January 31, 2020

2998 words 15 mins read

Paper Group ANR 60

Spatiotemporal PET reconstruction using ML-EM with learned diffeomorphic deformation. Adversarial Learning of General Transformations for Data Augmentation. Improving Heart Rate Variability Measurements from Consumer Smartwatches with Machine Learning. Augmenting Physiological Time Series Data: A Case Study for Sleep Apnea Detection. Transformer-ba …

Spatiotemporal PET reconstruction using ML-EM with learned diffeomorphic deformation


Title	Spatiotemporal PET reconstruction using ML-EM with learned diffeomorphic deformation
Authors	Ozan Öktem, Camille Pouchol, Olivier Verdier
Abstract	Patient movement in emission tomography deteriorates reconstruction quality because of motion blur. Gating the data improves the situation somewhat: each gate contains a movement phase which is approximately stationary. A standard method is to use only the data from a few gates, with little movement between them. However, the corresponding loss of data entails an increase of noise. Motion correction algorithms have been implemented to take into account all the gated data, but they do not scale well, especially not in 3D. We propose a novel motion correction algorithm which addresses the scalability issue. Our approach is to combine an enhanced ML-EM algorithm with deep learning based movement registration. The training is unsupervised, and with artificial data. We expect this approach to scale very well to higher resolutions and to 3D, as the overall cost of our algorithm is only marginally greater than that of a standard ML-EM algorithm. We show that we can significantly decrease the noise corresponding to a limited number of gates.
Tasks
Published	2019-08-26
URL	https://arxiv.org/abs/1908.09515v1
PDF	https://arxiv.org/pdf/1908.09515v1.pdf
PWC	https://paperswithcode.com/paper/spatiotemporal-pet-reconstruction-using-ml-em
Repo
Framework

Adversarial Learning of General Transformations for Data Augmentation


Title	Adversarial Learning of General Transformations for Data Augmentation
Authors	Saypraseuth Mounsaveng, David Vazquez, Ismail Ben Ayed, Marco Pedersoli
Abstract	Data augmentation (DA) is fundamental against overfitting in large convolutional neural networks, especially with a limited training dataset. In images, DA is usually based on heuristic transformations, like geometric or color transformations. Instead of using predefined transformations, our work learns data augmentation directly from the training data by learning to transform images with an encoder-decoder architecture combined with a spatial transformer network. The transformed images still belong to the same class but are new, more complex samples for the classifier. Our experiments show that our approach is better than previous generative data augmentation methods, and comparable to predefined transformation methods when training an image classifier.
Tasks	Data Augmentation
Published	2019-09-21
URL	https://arxiv.org/abs/1909.09801v1
PDF	https://arxiv.org/pdf/1909.09801v1.pdf
PWC	https://paperswithcode.com/paper/190909801
Repo
Framework

Improving Heart Rate Variability Measurements from Consumer Smartwatches with Machine Learning


Title	Improving Heart Rate Variability Measurements from Consumer Smartwatches with Machine Learning
Authors	Martin Maritsch, Caterina Bérubé, Mathias Kraus, Vera Lehmann, Thomas Züger, Stefan Feuerriegel, Tobias Kowatsch, Felix Wortmann
Abstract	The reactions of the human body to physical exercise, psychophysiological stress and heart diseases are reflected in heart rate variability (HRV). Thus, continuous monitoring of HRV can contribute to determining and predicting issues in well-being and mental health. HRV can be measured in everyday life by consumer wearable devices such as smartwatches which are easily accessible and affordable. However, they are arguably accurate due to the stability of the sensor. We hypothesize a systematic error which is related to the wearer movement. Our evidence builds upon explanatory and predictive modeling: we find a statistically significant correlation between error in HRV measurements and the wearer movement. We show that this error can be minimized by bringing into context additional available sensor information, such as accelerometer data. This work demonstrates our research-in-progress on how neural learning can minimize the error of such smartwatch HRV measurements.
Tasks	Heart Rate Variability
Published	2019-07-17
URL	https://arxiv.org/abs/1907.07496v1
PDF	https://arxiv.org/pdf/1907.07496v1.pdf
PWC	https://paperswithcode.com/paper/improving-heart-rate-variability-measurements
Repo
Framework

Augmenting Physiological Time Series Data: A Case Study for Sleep Apnea Detection


Title	Augmenting Physiological Time Series Data: A Case Study for Sleep Apnea Detection
Authors	Konstantinos Nikolaidis, Stein Kristiansen, Vera Goebel, Thomas Plagemann, Knut Liestøl, Mohan Kankanhalli
Abstract	Supervised machine learning applications in the health domain often face the problem of insufficient training datasets. The quantity of labelled data is small due to privacy concerns and the cost of data acquisition and labelling by a medical expert. Furthermore, it is quite common that collected data are unbalanced and getting enough data to personalize models for individuals is very expensive or even infeasible. This paper addresses these problems by (1) designing a recurrent Generative Adversarial Network to generate realistic synthetic data and to augment the original dataset, (2) enabling the generation of balanced datasets based on heavily unbalanced dataset, and (3) to control the data generation in such a way that the generated data resembles data from specific individuals. We apply these solutions for sleep apnea detection and study in the evaluation the performance of four well-known techniques, i.e., K-Nearest Neighbour, Random Forest, Multi-Layer Perceptron, and Support Vector Machine. All classifiers exhibit in the experiments a consistent increase in sensitivity and a kappa statistic increase by between 0.007 and 0.182.
Tasks	Sleep apnea detection, Time Series
Published	2019-05-22
URL	https://arxiv.org/abs/1905.09068v1
PDF	https://arxiv.org/pdf/1905.09068v1.pdf
PWC	https://paperswithcode.com/paper/augmenting-physiological-time-series-data-a
Repo
Framework

Transformer-based Cascaded Multimodal Speech Translation


Title	Transformer-based Cascaded Multimodal Speech Translation
Authors	Zixiu Wu, Ozan Caglayan, Julia Ive, Josiah Wang, Lucia Specia
Abstract	This paper describes the cascaded multimodal speech translation systems developed by Imperial College London for the IWSLT 2019 evaluation campaign. The architecture consists of an automatic speech recognition (ASR) system followed by a Transformer-based multimodal machine translation (MMT) system. While the ASR component is identical across the experiments, the MMT model varies in terms of the way of integrating the visual context (simple conditioning vs. attention), the type of visual features exploited (pooled, convolutional, action categories) and the underlying architecture. For the latter, we explore both the canonical transformer and its deliberation version with additive and cascade variants which differ in how they integrate the textual attention. Upon conducting extensive experiments, we found that (i) the explored visual integration schemes often harm the translation performance for the transformer and additive deliberation, but considerably improve the cascade deliberation; (ii) the transformer and cascade deliberation integrate the visual modality better than the additive deliberation, as shown by the incongruence analysis.
Tasks	Machine Translation, Multimodal Machine Translation, Speech Recognition
Published	2019-10-29
URL	https://arxiv.org/abs/1910.13215v3
PDF	https://arxiv.org/pdf/1910.13215v3.pdf
PWC	https://paperswithcode.com/paper/191013215
Repo
Framework

What does BERT Learn from Multiple-Choice Reading Comprehension Datasets?


Title	What does BERT Learn from Multiple-Choice Reading Comprehension Datasets?
Authors	Chenglei Si, Shuohang Wang, Min-Yen Kan, Jing Jiang
Abstract	Multiple-Choice Reading Comprehension (MCRC) requires the model to read the passage and question, and select the correct answer among the given options. Recent state-of-the-art models have achieved impressive performance on multiple MCRC datasets. However, such performance may not reflect the model’s true ability of language understanding and reasoning. In this work, we adopt two approaches to investigate what BERT learns from MCRC datasets: 1) an un-readable data attack, in which we add keywords to confuse BERT, leading to a significant performance drop; and 2) an un-answerable data training, in which we train BERT on partial or shuffled input. Under un-answerable data training, BERT achieves unexpectedly high performance. Based on our experiments on the 5 key MCRC datasets - RACE, MCTest, MCScript, MCScript2.0, DREAM - we observe that 1) fine-tuned BERT mainly learns how keywords lead to correct prediction, instead of learning semantic understanding and reasoning; and 2) BERT does not need correct syntactic information to solve the task; 3) there exists artifacts in these datasets such that they can be solved even without the full context.
Tasks	Reading Comprehension
Published	2019-10-28
URL	https://arxiv.org/abs/1910.12391v1
PDF	https://arxiv.org/pdf/1910.12391v1.pdf
PWC	https://paperswithcode.com/paper/what-does-bert-learn-from-multiple-choice
Repo
Framework

Tight Regret Bounds for Model-Based Reinforcement Learning with Greedy Policies


Title	Tight Regret Bounds for Model-Based Reinforcement Learning with Greedy Policies
Authors	Yonathan Efroni, Nadav Merlis, Mohammad Ghavamzadeh, Shie Mannor
Abstract	State-of-the-art efficient model-based Reinforcement Learning (RL) algorithms typically act by iteratively solving empirical models, i.e., by performing \emph{full-planning} on Markov Decision Processes (MDPs) built by the gathered experience. In this paper, we focus on model-based RL in the finite-state finite-horizon MDP setting and establish that exploring with \emph{greedy policies} – act by \emph{1-step planning} – can achieve tight minimax performance in terms of regret, $\tilde{\mathcal{O}}(\sqrt{HSAT})$. Thus, full-planning in model-based RL can be avoided altogether without any performance degradation, and, by doing so, the computational complexity decreases by a factor of $S$. The results are based on a novel analysis of real-time dynamic programming, then extended to model-based RL. Specifically, we generalize existing algorithms that perform full-planning to such that act by 1-step planning. For these generalizations, we prove regret bounds with the same rate as their full-planning counterparts.
Tasks
Published	2019-05-27
URL	https://arxiv.org/abs/1905.11527v2
PDF	https://arxiv.org/pdf/1905.11527v2.pdf
PWC	https://paperswithcode.com/paper/tight-regret-bounds-for-model-based
Repo
Framework

Achieving Generalizable Robustness of Deep Neural Networks by Stability Training


Title	Achieving Generalizable Robustness of Deep Neural Networks by Stability Training
Authors	Jan Laermann, Wojciech Samek, Nils Strodthoff
Abstract	We study the recently introduced stability training as a general-purpose method to increase the robustness of deep neural networks against input perturbations. In particular, we explore its use as an alternative to data augmentation and validate its performance against a number of distortion types and transformations including adversarial examples. In our image classification experiments using ImageNet data stability training performs on a par or even outperforms data augmentation for specific transformations, while consistently offering improved robustness against a broader range of distortion strengths and types unseen during training, a considerably smaller hyperparameter dependence and less potentially negative side effects compared to data augmentation.
Tasks	Data Augmentation, Image Classification
Published	2019-06-03
URL	https://arxiv.org/abs/1906.00735v2
PDF	https://arxiv.org/pdf/1906.00735v2.pdf
PWC	https://paperswithcode.com/paper/190600735
Repo
Framework

Spectral Graph Transformer Networks for Brain Surface Parcellation


Title	Spectral Graph Transformer Networks for Brain Surface Parcellation
Authors	Ran He, Karthik Gopinath, Christian Desrosiers, Herve Lombaert
Abstract	The analysis of the brain surface modeled as a graph mesh is a challenging task. Conventional deep learning approaches often rely on data lying in the Euclidean space. As an extension to irregular graphs, convolution operations are defined in the Fourier or spectral domain. This spectral domain is obtained by decomposing the graph Laplacian, which captures relevant shape information. However, the spectral decomposition across different brain graphs causes inconsistencies between the eigenvectors of individual spectral domains, causing the graph learning algorithm to fail. Current spectral graph convolution methods handle this variance by separately aligning the eigenvectors to a reference brain in a slow iterative step. This paper presents a novel approach for learning the transformation matrix required for aligning brain meshes using a direct data-driven approach. Our alignment and graph processing method provides a fast analysis of brain surfaces. The novel Spectral Graph Transformer (SGT) network proposed in this paper uses very few randomly sub-sampled nodes in the spectral domain to learn the alignment matrix for multiple brain surfaces. We validate the use of this SGT network along with a graph convolution network to perform cortical parcellation. Our method on 101 manually-labeled brain surfaces shows improved parcellation performance over a no-alignment strategy, gaining a significant speed (1400 fold) over traditional iterative alignment approaches.
Tasks
Published	2019-11-22
URL	https://arxiv.org/abs/1911.10118v1
PDF	https://arxiv.org/pdf/1911.10118v1.pdf
PWC	https://paperswithcode.com/paper/spectral-graph-transformer-networks-for-brain
Repo
Framework

Targetless Rotational Auto-Calibration of Radar and Camera for Intelligent Transportation Systems


Title	Targetless Rotational Auto-Calibration of Radar and Camera for Intelligent Transportation Systems
Authors	Christoph Schöller, Maximilian Schnettler, Annkathrin Krämmer, Gereon Hinz, Maida Bakovic, Müge Güzet, Alois Knoll
Abstract	Most intelligent transportation systems use a combination of radar sensors and cameras for robust vehicle perception. The calibration of these heterogeneous sensor types in an automatic fashion during system operation is challenging due to differing physical measurement principles and the high sparsity of traffic radars. We propose - to the best of our knowledge - the first data-driven method for automatic rotational radar-camera calibration without dedicated calibration targets. Our approach is based on a coarse and a fine convolutional neural network. We employ a boosting-inspired training algorithm, where we train the fine network on the residual error of the coarse network. Due to the unavailability of public datasets combining radar and camera measurements, we recorded our own real-world data. We demonstrate that our method is able to reach precise and robust sensor registration and show its generalization capabilities to different sensor alignments and perspectives.
Tasks	Calibration
Published	2019-04-18
URL	https://arxiv.org/abs/1904.08743v2
PDF	https://arxiv.org/pdf/1904.08743v2.pdf
PWC	https://paperswithcode.com/paper/targetless-rotational-auto-calibration-of
Repo
Framework

Tightening Mutual Information Based Bounds on Generalization Error


Title	Tightening Mutual Information Based Bounds on Generalization Error
Authors	Yuheng Bu, Shaofeng Zou, Venugopal V. Veeravalli
Abstract	A mutual information based upper bound on the generalization error of a supervised learning algorithm is derived in this paper. The bound is constructed in terms of the mutual information between each individual training sample and the output of the learning algorithm, which requires weaker conditions on the loss function, but provides a tighter characterization of the generalization error than existing studies. Examples are further provided to demonstrate that the bound derived in this paper is tighter, and has a broader range of applicability. Application to noisy and iterative algorithms, e.g., stochastic gradient Langevin dynamics (SGLD), is also studied, where the constructed bound provides a tighter characterization of the generalization error than existing results.
Tasks
Published	2019-01-15
URL	http://arxiv.org/abs/1901.04609v1
PDF	http://arxiv.org/pdf/1901.04609v1.pdf
PWC	https://paperswithcode.com/paper/tightening-mutual-information-based-bounds-on
Repo
Framework

PrTransH: Embedding Probabilistic Medical Knowledge from Real World EMR Data


Title	PrTransH: Embedding Probabilistic Medical Knowledge from Real World EMR Data
Authors	Linfeng Li, Peng Wang, Yao Wang, Jinpeng Jiang, Buzhou Tang, Jun Yan, Shenghui Wang, Yuting Liu
Abstract	This paper proposes an algorithm named as PrTransH to learn embedding vectors from real world EMR data based medical knowledge. The unique challenge in embedding medical knowledge graph from real world EMR data is that the uncertainty of knowledge triplets blurs the border between “correct triplet” and “wrong triplet”, changing the fundamental assumption of many existing algorithms. To address the challenge, some enhancements are made to existing TransH algorithm, including: 1) involve probability of medical knowledge triplet into training objective; 2) replace the margin-based ranking loss with unified loss calculation considering both valid and corrupted triplets; 3) augment training data set with medical background knowledge. Verifications on real world EMR data based medical knowledge graph prove that PrTransH outperforms TransH in link prediction task. To the best of our survey, this paper is the first one to learn and verify knowledge embedding on probabilistic knowledge graphs.
Tasks	Knowledge Graphs, Link Prediction
Published	2019-09-02
URL	https://arxiv.org/abs/1909.00672v1
PDF	https://arxiv.org/pdf/1909.00672v1.pdf
PWC	https://paperswithcode.com/paper/prtransh-embedding-probabilistic-medical
Repo
Framework

Learning Extreme Hummingbird Maneuvers on Flapping Wing Robots


Title	Learning Extreme Hummingbird Maneuvers on Flapping Wing Robots
Authors	Fan Fei, Zhan Tu, Jian Zhang, Xinyan Deng
Abstract	Biological studies show that hummingbirds can perform extreme aerobatic maneuvers during fast escape. Given a sudden looming visual stimulus at hover, a hummingbird initiates a fast backward translation coupled with a 180-degree yaw turn, which is followed by instant posture stabilization in just under 10 wingbeats. Consider the wingbeat frequency of 40Hz, this aggressive maneuver is carried out in just 0.2 seconds. Inspired by the hummingbirds’ near-maximal performance during such extreme maneuvers, we developed a flight control strategy and experimentally demonstrated that such maneuverability can be achieved by an at-scale 12-gram hummingbird robot equipped with just two actuators. The proposed hybrid control policy combines model-based nonlinear control with model-free reinforcement learning. We use model-based nonlinear control for nominal flight control, as the dynamic model is relatively accurate for these conditions. However, during extreme maneuver, the modeling error becomes unmanageable. A model-free reinforcement learning policy trained in simulation was optimized to ‘destabilize’ the system and maximize the performance during maneuvering. The hybrid policy manifests a maneuver that is close to that observed in hummingbirds. Direct simulation-to-real transfer is achieved, demonstrating the hummingbird-like fast evasive maneuvers on the at-scale hummingbird robot.
Tasks
Published	2019-02-25
URL	http://arxiv.org/abs/1902.09626v1
PDF	http://arxiv.org/pdf/1902.09626v1.pdf
PWC	https://paperswithcode.com/paper/learning-extreme-hummingbird-maneuvers-on
Repo
Framework

Learning an Interpretable Traffic Signal Control Policy


Title	Learning an Interpretable Traffic Signal Control Policy
Authors	James Ault, Josiah P. Hanna, Guni Sharon
Abstract	Signalized intersections are managed by controllers that assign right of way (green, yellow, and red lights) to non-conflicting directions. Optimizing the actuation policy of such controllers is expected to alleviate traffic congestion and its adverse impact. Given such a safety-critical domain, the affiliated actuation policy is required to be interpretable in a way that can be understood and regulated by a human. This paper presents and analyzes several on-line optimization techniques for tuning interpretable control functions. Although these techniques are defined in a general way, this paper assumes a specific class of interpretable control functions (polynomial functions) for analysis purposes. We show that such an interpretable policy function can be as effective as a deep neural network for approximating an optimized signal actuation policy. We present empirical evidence that supports the use of value-based reinforcement learning for on-line training of the control function. Specifically, we present and study three variants of the Deep Q-learning algorithm that allow the training of an interpretable policy function. Our Deep Regulatable Hardmax Q-learning variant is shown to be particularly effective in optimizing our interpretable actuation policy, resulting in up to 19.4% reduced vehicles delay compared to commonly deployed actuated signal controllers.
Tasks	Q-Learning
Published	2019-12-23
URL	https://arxiv.org/abs/1912.11023v2
PDF	https://arxiv.org/pdf/1912.11023v2.pdf
PWC	https://paperswithcode.com/paper/learning-an-interpretable-traffic-signal
Repo
Framework

FIRE: Unsupervised bi-directional inter-modality registration using deep networks


Title	FIRE: Unsupervised bi-directional inter-modality registration using deep networks
Authors	Chengjia Wang, Giorgos Papanastasiou, Agisilaos Chartsias, Grzegorz Jacenkow, Sotirios A. Tsaftaris, Heye Zhang
Abstract	Inter-modality image registration is an critical preprocessing step for many applications within the routine clinical pathway. This paper presents an unsupervised deep inter-modality registration network that can learn the optimal affine and non-rigid transformations simultaneously. Inverse-consistency is an important property commonly ignored in recent deep learning based inter-modality registration algorithms. We address this issue through the proposed multi-task architecture and the new comprehensive transformation network. Specifically, the proposed model learns a modality-independent latent representation to perform cycle-consistent cross-modality synthesis, and use an inverse-consistent loss to learn a pair of transformations to align the synthesized image with the target. We name this proposed framework as FIRE due to the shape of its structure. Our method shows comparable and better performances with the popular baseline method in experiments on multi-sequence brain MR data and intra-modality 4D cardiac Cine-MR data.
Tasks	Image Registration
Published	2019-07-11
URL	https://arxiv.org/abs/1907.05062v1
PDF	https://arxiv.org/pdf/1907.05062v1.pdf
PWC	https://paperswithcode.com/paper/fire-unsupervised-bi-directional-inter
Repo
Framework