July 28, 2019

3068 words 15 mins read

Paper Group ANR 297

Switching EEG Headsets Made Easy: Reducing Offline Calibration Effort Using Active Weighted Adaptation Regularization. Longitudinal Study of Child Face Recognition. Deep Galaxy: Classification of Galaxies based on Deep Convolutional Neural Networks. Scalable Co-Optimization of Morphology and Control in Embodied Machines. A Deep Compositional Framew …

Switching EEG Headsets Made Easy: Reducing Offline Calibration Effort Using Active Weighted Adaptation Regularization


Title	Switching EEG Headsets Made Easy: Reducing Offline Calibration Effort Using Active Weighted Adaptation Regularization
Authors	Dongrui Wu, Vernon J. Lawhern, W. David Hairston, Brent J. Lance
Abstract	Electroencephalography (EEG) headsets are the most commonly used sensing devices for Brain-Computer Interface. In real-world applications, there are advantages to extrapolating data from one user session to another. However, these advantages are limited if the data arise from different hardware systems, which often vary between application spaces. Currently, this creates a need to recalibrate classifiers, which negatively affects people’s interest in using such systems. In this paper, we employ active weighted adaptation regularization (AwAR), which integrates weighted adaptation regularization (wAR) and active learning, to expedite the calibration process. wAR makes use of labeled data from the previous headset and handles class-imbalance, and active learning selects the most informative samples from the new headset to label. Experiments on single-trial event-related potential classification show that AwAR can significantly increase the classification accuracy, given the same number of labeled samples from the new headset. In other words, AwAR can effectively reduce the number of labeled samples required from the new headset, given a desired classification accuracy, suggesting value in collating data for use in wide scale transfer-learning applications.
Tasks	Active Learning, Calibration, EEG, Transfer Learning
Published	2017-02-09
URL	http://arxiv.org/abs/1702.02906v1
PDF	http://arxiv.org/pdf/1702.02906v1.pdf
PWC	https://paperswithcode.com/paper/switching-eeg-headsets-made-easy-reducing
Repo
Framework

Longitudinal Study of Child Face Recognition


Title	Longitudinal Study of Child Face Recognition
Authors	Debayan Deb, Neeta Nain, Anil K. Jain
Abstract	We present a longitudinal study of face recognition performance on Children Longitudinal Face (CLF) dataset containing 3,682 face images of 919 subjects, in the age group [2, 18] years. Each subject has at least four face images acquired over a time span of up to six years. Face comparison scores are obtained from (i) a state-of-the-art COTS matcher (COTS-A), (ii) an open-source matcher (FaceNet), and (iii) a simple sum fusion of scores obtained from COTS-A and FaceNet matchers. To improve the performance of the open-source FaceNet matcher for child face recognition, we were able to fine-tune it on an independent training set of 3,294 face images of 1,119 children in the age group [3, 18] years. Multilevel statistical models are fit to genuine comparison scores from the CLF dataset to determine the decrease in face recognition accuracy over time. Additionally, we analyze both the verification and open-set identification accuracies in order to evaluate state-of-the-art face recognition technology for tracing and identifying children lost at a young age as victims of child trafficking or abduction.
Tasks	Face Recognition
Published	2017-11-10
URL	http://arxiv.org/abs/1711.03990v1
PDF	http://arxiv.org/pdf/1711.03990v1.pdf
PWC	https://paperswithcode.com/paper/longitudinal-study-of-child-face-recognition
Repo
Framework

Deep Galaxy: Classification of Galaxies based on Deep Convolutional Neural Networks


Title	Deep Galaxy: Classification of Galaxies based on Deep Convolutional Neural Networks
Authors	Nour Eldeen M. Khalifa, Mohamed Hamed N. Taha, Aboul Ella Hassanien, I. M. Selim
Abstract	In this paper, a deep convolutional neural network architecture for galaxies classification is presented. The galaxy can be classified based on its features into main three categories Elliptical, Spiral, and Irregular. The proposed deep galaxies architecture consists of 8 layers, one main convolutional layer for features extraction with 96 filters, followed by two principles fully connected layers for classification. It is trained over 1356 images and achieved 97.272% in testing accuracy. A comparative result is made and the testing accuracy was compared with other related works. The proposed architecture outperformed other related works in terms of testing accuracy.
Tasks
Published	2017-09-02
URL	http://arxiv.org/abs/1709.02245v1
PDF	http://arxiv.org/pdf/1709.02245v1.pdf
PWC	https://paperswithcode.com/paper/deep-galaxy-classification-of-galaxies-based
Repo
Framework

Scalable Co-Optimization of Morphology and Control in Embodied Machines


Title	Scalable Co-Optimization of Morphology and Control in Embodied Machines
Authors	Nick Cheney, Josh Bongard, Vytas SunSpiral, Hod Lipson
Abstract	Evolution sculpts both the body plans and nervous systems of agents together over time. In contrast, in AI and robotics, a robot’s body plan is usually designed by hand, and control policies are then optimized for that fixed design. The task of simultaneously co-optimizing the morphology and controller of an embodied robot has remained a challenge. In psychology, the theory of embodied cognition posits that behavior arises from a close coupling between body plan and sensorimotor control, which suggests why co-optimizing these two subsystems is so difficult: most evolutionary changes to morphology tend to adversely impact sensorimotor control, leading to an overall decrease in behavioral performance. Here, we further examine this hypothesis and demonstrate a technique for “morphological innovation protection”, which temporarily reduces selection pressure on recently morphologically-changed individuals, thus enabling evolution some time to “readapt” to the new morphology with subsequent control policy mutations. We show the potential for this method to avoid local optima and converge to similar highly fit morphologies across widely varying initial conditions, while sustaining fitness improvements further into optimization. While this technique is admittedly only the first of many steps that must be taken to achieve scalable optimization of embodied machines, we hope that theoretical insight into the cause of evolutionary stagnation in current methods will help to enable the automation of robot design and behavioral training – while simultaneously providing a testbed to investigate the theory of embodied cognition.
Tasks
Published	2017-06-19
URL	http://arxiv.org/abs/1706.06133v2
PDF	http://arxiv.org/pdf/1706.06133v2.pdf
PWC	https://paperswithcode.com/paper/scalable-co-optimization-of-morphology-and
Repo
Framework

A Deep Compositional Framework for Human-like Language Acquisition in Virtual Environment


Title	A Deep Compositional Framework for Human-like Language Acquisition in Virtual Environment
Authors	Haonan Yu, Haichao Zhang, Wei Xu
Abstract	We tackle a task where an agent learns to navigate in a 2D maze-like environment called XWORLD. In each session, the agent perceives a sequence of raw-pixel frames, a natural language command issued by a teacher, and a set of rewards. The agent learns the teacher’s language from scratch in a grounded and compositional manner, such that after training it is able to correctly execute zero-shot commands: 1) the combination of words in the command never appeared before, and/or 2) the command contains new object concepts that are learned from another task but never learned from navigation. Our deep framework for the agent is trained end to end: it learns simultaneously the visual representations of the environment, the syntax and semantics of the language, and the action module that outputs actions. The zero-shot learning capability of our framework results from its compositionality and modularity with parameter tying. We visualize the intermediate outputs of the framework, demonstrating that the agent truly understands how to solve the problem. We believe that our results provide some preliminary insights on how to train an agent with similar abilities in a 3D environment.
Tasks	Language Acquisition, Zero-Shot Learning
Published	2017-03-28
URL	http://arxiv.org/abs/1703.09831v3
PDF	http://arxiv.org/pdf/1703.09831v3.pdf
PWC	https://paperswithcode.com/paper/a-deep-compositional-framework-for-human-like
Repo
Framework

Conditional Adversarial Network for Semantic Segmentation of Brain Tumor


Title	Conditional Adversarial Network for Semantic Segmentation of Brain Tumor
Authors	Mina Rezaei, Konstantin Harmuth, Willi Gierke, Thomas Kellermeier, Martin Fischer, Haojin Yang, Christoph Meinel
Abstract	Automated medical image analysis has a significant value in diagnosis and treatment of lesions. Brain tumors segmentation has a special importance and difficulty due to the difference in appearances and shapes of the different tumor regions in magnetic resonance images. Additionally, the data sets are heterogeneous and usually limited in size in comparison with the computer vision problems. The recently proposed adversarial training has shown promising results in generative image modeling. In this paper, we propose a novel end-to-end trainable architecture for brain tumor semantic segmentation through conditional adversarial training. We exploit conditional Generative Adversarial Network (cGAN) and train a semantic segmentation Convolution Neural Network (CNN) along with an adversarial network that discriminates segmentation maps coming from the ground truth or from the segmentation network for BraTS 2017 segmentation task[15, 4, 2, 3]. We also propose an end-to-end trainable CNN for survival day prediction based on deep learning techniques for BraTS 2017 prediction task [15, 4, 2, 3]. The experimental results demonstrate the superior ability of the proposed approach for both tasks. The proposed model achieves on validation data a DICE score, Sensitivity and Specificity respectively 0.68, 0.99 and 0.98 for the whole tumor, regarding online judgment system.
Tasks	Semantic Segmentation
Published	2017-08-17
URL	http://arxiv.org/abs/1708.05227v1
PDF	http://arxiv.org/pdf/1708.05227v1.pdf
PWC	https://paperswithcode.com/paper/conditional-adversarial-network-for-semantic
Repo
Framework

Automatic Crack Detection in Built Infrastructure Using Unmanned Aerial Vehicles


Title	Automatic Crack Detection in Built Infrastructure Using Unmanned Aerial Vehicles
Authors	Manh Duong Phung, Van Truong Hoang, Tran Hiep Dinh, Quang Ha
Abstract	This paper addresses the problem of crack detection which is essential for health monitoring of built infrastructure. Our approach includes two stages, data collection using unmanned aerial vehicles (UAVs) and crack detection using histogram analysis. For the data collection, a 3D model of the structure is first created by using laser scanners. Based on the model, geometric properties are extracted to generate way points necessary for navigating the UAV to take images of the structure. Then, our next step is to stick together those obtained images from the overlapped field of view. The resulting image is then clustered by histogram analysis and peak detection. Potential cracks are finally identified by using locally adaptive thresholds. The whole process is automatically carried out so that the inspection time is significantly improved while safety hazards can be minimised. A prototypical system has been developed for evaluation and experimental results are included.
Tasks
Published	2017-07-31
URL	http://arxiv.org/abs/1707.09715v1
PDF	http://arxiv.org/pdf/1707.09715v1.pdf
PWC	https://paperswithcode.com/paper/automatic-crack-detection-in-built
Repo
Framework

Marked Temporal Dynamics Modeling based on Recurrent Neural Network


Title	Marked Temporal Dynamics Modeling based on Recurrent Neural Network
Authors	Yongqing Wang, Shenghua Liu, Huawei Shen, Xueqi Cheng
Abstract	We are now witnessing the increasing availability of event stream data, i.e., a sequence of events with each event typically being denoted by the time it occurs and its mark information (e.g., event type). A fundamental problem is to model and predict such kind of marked temporal dynamics, i.e., when the next event will take place and what its mark will be. Existing methods either predict only the mark or the time of the next event, or predict both of them, yet separately. Indeed, in marked temporal dynamics, the time and the mark of the next event are highly dependent on each other, requiring a method that could simultaneously predict both of them. To tackle this problem, in this paper, we propose to model marked temporal dynamics by using a mark-specific intensity function to explicitly capture the dependency between the mark and the time of the next event. Extensive experiments on two datasets demonstrate that the proposed method outperforms state-of-the-art methods at predicting marked temporal dynamics.
Tasks
Published	2017-01-14
URL	http://arxiv.org/abs/1701.03918v1
PDF	http://arxiv.org/pdf/1701.03918v1.pdf
PWC	https://paperswithcode.com/paper/marked-temporal-dynamics-modeling-based-on
Repo
Framework

User Intent Classification using Memory Networks: A Comparative Analysis for a Limited Data Scenario


Title	User Intent Classification using Memory Networks: A Comparative Analysis for a Limited Data Scenario
Authors	Arjun Bhardwaj, Alexander Rudnicky
Abstract	In this report, we provide a comparative analysis of different techniques for user intent classification towards the task of app recommendation. We analyse the performance of different models and architectures for multi-label classification over a dataset with a relative large number of classes and only a handful examples of each class. We focus, in particular, on memory network architectures, and compare how well the different versions perform under the task constraints. Since the classifier is meant to serve as a module in a practical dialog system, it needs to be able to work with limited training data and incorporate new data on the fly. We devise a 1-shot learning task to test the models under the above constraint. We conclude that relatively simple versions of memory networks perform better than other approaches. Although, for tasks with very limited data, simple non-parametric methods perform comparably, without needing the extra training data.
Tasks	Intent Classification, Multi-Label Classification
Published	2017-06-19
URL	http://arxiv.org/abs/1706.06160v1
PDF	http://arxiv.org/pdf/1706.06160v1.pdf
PWC	https://paperswithcode.com/paper/user-intent-classification-using-memory
Repo
Framework

Methodology and Results for the Competition on Semantic Similarity Evaluation and Entailment Recognition for PROPOR 2016


Title	Methodology and Results for the Competition on Semantic Similarity Evaluation and Entailment Recognition for PROPOR 2016
Authors	Luciano Barbosa, Paulo R. Cavalin, Victor Guimaraes, Matthias Kormaksson
Abstract	In this paper, we present the methodology and the results obtained by our teams, dubbed Blue Man Group, in the ASSIN (from the Portuguese {\it Avalia\c{c}~ao de Similaridade Sem^antica e Infer^encia Textual}) competition, held at PROPOR 2016\footnote{International Conference on the Computational Processing of the Portuguese Language - http://propor2016.di.fc.ul.pt/}. Our team’s strategy consisted of evaluating methods based on semantic word vectors, following two distinct directions: 1) to make use of low-dimensional, compact, feature sets, and 2) deep learning-based strategies dealing with high-dimensional feature vectors. Evaluation results demonstrated that the first strategy was more promising, so that the results from the second strategy have been discarded. As a result, by considering the best run of each of the six teams, we have been able to achieve the best accuracy and F1 values in entailment recognition, in the Brazilian Portuguese set, and the best F1 score overall. In the semantic similarity task, our team was ranked second in the Brazilian Portuguese set, and third considering both sets.
Tasks	Semantic Similarity, Semantic Textual Similarity
Published	2017-09-19
URL	http://arxiv.org/abs/1709.08694v1
PDF	http://arxiv.org/pdf/1709.08694v1.pdf
PWC	https://paperswithcode.com/paper/methodology-and-results-for-the-competition
Repo
Framework

Obstacle detection test in real-word traffic contexts for the purposes of motorcycle autonomous emergency braking (MAEB)


Title	Obstacle detection test in real-word traffic contexts for the purposes of motorcycle autonomous emergency braking (MAEB)
Authors	Giovanni Savino, Simone Piantini, Gustavo Gil, Marco Pierini
Abstract	Research suggests that a Motorcycle Autonomous Emergency Braking system (MAEB) could influence 25% of the crashes involving powered two wheelers (PTWs). By automatically slowing down a host PTW of up to 10 km/h in inevitable collision scenarios, MAEB could potentially mitigate the crash severity for the riders. The feasibility of automatic decelerations of motorcycles was shown via field trials in controlled environment. However, the feasibility of correct MAEB triggering in the real traffic context is still unclear. In particular, MAEB requires an accurate obstacle detection, the feasibility of which from a single track vehicle has not been confirmed yet. To address this issue, our study presents obstacle detection tests in a real-world MAEB-sensitive crash scenario.
Tasks
Published	2017-06-25
URL	http://arxiv.org/abs/1707.03435v2
PDF	http://arxiv.org/pdf/1707.03435v2.pdf
PWC	https://paperswithcode.com/paper/obstacle-detection-test-in-real-word-traffic
Repo
Framework

Expert and Non-Expert Opinion about Technological Unemployment


Title	Expert and Non-Expert Opinion about Technological Unemployment
Authors	Toby Walsh
Abstract	There is significant concern that technological advances, especially in Robotics and Artificial Intelligence (AI), could lead to high levels of unemployment in the coming decades. Studies have estimated that around half of all current jobs are at risk of automation. To look into this issue in more depth, we surveyed experts in Robotics and AI about the risk, and compared their views with those of non-experts. Whilst the experts predicted a significant number of occupations were at risk of automation in the next two decades, they were more cautious than people outside the field in predicting occupations at risk. Their predictions were consistent with their estimates for when computers might be expected to reach human level performance across a wide range of skills. These estimates were typically decades later than those of the non-experts. Technological barriers may therefore provide society with more time to prepare for an automated future than the public fear. In addition, public expectations may need to be dampened about the speed of progress to be expected in Robotics and AI.
Tasks
Published	2017-06-21
URL	http://arxiv.org/abs/1706.06906v1
PDF	http://arxiv.org/pdf/1706.06906v1.pdf
PWC	https://paperswithcode.com/paper/expert-and-non-expert-opinion-about
Repo
Framework

Deep Residual Networks and Weight Initialization


Title	Deep Residual Networks and Weight Initialization
Authors	Masato Taki
Abstract	Residual Network (ResNet) is the state-of-the-art architecture that realizes successful training of really deep neural network. It is also known that good weight initialization of neural network avoids problem of vanishing/exploding gradients. In this paper, simplified models of ResNets are analyzed. We argue that goodness of ResNet is correlated with the fact that ResNets are relatively insensitive to choice of initial weights. We also demonstrate how batch normalization improves backpropagation of deep ResNets without tuning initial values of weights.
Tasks
Published	2017-09-09
URL	http://arxiv.org/abs/1709.02956v1
PDF	http://arxiv.org/pdf/1709.02956v1.pdf
PWC	https://paperswithcode.com/paper/deep-residual-networks-and-weight
Repo
Framework

Nonparametric Preference Completion


Title	Nonparametric Preference Completion
Authors	Julian Katz-Samuels, Clayton Scott
Abstract	We consider the task of collaborative preference completion: given a pool of items, a pool of users and a partially observed item-user rating matrix, the goal is to recover the \emph{personalized ranking} of each user over all of the items. Our approach is nonparametric: we assume that each item $i$ and each user $u$ have unobserved features $x_i$ and $y_u$, and that the associated rating is given by $g_u(f(x_i,y_u))$ where $f$ is Lipschitz and $g_u$ is a monotonic transformation that depends on the user. We propose a $k$-nearest neighbors-like algorithm and prove that it is consistent. To the best of our knowledge, this is the first consistency result for the collaborative preference completion problem in a nonparametric setting. Finally, we demonstrate the performance of our algorithm with experiments on the Netflix and Movielens datasets.
Tasks
Published	2017-05-24
URL	http://arxiv.org/abs/1705.08621v2
PDF	http://arxiv.org/pdf/1705.08621v2.pdf
PWC	https://paperswithcode.com/paper/nonparametric-preference-completion
Repo
Framework

Robust and fully automated segmentation of mandible from CT scans


Title	Robust and fully automated segmentation of mandible from CT scans
Authors	Neslisah Torosdagli, Denise K. Liberton, Payal Verma, Murat Sincan Janice Lee, Sumanta Pattanaik, Ulas Bagci
Abstract	Mandible bone segmentation from computed tomography (CT) scans is challenging due to mandible’s structural irregularities, complex shape patterns, and lack of contrast in joints. Furthermore, connections of teeth to mandible and mandible to remaining parts of the skull make it extremely difficult to identify mandible boundary automatically. This study addresses these challenges by proposing a novel framework where we define the segmentation as two complementary tasks: recognition and delineation. For recognition, we use random forest regression to localize mandible in 3D. For delineation, we propose to use 3D gradient-based fuzzy connectedness (FC) image segmentation algorithm, operating on the recognized mandible sub-volume. Despite heavy CT artifacts and dental fillings, consisting half of the CT image data in our experiments, we have achieved highly accurate detection and delineation results. Specifically, detection accuracy more than 96% (measured by union of intersection (UoI)), the delineation accuracy of 91% (measured by dice similarity coefficient), and less than 1 mm in shape mismatch (Hausdorff Distance) were found.
Tasks	Computed Tomography (CT), Semantic Segmentation
Published	2017-02-23
URL	http://arxiv.org/abs/1702.07059v1
PDF	http://arxiv.org/pdf/1702.07059v1.pdf
PWC	https://paperswithcode.com/paper/robust-and-fully-automated-segmentation-of
Repo
Framework