October 20, 2019

3299 words 16 mins read

Paper Group ANR 87

Multi-robot Symmetric Rendezvous Search on the Line with an Unknown Initial Distance. Cost-Aware Fine-Grained Recognition for IoTs Based on Sequential Fixations. Staying Alive - CPR Quality Parameters from Wrist-worn Inertial Sensor Data with Evolutionary Fitted Sinusoidal Models. Overfitting or perfect fitting? Risk bounds for classification and r …

Multi-robot Symmetric Rendezvous Search on the Line with an Unknown Initial Distance


Title	Multi-robot Symmetric Rendezvous Search on the Line with an Unknown Initial Distance
Authors	Deniz Ozsoyeller
Abstract	In this paper, we study the symmetric rendezvous search problem on the line with n > 2 robots that are unaware of their locations and the initial distances between them. In the symmetric version of this problem, the robots execute the same strategy. The multi-robot symmetric rendezvous algorithm, MSR presented in this paper is an extension our symmetric rendezvous algorithm, SR presented in [23]. We study both the synchronous and asynchronous cases of the problem. The asynchronous version of MSR algorithm is called MASR algorithm. We consider that robots start executing MASR at different times. We perform the theoretical analysis of MSR and MASR, and show that their competitive ratios are $O(n^{0.67})$ and $O(n^{1.5})$, respectively. Finally, we confirm our theoretical results through simulations.
Tasks
Published	2018-05-21
URL	http://arxiv.org/abs/1805.08645v1
PDF	http://arxiv.org/pdf/1805.08645v1.pdf
PWC	https://paperswithcode.com/paper/multi-robot-symmetric-rendezvous-search-on
Repo
Framework

Cost-Aware Fine-Grained Recognition for IoTs Based on Sequential Fixations


Title	Cost-Aware Fine-Grained Recognition for IoTs Based on Sequential Fixations
Authors	Hanxiao Wang, Venkatesh Saligrama, Stan Sclaroff, Vitaly Ablavsky
Abstract	We consider the problem of fine-grained classification on an edge camera device that has limited power. The edge device must sparingly interact with the cloud to minimize communication bits to conserve power, and the cloud upon receiving the edge inputs returns a classification label. To deal with fine-grained classification, we adopt the perspective of sequential fixation with a foveated field-of-view to model cloud-edge interactions. We propose a novel deep reinforcement learning-based foveation model, DRIFT, that sequentially generates and recognizes mixed-acuity images.Training of DRIFT requires only image-level category labels and encourages fixations to contain task-relevant information, while maintaining data efficiency. Specifically, wetrain a foveation actor network with a novel Deep Deterministic Policy Gradient by Conditioned Critic and Coaching (DDPGC3) algorithm. In addition, we propose to shape the reward to provide informative feedback after each fixation to better guide RL training. We demonstrate the effectiveness of DRIFT on this task by evaluating on five fine-grained classification benchmark datasets, and show that the proposed approach achieves state-of-the-art performance with over 3X reduction in transmitted pixels.
Tasks	Decision Making, Foveation
Published	2018-11-16
URL	https://arxiv.org/abs/1811.06868v2
PDF	https://arxiv.org/pdf/1811.06868v2.pdf
PWC	https://paperswithcode.com/paper/learning-where-to-fixate-on-foveated-images
Repo
Framework

Staying Alive - CPR Quality Parameters from Wrist-worn Inertial Sensor Data with Evolutionary Fitted Sinusoidal Models


Title	Staying Alive - CPR Quality Parameters from Wrist-worn Inertial Sensor Data with Evolutionary Fitted Sinusoidal Models
Authors	Christian Lins, Andreas Klausen, Sandra Hellmers, Andreas Hein, Sebastian Fudickar
Abstract	In this paper, a robust sinusoidal model fitting method based on the Differential Evolution (DE) algorithm for determining cardiopulmonary resuscitation (CPR) quality-parameters - naming chest compression frequency and depth - as measured by an inertial sensor placed at the wrist is presented. Once included into a smartphone or smartwatch app, the proposed algorithm will enable bystanders to improve CPR (as part of a continuous closed-loop support-system). By evaluating the precision of the model with data recorded by a Laerdal Resusci Anne mannequin as reference standard, a low variance for compression frequency of $\pm 2.0$ cpm has been found for the sensor placed at the wrist, making this previously unconsidered position a suitable alternative to the typical placement in the hand for CPR-training smartphone apps.
Tasks
Published	2018-08-31
URL	http://arxiv.org/abs/1809.07692v2
PDF	http://arxiv.org/pdf/1809.07692v2.pdf
PWC	https://paperswithcode.com/paper/staying-alive-cpr-quality-parameters-from
Repo
Framework

Overfitting or perfect fitting? Risk bounds for classification and regression rules that interpolate


Title	Overfitting or perfect fitting? Risk bounds for classification and regression rules that interpolate
Authors	Mikhail Belkin, Daniel Hsu, Partha Mitra
Abstract	Many modern machine learning models are trained to achieve zero or near-zero training error in order to obtain near-optimal (but non-zero) test error. This phenomenon of strong generalization performance for “overfitted” / interpolated classifiers appears to be ubiquitous in high-dimensional data, having been observed in deep networks, kernel machines, boosting and random forests. Their performance is consistently robust even when the data contain large amounts of label noise. Very little theory is available to explain these observations. The vast majority of theoretical analyses of generalization allows for interpolation only when there is little or no label noise. This paper takes a step toward a theoretical foundation for interpolated classifiers by analyzing local interpolating schemes, including geometric simplicial interpolation algorithm and singularly weighted $k$-nearest neighbor schemes. Consistency or near-consistency is proved for these schemes in classification and regression problems. Moreover, the nearest neighbor schemes exhibit optimal rates under some standard statistical assumptions. Finally, this paper suggests a way to explain the phenomenon of adversarial examples, which are seemingly ubiquitous in modern machine learning, and also discusses some connections to kernel machines and random forests in the interpolated regime.
Tasks
Published	2018-06-13
URL	http://arxiv.org/abs/1806.05161v3
PDF	http://arxiv.org/pdf/1806.05161v3.pdf
PWC	https://paperswithcode.com/paper/overfitting-or-perfect-fitting-risk-bounds
Repo
Framework

Predicting Recall Probability to Adaptively Prioritize Study


Title	Predicting Recall Probability to Adaptively Prioritize Study
Authors	Shane Mooney, Karen Sun, Eric Bomgardner
Abstract	Students have a limited time to study and are typically ineffective at allocating study time. Machine-directed study strategies that identify which items need reinforcement and dictate the spacing of repetition have been shown to help students optimize mastery (Mozer & Lindsey 2017). The large volume of research on this matter is typically conducted in constructed experimental settings with fixed instruction, content, and scheduling; in contrast, we aim to develop methods that can address any demographic, subject matter, or study schedule. We show two methods that model item-specific recall probability for use in a discrepancy-reduction instruction strategy. The first model predicts item recall probability using a multiple logistic regression (MLR) model based on previous answer correctness and temporal spacing of study. Prompted by literature suggesting that forgetting is better modeled by the power law than an exponential decay (Wickelgren 1974), we compare the MLR approach with a Recurrent Power Law (RPL) model which adaptively fits a forgetting curve. We then discuss the performance of these models against study datasets comprised of millions of answers and show that the RPL approach is more accurate and flexible than the MLR model. Finally, we give an overview of promising future approaches to knowledge modeling.
Tasks
Published	2018-02-28
URL	http://arxiv.org/abs/1803.00111v1
PDF	http://arxiv.org/pdf/1803.00111v1.pdf
PWC	https://paperswithcode.com/paper/predicting-recall-probability-to-adaptively
Repo
Framework

Direct Automated Quantitative Measurement of Spine via Cascade Amplifier Regression Network


Title	Direct Automated Quantitative Measurement of Spine via Cascade Amplifier Regression Network
Authors	Shumao Pang, Stephanie Leung, Ilanit Ben Nachum, Qianjin Feng, Shuo Li
Abstract	Automated quantitative measurement of the spine (i.e., multiple indices estimation of heights, widths, areas, and so on for the vertebral body and disc) is of the utmost importance in clinical spinal disease diagnoses, such as osteoporosis, intervertebral disc degeneration, and lumbar disc herniation, yet still an unprecedented challenge due to the variety of spine structure and the high dimensionality of indices to be estimated. In this paper, we propose a novel cascade amplifier regression network (CARN), which includes the CARN architecture and local shape-constrained manifold regularization (LSCMR) loss function, to achieve accurate direct automated multiple indices estimation. The CARN architecture is composed of a cascade amplifier network (CAN) for expressive feature embedding and a linear regression model for multiple indices estimation. The CAN consists of cascade amplifier units (AUs), which are used for selective feature reuse by stimulating effective feature and suppressing redundant feature during propagating feature map between adjacent layers, thus an expressive feature embedding is obtained. During training, the LSCMR is utilized to alleviate overfitting and generate realistic estimation by learning the multiple indices distribution. Experiments on MR images of 195 subjects show that the proposed CARN achieves impressive performance with mean absolute errors of 1.2496 mm, 1.2887 mm, and 1.2692 mm for estimation of 15 heights of discs, 15 heights of vertebral bodies, and total indices respectively. The proposed method has great potential in clinical spinal disease diagnoses.
Tasks
Published	2018-06-14
URL	http://arxiv.org/abs/1806.05570v1
PDF	http://arxiv.org/pdf/1806.05570v1.pdf
PWC	https://paperswithcode.com/paper/direct-automated-quantitative-measurement-of
Repo
Framework

Cancelable Indexing Based on Low-rank Approximation of Correlation-invariant Random Filtering for Fast and Secure Biometric Identification


Title	Cancelable Indexing Based on Low-rank Approximation of Correlation-invariant Random Filtering for Fast and Secure Biometric Identification
Authors	Takao Murakami, Tetsushi Ohki, Yosuke Kaga, Masakazu Fujio, Kenta Takahashi
Abstract	A cancelable biometric scheme called correlation-invariant random filtering (CIRF) is known as a promising template protection scheme. This scheme transforms a biometric feature represented as an image via the 2D number theoretic transform (NTT) and random filtering. CIRF has perfect secrecy in that the transformed feature leaks no information about the original feature. However, CIRF cannot be applied to large-scale biometric identification, since the 2D inverse NTT in the matching phase requires high computational time. Furthermore, existing biometric indexing schemes cannot be used in conjunction with template protection schemes to speed up biometric identification, since a biometric index leaks some information about the original feature. In this paper, we propose a novel indexing scheme called “cancelable indexing” to speed up CIRF without losing its security properties. The proposed scheme is based on fast computation of CIRF via low-rank approximation of biometric images and via a minimum spanning tree representation of low-rank matrices in the Fourier domain. We prove that the transformed index leaks no information about the original index and the original biometric feature (i.e., perfect secrecy), and thoroughly discuss the security of the proposed scheme. We also demonstrate that it significantly reduces the one-to-many matching time using a finger-vein dataset that includes six fingers from 505 subjects.
Tasks
Published	2018-04-05
URL	http://arxiv.org/abs/1804.01670v1
PDF	http://arxiv.org/pdf/1804.01670v1.pdf
PWC	https://paperswithcode.com/paper/cancelable-indexing-based-on-low-rank
Repo
Framework

Learning Optimal Deep Projection of $^{18}$F-FDG PET Imaging for Early Differential Diagnosis of Parkinsonian Syndromes


Title	Learning Optimal Deep Projection of $^{18}$F-FDG PET Imaging for Early Differential Diagnosis of Parkinsonian Syndromes
Authors	Shubham Kumar, Abhijit Guha Roy, Ping Wu, Sailesh Conjeti, R. S. Anand, Jian Wang, Igor Yakushev, Stefan Förster, Markus Schwaiger, Sung-Cheng Huang, Axel Rominger, Chuantao Zuo, Kuangyu Shi
Abstract	Several diseases of parkinsonian syndromes present similar symptoms at early stage and no objective widely used diagnostic methods have been approved until now. Positron emission tomography (PET) with $^{18}$F-FDG was shown to be able to assess early neuronal dysfunction of synucleinopathies and tauopathies. Tensor factorization (TF) based approaches have been applied to identify characteristic metabolic patterns for differential diagnosis. However, these conventional dimension-reduction strategies assume linear or multi-linear relationships inside data, and are therefore insufficient to distinguish nonlinear metabolic differences between various parkinsonian syndromes. In this paper, we propose a Deep Projection Neural Network (DPNN) to identify characteristic metabolic pattern for early differential diagnosis of parkinsonian syndromes. We draw our inspiration from the existing TF methods. The network consists of a (i) compression part: which uses a deep network to learn optimal 2D projections of 3D scans, and a (ii) classification part: which maps the 2D projections to labels. The compression part can be pre-trained using surplus unlabelled datasets. Also, as the classification part operates on these 2D projections, it can be trained end-to-end effectively with limited labelled data, in contrast to 3D approaches. We show that DPNN is more effective in comparison to existing state-of-the-art and plausible baselines.
Tasks	Dimensionality Reduction
Published	2018-10-11
URL	http://arxiv.org/abs/1810.05733v1
PDF	http://arxiv.org/pdf/1810.05733v1.pdf
PWC	https://paperswithcode.com/paper/learning-optimal-deep-projection-of-18f-fdg
Repo
Framework

A Self-Replication Basis for Designing Complex Agents


Title	A Self-Replication Basis for Designing Complex Agents
Authors	Thommen George Karimpanal
Abstract	In this work, we describe a self-replication-based mechanism for designing agents of increasing complexity. We demonstrate the validity of this approach by solving simple, standard evolutionary computation problems in simulation. In the context of these simulation results, we describe the fundamental differences of this approach when compared to traditional approaches. Further, we highlight the possible advantages of applying this approach to the problem of designing complex artificial agents, along with the potential drawbacks and issues to be addressed in the future.
Tasks
Published	2018-05-18
URL	http://arxiv.org/abs/1806.06010v1
PDF	http://arxiv.org/pdf/1806.06010v1.pdf
PWC	https://paperswithcode.com/paper/a-self-replication-basis-for-designing
Repo
Framework

Improving Multilingual Semantic Textual Similarity with Shared Sentence Encoder for Low-resource Languages


Title	Improving Multilingual Semantic Textual Similarity with Shared Sentence Encoder for Low-resource Languages
Authors	Xin Tang, Shanbo Cheng, Loc Do, Zhiyu Min, Feng Ji, Heng Yu, Ji Zhang, Haiqin Chen
Abstract	Measuring the semantic similarity between two sentences (or Semantic Textual Similarity - STS) is fundamental in many NLP applications. Despite the remarkable results in supervised settings with adequate labeling, little attention has been paid to this task in low-resource languages with insufficient labeling. Existing approaches mostly leverage machine translation techniques to translate sentences into rich-resource language. These approaches either beget language biases, or be impractical in industrial applications where spoken language scenario is more often and rigorous efficiency is required. In this work, we propose a multilingual framework to tackle the STS task in a low-resource language e.g. Spanish, Arabic , Indonesian and Thai, by utilizing the rich annotation data in a rich resource language, e.g. English. Our approach is extended from a basic monolingual STS framework to a shared multilingual encoder pretrained with translation task to incorporate rich-resource language data. By exploiting the nature of a shared multilingual encoder, one sentence can have multiple representations for different target translation language, which are used in an ensemble model to improve similarity evaluation. We demonstrate the superiority of our method over other state of the art approaches on SemEval STS task by its significant improvement on non-MT method, as well as an online industrial product where MT method fails to beat baseline while our approach still has consistently improvements.
Tasks	Machine Translation, Semantic Similarity, Semantic Textual Similarity
Published	2018-10-20
URL	http://arxiv.org/abs/1810.08740v2
PDF	http://arxiv.org/pdf/1810.08740v2.pdf
PWC	https://paperswithcode.com/paper/improving-multilingual-semantic-textual
Repo
Framework

Topic representation: finding more representative words in topic models


Title	Topic representation: finding more representative words in topic models
Authors	Jinjin Chi, Jihong Ouyang, Changchun Li, Xueyang Dong, Ximing Li, Xinhua Wang
Abstract	The top word list, i.e., the top-M words with highest marginal probability in a given topic, is the standard topic representation in topic models. Most of recent automatical topic labeling algorithms and popular topic quality metrics are based on it. However, we find, empirically, words in this type of top word list are not always representative. The objective of this paper is to find more representative top word lists for topics. To achieve this, we rerank the words in a given topic by further considering marginal probability on words over every other topic. The reranking list of top-M words is used to be a novel topic representation for topic models. We investigate three reranking methodologies, using (1) standard deviation weight, (2) standard deviation weight with topic size and (3) Chi Square \c{hi}2statistic selection. Experimental results on real world collections indicate that our representations can extract more representative words for topics, agreeing with human judgements.
Tasks	Topic Models
Published	2018-10-23
URL	http://arxiv.org/abs/1810.10307v1
PDF	http://arxiv.org/pdf/1810.10307v1.pdf
PWC	https://paperswithcode.com/paper/topic-representation-finding-more
Repo
Framework

Classification and Disease Localization in Histopathology Using Only Global Labels: A Weakly-Supervised Approach


Title	Classification and Disease Localization in Histopathology Using Only Global Labels: A Weakly-Supervised Approach
Authors	Pierre Courtiol, Eric W. Tramel, Marc Sanselme, Gilles Wainrib
Abstract	Analysis of histopathology slides is a critical step for many diagnoses, and in particular in oncology where it defines the gold standard. In the case of digital histopathological analysis, highly trained pathologists must review vast whole-slide-images of extreme digital resolution ($100,000^2$ pixels) across multiple zoom levels in order to locate abnormal regions of cells, or in some cases single cells, out of millions. The application of deep learning to this problem is hampered not only by small sample sizes, as typical datasets contain only a few hundred samples, but also by the generation of ground-truth localized annotations for training interpretable classification and segmentation models. We propose a method for disease localization in the context of weakly supervised learning, where only image-level labels are available during training. Even without pixel-level annotations, we are able to demonstrate performance comparable with models trained with strong annotations on the Camelyon-16 lymph node metastases detection challenge. We accomplish this through the use of pre-trained deep convolutional networks, feature embedding, as well as learning via top instances and negative evidence, a multiple instance learning technique from the field of semantic segmentation and object detection.
Tasks	Multiple Instance Learning, Object Detection, Semantic Segmentation
Published	2018-02-01
URL	https://arxiv.org/abs/1802.02212v2
PDF	https://arxiv.org/pdf/1802.02212v2.pdf
PWC	https://paperswithcode.com/paper/classification-and-disease-localization-in
Repo
Framework

Object Counts! Bringing Explicit Detections Back into Image Captioning


Title	Object Counts! Bringing Explicit Detections Back into Image Captioning
Authors	Josiah Wang, Pranava Madhyastha, Lucia Specia
Abstract	The use of explicit object detectors as an intermediate step to image captioning - which used to constitute an essential stage in early work - is often bypassed in the currently dominant end-to-end approaches, where the language model is conditioned directly on a mid-level image embedding. We argue that explicit detections provide rich semantic information, and can thus be used as an interpretable representation to better understand why end-to-end image captioning systems work well. We provide an in-depth analysis of end-to-end image captioning by exploring a variety of cues that can be derived from such object detections. Our study reveals that end-to-end image captioning systems rely on matching image representations to generate captions, and that encoding the frequency, size and position of objects are complementary and all play a role in forming a good image representation. It also reveals that different object categories contribute in different ways towards image captioning.
Tasks	Image Captioning, Language Modelling
Published	2018-04-23
URL	http://arxiv.org/abs/1805.00314v1
PDF	http://arxiv.org/pdf/1805.00314v1.pdf
PWC	https://paperswithcode.com/paper/object-counts-bringing-explicit-detections
Repo
Framework

Progressive Sampling-Based Bayesian Optimization for Efficient and Automatic Machine Learning Model Selection


Title	Progressive Sampling-Based Bayesian Optimization for Efficient and Automatic Machine Learning Model Selection
Authors	Xueqiang Zeng, Gang Luo
Abstract	Purpose: Machine learning is broadly used for clinical data analysis. Before training a model, a machine learning algorithm must be selected. Also, the values of one or more model parameters termed hyper-parameters must be set. Selecting algorithms and hyper-parameter values requires advanced machine learning knowledge and many labor-intensive manual iterations. To lower the bar to machine learning, miscellaneous automatic selection methods for algorithms and/or hyper-parameter values have been proposed. Existing automatic selection methods are inefficient on large data sets. This poses a challenge for using machine learning in the clinical big data era. Methods: To address the challenge, this paper presents progressive sampling-based Bayesian optimization, an efficient and automatic selection method for both algorithms and hyper-parameter values. Results: We report an implementation of the method. We show that compared to a state of the art automatic selection method, our method can significantly reduce search time, classification error rate, and standard deviation of error rate due to randomization. Conclusions: This is major progress towards enabling fast turnaround in identifying high-quality solutions required by many machine learning-based clinical data analysis tasks.
Tasks	Automatic Machine Learning Model Selection, Model Selection
Published	2018-12-06
URL	http://arxiv.org/abs/1812.02855v1
PDF	http://arxiv.org/pdf/1812.02855v1.pdf
PWC	https://paperswithcode.com/paper/progressive-sampling-based-bayesian
Repo
Framework

A Multi-component CNN-RNN Approach for Dimensional Emotion Recognition in-the-wild


Title	A Multi-component CNN-RNN Approach for Dimensional Emotion Recognition in-the-wild
Authors	Dimitrios Kollias, Stefanos Zafeiriou
Abstract	This paper presents our approach to the One-Minute Gradual-Emotion Recognition (OMG-Emotion) Challenge, focusing on dimensional emotion recognition through visual analysis of the provided emotion videos. The approach is based on a Convolutional and Recurrent (CNN-RNN) deep neural architecture we have developed for the relevant large AffWild Emotion Database. We extended and adapted this architecture, by letting a combination of multiple features generated in the CNN component be explored by RNN subnets. Our target has been to obtain best performance on the OMG-Emotion visual validation data set, while learning the respective visual training data set. Extended experimentation has led to best architectures for the estimation of the values of the valence and arousal emotion dimensions over these data sets.
Tasks	Emotion Recognition
Published	2018-05-03
URL	https://arxiv.org/abs/1805.01452v5
PDF	https://arxiv.org/pdf/1805.01452v5.pdf
PWC	https://paperswithcode.com/paper/a-multi-component-cnn-rnn-approach-for
Repo
Framework