Paper Group ANR 304
Tagging like Humans: Diverse and Distinct Image Annotation. Wideband Time-Domain Digital Backpropagation via Subband Processing and Deep Learning. Machine learning and AI research for Patient Benefit: 20 Critical Questions on Transparency, Replicability, Ethics and Effectiveness. Time Series Featurization via Topological Data Analysis. Cooperative …
Tagging like Humans: Diverse and Distinct Image Annotation
Title | Tagging like Humans: Diverse and Distinct Image Annotation |
Authors | Baoyuan Wu, Weidong Chen, Peng Sun, Wei Liu, Bernard Ghanem, Siwei Lyu |
Abstract | In this work we propose a new automatic image annotation model, dubbed {\bf diverse and distinct image annotation} (D2IA). The generative model D2IA is inspired by the ensemble of human annotations, which create semantically relevant, yet distinct and diverse tags. In D2IA, we generate a relevant and distinct tag subset, in which the tags are relevant to the image contents and semantically distinct to each other, using sequential sampling from a determinantal point process (DPP) model. Multiple such tag subsets that cover diverse semantic aspects or diverse semantic levels of the image contents are generated by randomly perturbing the DPP sampling process. We leverage a generative adversarial network (GAN) model to train D2IA. Extensive experiments including quantitative and qualitative comparisons, as well as human subject studies, on two benchmark datasets demonstrate that the proposed model can produce more diverse and distinct tags than the state-of-the-arts. |
Tasks | |
Published | 2018-03-31 |
URL | http://arxiv.org/abs/1804.00113v1 |
http://arxiv.org/pdf/1804.00113v1.pdf | |
PWC | https://paperswithcode.com/paper/tagging-like-humans-diverse-and-distinct |
Repo | |
Framework | |
Wideband Time-Domain Digital Backpropagation via Subband Processing and Deep Learning
Title | Wideband Time-Domain Digital Backpropagation via Subband Processing and Deep Learning |
Authors | Christian Häger, Henry D. Pfister |
Abstract | We propose a low-complexity sub-banded DSP architecture for digital backpropagation where the walk-off effect is compensated using simple delay elements. For a simulated 96-Gbaud signal and 2500 km optical link, our method achieves a 2.8 dB SNR improvement over linear equalization. |
Tasks | |
Published | 2018-07-04 |
URL | http://arxiv.org/abs/1807.01545v1 |
http://arxiv.org/pdf/1807.01545v1.pdf | |
PWC | https://paperswithcode.com/paper/wideband-time-domain-digital-backpropagation |
Repo | |
Framework | |
Machine learning and AI research for Patient Benefit: 20 Critical Questions on Transparency, Replicability, Ethics and Effectiveness
Title | Machine learning and AI research for Patient Benefit: 20 Critical Questions on Transparency, Replicability, Ethics and Effectiveness |
Authors | Sebastian Vollmer, Bilal A. Mateen, Gergo Bohner, Franz J Király, Rayid Ghani, Pall Jonsson, Sarah Cumbers, Adrian Jonas, Katherine S. L. McAllister, Puja Myles, David Granger, Mark Birse, Richard Branson, Karel GM Moons, Gary S Collins, John P. A. Ioannidis, Chris Holmes, Harry Hemingway |
Abstract | Machine learning (ML), artificial intelligence (AI) and other modern statistical methods are providing new opportunities to operationalize previously untapped and rapidly growing sources of data for patient benefit. Whilst there is a lot of promising research currently being undertaken, the literature as a whole lacks: transparency; clear reporting to facilitate replicability; exploration for potential ethical concerns; and, clear demonstrations of effectiveness. There are many reasons for why these issues exist, but one of the most important that we provide a preliminary solution for here is the current lack of ML/AI- specific best practice guidance. Although there is no consensus on what best practice looks in this field, we believe that interdisciplinary groups pursuing research and impact projects in the ML/AI for health domain would benefit from answering a series of questions based on the important issues that exist when undertaking work of this nature. Here we present 20 questions that span the entire project life cycle, from inception, data analysis, and model evaluation, to implementation, as a means to facilitate project planning and post-hoc (structured) independent evaluation. By beginning to answer these questions in different settings, we can start to understand what constitutes a good answer, and we expect that the resulting discussion will be central to developing an international consensus framework for transparent, replicable, ethical and effective research in artificial intelligence (AI-TREE) for health. |
Tasks | |
Published | 2018-12-21 |
URL | http://arxiv.org/abs/1812.10404v1 |
http://arxiv.org/pdf/1812.10404v1.pdf | |
PWC | https://paperswithcode.com/paper/machine-learning-and-ai-research-for-patient |
Repo | |
Framework | |
Time Series Featurization via Topological Data Analysis
Title | Time Series Featurization via Topological Data Analysis |
Authors | Kwangho Kim, Jisu Kim, Alessandro Rinaldo |
Abstract | We develop a novel algorithm for feature extraction in time series data by leveraging tools from topological data analysis. Our algorithm provides a simple, efficient way to successfully harness topological features of the attractor of the underlying dynamical system for an observed time series. The proposed methodology relies on the persistent landscapes and silhouette of the Rips complex obtained after a de-noising step based on principal components applied to a time-delayed embedding of a noisy, discrete time series sample. We analyze the stability properties of the proposed approach and show that the resulting TDA-based features are robust to sampling noise. Experiments on synthetic and real-world data demonstrate the effectiveness of our approach. We expect our method to provide new insights on feature extraction from granular, noisy time series data. |
Tasks | Dimensionality Reduction, Feature Engineering, Time Series, Topological Data Analysis |
Published | 2018-12-07 |
URL | https://arxiv.org/abs/1812.02987v2 |
https://arxiv.org/pdf/1812.02987v2.pdf | |
PWC | https://paperswithcode.com/paper/time-series-featurization-via-topological |
Repo | |
Framework | |
Cooperative Tracking of Cyclists Based on Smart Devices and Infrastructure
Title | Cooperative Tracking of Cyclists Based on Smart Devices and Infrastructure |
Authors | Günther Reitberger, Stefan Zernetsch, Maarten Bieshaar, Bernhard Sick, Konrad Doll, Erich Fuchs |
Abstract | In future traffic scenarios, vehicles and other traffic participants will be interconnected and equipped with various types of sensors, allowing for cooperation based on data or information exchange. This article presents an approach to cooperative tracking of cyclists using smart devices and infrastructure-based sensors. A smart device is carried by the cyclists and an intersection is equipped with a wide angle stereo camera system. Two tracking models are presented and compared. The first model is based on the stereo camera system detections only, whereas the second model cooperatively combines the camera based detections with velocity and yaw rate data provided by the smart device. Our aim is to overcome limitations of tracking approaches based on single data sources. We show in numerical evaluations on scenes where cyclists are starting or turning right that the cooperation leads to an improvement in both the ability to keep track of a cyclist and the accuracy of the track particularly when it comes to occlusions in the visual system. We, therefore, contribute to the safety of vulnerable road users in future traffic. |
Tasks | |
Published | 2018-03-06 |
URL | http://arxiv.org/abs/1803.02096v2 |
http://arxiv.org/pdf/1803.02096v2.pdf | |
PWC | https://paperswithcode.com/paper/cooperative-tracking-of-cyclists-based-on |
Repo | |
Framework | |
SMT vs NMT: A Comparison over Hindi & Bengali Simple Sentences
Title | SMT vs NMT: A Comparison over Hindi & Bengali Simple Sentences |
Authors | Sainik Kumar Mahata, Soumil Mandal, Dipankar Das, Sivaji Bandyopadhyay |
Abstract | In the present article, we identified the qualitative differences between Statistical Machine Translation (SMT) and Neural Machine Translation (NMT) outputs. We have tried to answer two important questions: 1. Does NMT perform equivalently well with respect to SMT and 2. Does it add extra flavor in improving the quality of MT output by employing simple sentences as training units. In order to obtain insights, we have developed three core models viz., SMT model based on Moses toolkit, followed by character and word level NMT models. All of the systems use English-Hindi and English-Bengali language pairs containing simple sentences as well as sentences of other complexity. In order to preserve the translations semantics with respect to the target words of a sentence, we have employed soft-attention into our word level NMT model. We have further evaluated all the systems with respect to the scenarios where they succeed and fail. Finally, the quality of translation has been validated using BLEU and TER metrics along with manual parameters like fluency, adequacy etc. We observed that NMT outperforms SMT in case of simple sentences whereas SMT outperforms in case of all types of sentence. |
Tasks | Machine Translation |
Published | 2018-12-12 |
URL | http://arxiv.org/abs/1812.04898v1 |
http://arxiv.org/pdf/1812.04898v1.pdf | |
PWC | https://paperswithcode.com/paper/smt-vs-nmt-a-comparison-over-hindi-bengali |
Repo | |
Framework | |
An approach to predictively securing critical cloud infrastructures through probabilistic modeling
Title | An approach to predictively securing critical cloud infrastructures through probabilistic modeling |
Authors | Satvik Jain, Arun Balaji Buduru, Anshuman Chhabra |
Abstract | Cloud infrastructures are being increasingly utilized in critical infrastructures such as banking/finance, transportation and utility management. Sophistication and resources used in recent security breaches including those on critical infrastructures show that attackers are no longer limited by monetary/computational constraints. In fact, they may be aided by entities with large financial and human resources. Hence there is urgent need to develop predictive approaches for cyber defense to strengthen cloud infrastructures specifically utilized by critical infrastructures. Extensive research has been done in the past on applying techniques such as Game Theory, Machine Learning and Bayesian Networks among others for the predictive defense of critical infrastructures. However a major drawback of these approaches is that they do not incorporate probabilistic human behavior which limits their predictive ability. In this paper, a stochastic approach is proposed to predict less secure states in critical cloud systems which might lead to potential security breaches. These less-secure states are deemed as risky' states in our approach. Markov Decision Process (MDP) is used to accurately incorporate user behavior(s) as well as operational behavior of the cloud infrastructure through a set of features. The developed reward/cost mechanism is then used to select appropriate actions’ to identify risky states at future time steps by learning an optimal policy. Experimental results show that the proposed framework performs well in identifying future `risky’ states. Through this work we demonstrate the effectiveness of using probabilistic modeling (MDP) to predictively secure critical cloud infrastructures. | |
Tasks | |
Published | 2018-10-29 |
URL | http://arxiv.org/abs/1810.11937v1 |
http://arxiv.org/pdf/1810.11937v1.pdf | |
PWC | https://paperswithcode.com/paper/an-approach-to-predictively-securing-critical |
Repo | |
Framework | |
Accelerating NMT Batched Beam Decoding with LMBR Posteriors for Deployment
Title | Accelerating NMT Batched Beam Decoding with LMBR Posteriors for Deployment |
Authors | Gonzalo Iglesias, William Tambellini, Adrià De Gispert, Eva Hasler, Bill Byrne |
Abstract | We describe a batched beam decoding algorithm for NMT with LMBR n-gram posteriors, showing that LMBR techniques still yield gains on top of the best recently reported results with Transformers. We also discuss acceleration strategies for deployment, and the effect of the beam size and batching on memory and speed. |
Tasks | |
Published | 2018-04-30 |
URL | http://arxiv.org/abs/1804.11324v1 |
http://arxiv.org/pdf/1804.11324v1.pdf | |
PWC | https://paperswithcode.com/paper/accelerating-nmt-batched-beam-decoding-with |
Repo | |
Framework | |
Edge and Corner Detection for Unorganized 3D Point Clouds with Application to Robotic Welding
Title | Edge and Corner Detection for Unorganized 3D Point Clouds with Application to Robotic Welding |
Authors | Syeda Mariam Ahmed, Yan Zhi Tan, Chee Meng Chew, Abdullah Al Mamun, Fook Seng Wong |
Abstract | In this paper, we propose novel edge and corner detection algorithms for unorganized point clouds. Our edge detection method evaluates symmetry in a local neighborhood and uses an adaptive density based threshold to differentiate 3D edge points. We extend this algorithm to propose a novel corner detector that clusters curvature vectors and uses their geometrical statistics to classify a point as corner. We perform rigorous evaluation of the algorithms on RGB-D semantic segmentation and 3D washer models from the ShapeNet dataset and report higher precision and recall scores. Finally, we also demonstrate how our edge and corner detectors can be used as a novel approach towards automatic weld seam detection for robotic welding. We propose to generate weld seams directly from a point cloud as opposed to using 3D models for offline planning of welding paths. For this application, we show a comparison between Harris 3D and our proposed approach on a panel workpiece. |
Tasks | Edge Detection, Semantic Segmentation |
Published | 2018-09-27 |
URL | http://arxiv.org/abs/1809.10468v1 |
http://arxiv.org/pdf/1809.10468v1.pdf | |
PWC | https://paperswithcode.com/paper/edge-and-corner-detection-for-unorganized-3d |
Repo | |
Framework | |
Reducing Parameter Space for Neural Network Training
Title | Reducing Parameter Space for Neural Network Training |
Authors | Tong Qin, Ling Zhou, Dongbin Xiu |
Abstract | For neural networks (NNs) with rectified linear unit (ReLU) or binary activation functions, we show that their training can be accomplished in a reduced parameter space. Specifically, the weights in each neuron can be trained on the unit sphere, as opposed to the entire space, and the threshold can be trained in a bounded interval, as opposed to the real line. We show that the NNs in the reduced parameter space are mathematically equivalent to the standard NNs with parameters in the whole space. The reduced parameter space shall facilitate the optimization procedure for the network training, as the search space becomes (much) smaller. We demonstrate the improved training performance using numerical examples. |
Tasks | |
Published | 2018-05-22 |
URL | https://arxiv.org/abs/1805.08340v3 |
https://arxiv.org/pdf/1805.08340v3.pdf | |
PWC | https://paperswithcode.com/paper/reducing-parameter-space-for-neural-network |
Repo | |
Framework | |
A Two-Step Pursuit-Evasion Algorithm for Autonomous Underwater Vehicles
Title | A Two-Step Pursuit-Evasion Algorithm for Autonomous Underwater Vehicles |
Authors | Özer Özkahraman, Petter Ögren |
Abstract | In this paper, we consider the problem of pursuit-evasion using multiple Autonomous Underwater Vehicles (AUVs) in a 3D water volume, with and without obstacles in terms of islands and the seabed topography. Pursuit-evasion is a well studied topic in robotics, but the results are mostly set in 2D environments, using unlimited line-of-sight sensing. We propose an algorithm for range-limited sensing in 3D environments that captures a finite-speed evader based on a single previous observation of its location. The pursuers are first moved to form a cage formation that contains the evader while minimizing the number of pursuers required. Upon completion of the initial cage, the cage is then changed to a smaller spherical cage that is shrunk until every part of the volume containing the evader is sensed, capturing the evader. The pursuers only need minimal communication and computation while the mission is carried out and most of the computation is done beforehand, allowing for easy implementation. |
Tasks | |
Published | 2018-09-26 |
URL | http://arxiv.org/abs/1809.09876v2 |
http://arxiv.org/pdf/1809.09876v2.pdf | |
PWC | https://paperswithcode.com/paper/a-two-step-pursuit-evasion-algorithm-for |
Repo | |
Framework | |
Attention-GAN for Object Transfiguration in Wild Images
Title | Attention-GAN for Object Transfiguration in Wild Images |
Authors | Xinyuan Chen, Chang Xu, Xiaokang Yang, Dacheng Tao |
Abstract | This paper studies the object transfiguration problem in wild images. The generative network in classical GANs for object transfiguration often undertakes a dual responsibility: to detect the objects of interests and to convert the object from source domain to target domain. In contrast, we decompose the generative network into two separat networks, each of which is only dedicated to one particular sub-task. The attention network predicts spatial attention maps of images, and the transformation network focuses on translating objects. Attention maps produced by attention network are encouraged to be sparse, so that major attention can be paid to objects of interests. No matter before or after object transfiguration, attention maps should remain constant. In addition, learning attention network can receive more instructions, given the available segmentation annotations of images. Experimental results demonstrate the necessity of investigating attention in object transfiguration, and that the proposed algorithm can learn accurate attention to improve quality of generated images. |
Tasks | |
Published | 2018-03-19 |
URL | http://arxiv.org/abs/1803.06798v1 |
http://arxiv.org/pdf/1803.06798v1.pdf | |
PWC | https://paperswithcode.com/paper/attention-gan-for-object-transfiguration-in |
Repo | |
Framework | |
Development of a sensory-neural network for medical diagnosing
Title | Development of a sensory-neural network for medical diagnosing |
Authors | Igor Grabec, Eva Švegl, Mihael Sok |
Abstract | Performance of a sensory-neural network developed for diagnosing of diseases is described. Information about patient’s condition is provided by answers to the questionnaire. Questions correspond to sensors generating signals when patients acknowledge symptoms. These signals excite neurons in which characteristics of the diseases are represented by synaptic weights associated with indicators of symptoms. The disease corresponding to the most excited neuron is proposed as the result of diagnosing. Its reliability is estimated by the likelihood defined by the ratio of excitation of the most excited neuron and the complete neural network. |
Tasks | |
Published | 2018-07-06 |
URL | http://arxiv.org/abs/1807.02477v1 |
http://arxiv.org/pdf/1807.02477v1.pdf | |
PWC | https://paperswithcode.com/paper/development-of-a-sensory-neural-network-for |
Repo | |
Framework | |
The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks
Title | The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks |
Authors | Nicholas Carlini, Chang Liu, Úlfar Erlingsson, Jernej Kos, Dawn Song |
Abstract | This paper describes a testing methodology for quantitatively assessing the risk that rare or unique training-data sequences are unintentionally memorized by generative sequence models—a common type of machine-learning model. Because such models are sometimes trained on sensitive data (e.g., the text of users’ private messages), this methodology can benefit privacy by allowing deep-learning practitioners to select means of training that minimize such memorization. In experiments, we show that unintended memorization is a persistent, hard-to-avoid issue that can have serious consequences. Specifically, for models trained without consideration of memorization, we describe new, efficient procedures that can extract unique, secret sequences, such as credit card numbers. We show that our testing strategy is a practical and easy-to-use first line of defense, e.g., by describing its application to quantitatively limit data exposure in Google’s Smart Compose, a commercial text-completion neural network trained on millions of users’ email messages. |
Tasks | |
Published | 2018-02-22 |
URL | https://arxiv.org/abs/1802.08232v3 |
https://arxiv.org/pdf/1802.08232v3.pdf | |
PWC | https://paperswithcode.com/paper/the-secret-sharer-measuring-unintended-neural |
Repo | |
Framework | |
Fast and Accurate Camera Covariance Computation for Large 3D Reconstruction
Title | Fast and Accurate Camera Covariance Computation for Large 3D Reconstruction |
Authors | Michal Polic, Wolfgang Förstner, Tomas Pajdla |
Abstract | Estimating uncertainty of camera parameters computed in Structure from Motion (SfM) is an important tool for evaluating the quality of the reconstruction and guiding the reconstruction process. Yet, the quality of the estimated parameters of large reconstructions has been rarely evaluated due to the computational challenges. We present a new algorithm which employs the sparsity of the uncertainty propagation and speeds the computation up about ten times \wrt previous approaches. Our computation is accurate and does not use any approximations. We can compute uncertainties of thousands of cameras in tens of seconds on a standard PC. We also demonstrate that our approach can be effectively used for reconstructions of any size by applying it to smaller sub-reconstructions. |
Tasks | 3D Reconstruction |
Published | 2018-08-07 |
URL | http://arxiv.org/abs/1808.02414v1 |
http://arxiv.org/pdf/1808.02414v1.pdf | |
PWC | https://paperswithcode.com/paper/fast-and-accurate-camera-covariance |
Repo | |
Framework | |