October 16, 2019

2970 words 14 mins read

Paper Group ANR 1002

Predicting Blood Glucose with an LSTM and Bi-LSTM Based Deep Neural Network. Cosmic String Detection with Tree-Based Machine Learning. Dynamic Filtering with Large Sampling Field for ConvNets. Linear solution to the minimal absolute pose rolling shutter problem. Transformation on Computer-Generated Facial Image to Avoid Detection by Spoofing Detect …

Predicting Blood Glucose with an LSTM and Bi-LSTM Based Deep Neural Network


Title	Predicting Blood Glucose with an LSTM and Bi-LSTM Based Deep Neural Network
Authors	Qingnan Sun, Marko V. Jankovic, Lia Bally, Stavroula G. Mougiakakou
Abstract	A deep learning network was used to predict future blood glucose levels, as this can permit diabetes patients to take action before imminent hyperglycaemia and hypoglycaemia. A sequential model with one long-short-term memory (LSTM) layer, one bidirectional LSTM layer and several fully connected layers was used to predict blood glucose levels for different prediction horizons. The method was trained and tested on 26 datasets from 20 real patients. The proposed network outperforms the baseline methods in terms of all evaluation criteria.
Tasks
Published	2018-09-11
URL	http://arxiv.org/abs/1809.03817v1
PDF	http://arxiv.org/pdf/1809.03817v1.pdf
PWC	https://paperswithcode.com/paper/predicting-blood-glucose-with-an-lstm-and-bi
Repo
Framework

Cosmic String Detection with Tree-Based Machine Learning


Title	Cosmic String Detection with Tree-Based Machine Learning
Authors	A. Vafaei Sadr, M. Farhang, S. M. S. Movahed, B. Bassett, M. Kunz
Abstract	We explore the use of random forest and gradient boosting, two powerful tree-based machine learning algorithms, for the detection of cosmic strings in maps of the cosmic microwave background (CMB), through their unique Gott-Kaiser-Stebbins effect on the temperature anisotropies.The information in the maps is compressed into feature vectors before being passed to the learning units. The feature vectors contain various statistical measures of processed CMB maps that boost the cosmic string detectability. Our proposed classifiers, after training, give results improved over or similar to the claimed detectability levels of the existing methods for string tension, $G\mu$. They can make $3\sigma$ detection of strings with $G\mu \gtrsim 2.1\times 10^{-10}$ for noise-free, $0.9'$-resolution CMB observations. The minimum detectable tension increases to $G\mu \gtrsim 3.0\times 10^{-8}$ for a more realistic, CMB S4-like (II) strategy, still a significant improvement over the previous results.
Tasks
Published	2018-01-12
URL	http://arxiv.org/abs/1801.04140v1
PDF	http://arxiv.org/pdf/1801.04140v1.pdf
PWC	https://paperswithcode.com/paper/cosmic-string-detection-with-tree-based
Repo
Framework

Dynamic Filtering with Large Sampling Field for ConvNets


Title	Dynamic Filtering with Large Sampling Field for ConvNets
Authors	Jialin Wu, Dai Li, Yu Yang, Chandrajit Bajaj, Xiangyang Ji
Abstract	We propose a dynamic filtering strategy with large sampling field for ConvNets (LS-DFN), where the position-specific kernels learn from not only the identical position but also multiple sampled neighbor regions. During sampling, residual learning is introduced to ease training and an attention mechanism is applied to fuse features from different samples. Such multiple samples enlarge the kernels’ receptive fields significantly without requiring more parameters. While LS-DFN inherits the advantages of DFN, namely avoiding feature map blurring by position-wise kernels while keeping translation invariance, it also efficiently alleviates the overfitting issue caused by much more parameters than normal CNNs. Our model is efficient and can be trained end-to-end via standard back-propagation. We demonstrate the merits of our LS-DFN on both sparse and dense prediction tasks involving object detection, semantic segmentation, and flow estimation. Our results show LS-DFN enjoys stronger recognition abilities in object detection and semantic segmentation tasks on VOC benchmark and sharper responses in flow estimation on FlyingChairs dataset compared to strong baselines.
Tasks	Object Detection, Semantic Segmentation
Published	2018-03-20
URL	https://arxiv.org/abs/1803.07624v3
PDF	https://arxiv.org/pdf/1803.07624v3.pdf
PWC	https://paperswithcode.com/paper/dynamic-sampling-convolutional-neural
Repo
Framework

Linear solution to the minimal absolute pose rolling shutter problem


Title	Linear solution to the minimal absolute pose rolling shutter problem
Authors	Zuzana Kukelova, Cenek Albl, Akihiro Sugimoto, Tomas Pajdla
Abstract	This paper presents new efficient solutions to the rolling shutter camera absolute pose problem. Unlike the state-of-the-art polynomial solvers, we approach the problem using simple and fast linear solvers in an iterative scheme. We present several solutions based on fixing different sets of variables and investigate the performance of them thoroughly. We design a new alternation strategy that estimates all parameters in each iteration linearly by fixing just the non-linear terms. Our best 6-point solver, based on the new alternation technique, shows an identical or even better performance than the state-of-the-art R6P solver and is two orders of magnitude faster. In addition, a linear non-iterative solver is presented that requires a non-minimal number of 9 correspondences but provides even better results than the state-of-the-art R6P. Moreover, all proposed linear solvers provide a single solution while the state-of-the-art R6P provides up to 20 solutions which have to be pruned by expensive verification.
Tasks
Published	2018-12-30
URL	http://arxiv.org/abs/1812.11532v1
PDF	http://arxiv.org/pdf/1812.11532v1.pdf
PWC	https://paperswithcode.com/paper/linear-solution-to-the-minimal-absolute-pose
Repo
Framework

Transformation on Computer-Generated Facial Image to Avoid Detection by Spoofing Detector


Title	Transformation on Computer-Generated Facial Image to Avoid Detection by Spoofing Detector
Authors	Huy H. Nguyen, Ngoc-Dung T. Tieu, Hoang-Quoc Nguyen-Son, Junichi Yamagishi, Isao Echizen
Abstract	Making computer-generated (CG) images more difficult to detect is an interesting problem in computer graphics and security. While most approaches focus on the image rendering phase, this paper presents a method based on increasing the naturalness of CG facial images from the perspective of spoofing detectors. The proposed method is implemented using a convolutional neural network (CNN) comprising two autoencoders and a transformer and is trained using a black-box discriminator without gradient information. Over 50% of the transformed CG images were not detected by three state-of-the-art spoofing detectors. This capability raises an alarm regarding the reliability of facial authentication systems, which are becoming widely used in daily life.
Tasks
Published	2018-04-12
URL	http://arxiv.org/abs/1804.04418v1
PDF	http://arxiv.org/pdf/1804.04418v1.pdf
PWC	https://paperswithcode.com/paper/transformation-on-computer-generated-facial
Repo
Framework

A fully automated framework for lung tumour detection, segmentation and analysis


Title	A fully automated framework for lung tumour detection, segmentation and analysis
Authors	Devesh Walawalkar
Abstract	Early and correct diagnosis is a very important aspect of cancer treatment. Detection of tumour in Computed Tomography scan is a tedious and tricky task which requires expert knowledge and a lot of human working hours. As small human error is present in any work he does, it is possible that a CT scan could be misdiagnosed causing the patient to become terminal. This paper introduces a novel fully automated framework which helps to detect and segment tumour, if present in a lung CT scan series. It also provides useful analysis of the detected tumour such as its approximate volume, centre location and more. The framework provides a single click solution which analyses all CT images of a single patient series in one go. It helps to reduce the work of manually going through each CT slice and provides quicker and more accurate tumour diagnosis. It makes use of customized image processing and image segmentation methods, to detect and segment the prospective tumour region from the CT scan. It then uses a trained ensemble classifier to correctly classify the segmented region as being tumour or not. Tumour analysis further computed can then be used to determine malignity of the tumour. With an accuracy of 98.14%, the implemented framework can be used in various practical scenarios, capable of eliminating need of any expert pathologist intervention.
Tasks	Semantic Segmentation
Published	2018-01-04
URL	http://arxiv.org/abs/1801.01402v1
PDF	http://arxiv.org/pdf/1801.01402v1.pdf
PWC	https://paperswithcode.com/paper/a-fully-automated-framework-for-lung-tumour
Repo
Framework

PartsNet: A Unified Deep Network for Automotive Engine Precision Parts Defect Detection


Title	PartsNet: A Unified Deep Network for Automotive Engine Precision Parts Defect Detection
Authors	Zhenshen Qu, Jianxiong Shen, Ruikun Li, Junyu Liu, Qiuyu Guan
Abstract	Defect detection is a basic and essential task in automatic parts production, especially for automotive engine precision parts. In this paper, we propose a new idea to construct a deep convolutional network combining related knowledge of feature processing and the representation ability of deep learning. Our algorithm consists of a pixel-wise segmentation Deep Neural Network (DNN) and a feature refining network. The fully convolutional DNN is presented to learn basic features of parts defects. After that, several typical traditional methods which are used to refine the segmentation results are transformed into convolutional manners and integrated. We assemble these methods as a shallow network with fixed weights and empirical thresholds. These thresholds are then released to enhance its adaptation ability and realize end-to-end training. Testing results on different datasets show that the proposed method has good portability and outperforms the state-of-the-art algorithms.
Tasks
Published	2018-10-29
URL	http://arxiv.org/abs/1810.12061v1
PDF	http://arxiv.org/pdf/1810.12061v1.pdf
PWC	https://paperswithcode.com/paper/partsnet-a-unified-deep-network-for
Repo
Framework

Improving Variational Encoder-Decoders in Dialogue Generation


Title	Improving Variational Encoder-Decoders in Dialogue Generation
Authors	Xiaoyu Shen, Hui Su, Shuzi Niu, Vera Demberg
Abstract	Variational encoder-decoders (VEDs) have shown promising results in dialogue generation. However, the latent variable distributions are usually approximated by a much simpler model than the powerful RNN structure used for encoding and decoding, yielding the KL-vanishing problem and inconsistent training objective. In this paper, we separate the training step into two phases: The first phase learns to autoencode discrete texts into continuous embeddings, from which the second phase learns to generalize latent representations by reconstructing the encoded embedding. In this case, latent variables are sampled by transforming Gaussian noise through multi-layer perceptrons and are trained with a separate VED model, which has the potential of realizing a much more flexible distribution. We compare our model with current popular models and the experiment demonstrates substantial improvement in both metric-based and human evaluations.
Tasks	Dialogue Generation
Published	2018-02-06
URL	http://arxiv.org/abs/1802.02032v1
PDF	http://arxiv.org/pdf/1802.02032v1.pdf
PWC	https://paperswithcode.com/paper/improving-variational-encoder-decoders-in
Repo
Framework

Unsupervised Discovery of Toxoplasma gondii Motility Phenotypes


Title	Unsupervised Discovery of Toxoplasma gondii Motility Phenotypes
Authors	Mojtaba S. Fazli, Stephen A. Vella, Silvia N. J. Moreno, Shannon Quinn
Abstract	Toxoplasma gondii is a parasitic protozoan that causes dis- seminated toxoplasmosis, a disease that afflicts roughly a third of the worlds population. Its virulence is predicated on its motility and ability to enter and exit nucleated cells; therefore, studies elucidating its mechanism of motility and in particular, its motility patterns in the context of its lytic cycle, are critical to the eventual development of therapeutic strate- gies. Here, we present an end-to-end computational pipeline for identifying T. gondii motility phenotypes in a completely unsupervised, data-driven way. We track the parasites before and after addition of extracellular Ca2+ to study its effects on the parasite motility patterns and use this information to parameterize the motion and group it according to similarity of spatiotemporal dynamics.
Tasks
Published	2018-01-08
URL	http://arxiv.org/abs/1801.02591v2
PDF	http://arxiv.org/pdf/1801.02591v2.pdf
PWC	https://paperswithcode.com/paper/unsupervised-discovery-of-toxoplasma-gondii
Repo
Framework

End-to-End Fine-Grained Action Segmentation and Recognition Using Conditional Random Field Models and Discriminative Sparse Coding


Title	End-to-End Fine-Grained Action Segmentation and Recognition Using Conditional Random Field Models and Discriminative Sparse Coding
Authors	Effrosyni Mavroudi, Divya Bhaskara, Shahin Sefati, Haider Ali, René Vidal
Abstract	Fine-grained action segmentation and recognition is an important yet challenging task. Given a long, untrimmed sequence of kinematic data, the task is to classify the action at each time frame and segment the time series into the correct sequence of actions. In this paper, we propose a novel framework that combines a temporal Conditional Random Field (CRF) model with a powerful frame-level representation based on discriminative sparse coding. We introduce an end-to-end algorithm for jointly learning the weights of the CRF model, which include action classification and action transition costs, as well as an overcomplete dictionary of mid-level action primitives. This results in a CRF model that is driven by sparse coding features obtained using a discriminative dictionary that is shared among different actions and adapted to the task of structured output learning. We evaluate our method on three surgical tasks using kinematic data from the JIGSAWS dataset, as well as on a food preparation task using accelerometer data from the 50 Salads dataset. Our results show that the proposed method performs on par or better than state-of-the-art methods.
Tasks	Action Classification, action segmentation, Time Series
Published	2018-01-29
URL	http://arxiv.org/abs/1801.09571v1
PDF	http://arxiv.org/pdf/1801.09571v1.pdf
PWC	https://paperswithcode.com/paper/end-to-end-fine-grained-action-segmentation
Repo
Framework

Blockchain as a Service: A Decentralized and Secure Computing Paradigm


Title	Blockchain as a Service: A Decentralized and Secure Computing Paradigm
Authors	Gihan J. Mendis, Yifu Wu, Jin Wei, Moein Sabounchi, Rigoberto Roche’
Abstract	Thanks to the advances in machine learning, data-driven analysis tools have become valuable solutions for various applications. However, there still remain essential challenges to develop effective data-driven methods because of the need to acquire a large amount of data and to have sufficient computing power to handle the data. In many instances these challenges are addressed by relying on a dominant cloud computing vendor, but, although commercial cloud vendors provide valuable platforms for data analytics, they can suffer from a lack of transparency, security, and privacy-perservation. Furthermore, reliance on cloud servers prevents applying big data analytics in environments where the computing power is scattered. To address these challenges, a decentralize, secure, and privacy-preserving computing paradigm is proposed to enable an asynchronized cooperative computing process amongst scattered and untrustworthy computing nodes that may have limited computing power and computing intelligence. This paradigm is designed by exploring blockchain, decentralized learning, homomorphic encryption, and software defined networking(SDN) techniques. The performance of the proposed paradigm is evaluated via different scenarios in the simulation section.
Tasks
Published	2018-07-05
URL	https://arxiv.org/abs/1807.02515v3
PDF	https://arxiv.org/pdf/1807.02515v3.pdf
PWC	https://paperswithcode.com/paper/blockchain-as-a-service-an-autonomous-privacy
Repo
Framework

Security Analysis and Enhancement of Model Compressed Deep Learning Systems under Adversarial Attacks


Title	Security Analysis and Enhancement of Model Compressed Deep Learning Systems under Adversarial Attacks
Authors	Qi Liu, Tao Liu, Zihao Liu, Yanzhi Wang, Yier Jin, Wujie Wen
Abstract	DNN is presenting human-level performance for many complex intelligent tasks in real-world applications. However, it also introduces ever-increasing security concerns. For example, the emerging adversarial attacks indicate that even very small and often imperceptible adversarial input perturbations can easily mislead the cognitive function of deep learning systems (DLS). Existing DNN adversarial studies are narrowly performed on the ideal software-level DNN models with a focus on single uncertainty factor, i.e. input perturbations, however, the impact of DNN model reshaping on adversarial attacks, which is introduced by various hardware-favorable techniques such as hash-based weight compression during modern DNN hardware implementation, has never been discussed. In this work, we for the first time investigate the multi-factor adversarial attack problem in practical model optimized deep learning systems by jointly considering the DNN model-reshaping (e.g. HashNet based deep compression) and the input perturbations. We first augment adversarial example generating method dedicated to the compressed DNN models by incorporating the software-based approaches and mathematical modeled DNN reshaping. We then conduct a comprehensive robustness and vulnerability analysis of deep compressed DNN models under derived adversarial attacks. A defense technique named “gradient inhibition” is further developed to ease the generating of adversarial examples thus to effectively mitigate adversarial attacks towards both software and hardware-oriented DNNs. Simulation results show that “gradient inhibition” can decrease the average success rate of adversarial attacks from 87.99% to 4.77% (from 86.74% to 4.64%) on MNIST (CIFAR-10) benchmark with marginal accuracy degradation across various DNNs.
Tasks	Adversarial Attack
Published	2018-02-14
URL	http://arxiv.org/abs/1802.05193v2
PDF	http://arxiv.org/pdf/1802.05193v2.pdf
PWC	https://paperswithcode.com/paper/security-analysis-and-enhancement-of-model
Repo
Framework

Occlusion Resistant Object Rotation Regression from Point Cloud Segments


Title	Occlusion Resistant Object Rotation Regression from Point Cloud Segments
Authors	Ge Gao, Mikko Lauri, Jianwei Zhang, Simone Frintrop
Abstract	Rotation estimation of known rigid objects is important for robotic applications such as dexterous manipulation. Most existing methods for rotation estimation use intermediate representations such as templates, global or local feature descriptors, or object coordinates, which require multiple steps in order to infer the object pose. We propose to directly regress a pose vector from raw point cloud segments using a convolutional neural network. Experimental results show that our method can potentially achieve competitive performance compared to a state-of-the-art method, while also showing more robustness against occlusion. Our method does not require any post processing such as refinement with the iterative closest point algorithm.
Tasks
Published	2018-08-16
URL	http://arxiv.org/abs/1808.05498v2
PDF	http://arxiv.org/pdf/1808.05498v2.pdf
PWC	https://paperswithcode.com/paper/occlusion-resistant-object-rotation
Repo
Framework

Zap: Making Predictions Based on Online User Behavior


Title	Zap: Making Predictions Based on Online User Behavior
Authors	Yuri Chervonyi, Dragos Harabor, Brian Zhang, Josh Sacks
Abstract	This paper introduces Zap, a generic machine learning pipeline for making predictions based on online user behavior. Zap combines well known techniques for processing sequential data with more obscure techniques such as Bloom filters, bucketing, and model calibration into an end-to-end solution. The pipeline creates website- and task-specific models without knowing anything about the structure of the website. It is designed to minimize the amount of website-specific code, which is realized by factoring all website-specific logic into example generators. New example generators can typically be written up in a few lines of code.
Tasks	Calibration
Published	2018-07-16
URL	http://arxiv.org/abs/1807.06046v1
PDF	http://arxiv.org/pdf/1807.06046v1.pdf
PWC	https://paperswithcode.com/paper/zap-making-predictions-based-on-online-user
Repo
Framework

Privado: Practical and Secure DNN Inference with Enclaves


Title	Privado: Practical and Secure DNN Inference with Enclaves
Authors	Karan Grover, Shruti Tople, Shweta Shinde, Ranjita Bhagwan, Ramachandran Ramjee
Abstract	Cloud providers are extending support for trusted hardware primitives such as Intel SGX. Simultaneously, the field of deep learning is seeing enormous innovation as well as an increase in adoption. In this paper, we ask a timely question: “Can third-party cloud services use Intel SGX enclaves to provide practical, yet secure DNN Inference-as-a-service?” We first demonstrate that DNN models executing inside enclaves are vulnerable to access pattern based attacks. We show that by simply observing access patterns, an attacker can classify encrypted inputs with 97% and 71% attack accuracy for MNIST and CIFAR10 datasets on models trained to achieve 99% and 79% original accuracy respectively. This motivates the need for PRIVADO, a system we have designed for secure, easy-to-use, and performance efficient inference-as-a-service. PRIVADO is input-oblivious: it transforms any deep learning framework that is written in C/C++ to be free of input-dependent access patterns thus eliminating the leakage. PRIVADO is fully-automated and has a low TCB: with zero developer effort, given an ONNX description of a model, it generates compact and enclave-compatible code which can be deployed on an SGX cloud platform. PRIVADO incurs low performance overhead: we use PRIVADO with Torch framework and show its overhead to be 17.18% on average on 11 different contemporary neural networks.
Tasks
Published	2018-10-01
URL	https://arxiv.org/abs/1810.00602v2
PDF	https://arxiv.org/pdf/1810.00602v2.pdf
PWC	https://paperswithcode.com/paper/privado-practical-and-secure-dnn-inference
Repo
Framework