Tasks
Published	2018-02-25
URL	http://arxiv.org/abs/1802.09047v1
PDF	http://arxiv.org/pdf/1802.09047v1.pdf
PWC	https://paperswithcode.com/paper/power-efficient-spiking-neural-network
Repo
Framework