Paper Group ANR 97
End to End Vehicle Lateral Control Using a Single Fisheye Camera. Learning Multilingual Topics from Incomparable Corpus. Classification of 12-Lead ECG Signals with Bi-directional LSTM Network. Region of Interest Detection in Dermoscopic Images for Natural Data-augmentation. Fruit and Vegetable Identification Using Machine Learning for Retail Applic …
End to End Vehicle Lateral Control Using a Single Fisheye Camera
| Title | End to End Vehicle Lateral Control Using a Single Fisheye Camera |
| Authors | Marin Toromanoff, Emilie Wirbel, Frédéric Wilhelm, Camilo Vejarano, Xavier Perrotton, Fabien Moutarde |
| Abstract | Convolutional neural networks are commonly used to control the steering angle for autonomous cars. Most of the time, multiple long range cameras are used to generate lateral failure cases. In this paper we present a novel model to generate this data and label augmentation using only one short range fisheye camera. We present our simulator and how it can be used as a consistent metric for lateral end-to-end control evaluation. Experiments are conducted on a custom dataset corresponding to more than 10000 km and 200 hours of open road driving. Finally we evaluate this model on real world driving scenarios, open road and a custom test track with challenging obstacle avoidance and sharp turns. In our simulator based on real-world videos, the final model was capable of more than 99% autonomy on urban road |
| Tasks | |
| Published | 2018-08-20 |
| URL | http://arxiv.org/abs/1808.06940v1 |
| http://arxiv.org/pdf/1808.06940v1.pdf | |
| PWC | https://paperswithcode.com/paper/end-to-end-vehicle-lateral-control-using-a |
| Repo | |
| Framework | |
Learning Multilingual Topics from Incomparable Corpus
| Title | Learning Multilingual Topics from Incomparable Corpus |
| Authors | Shudong Hao, Michael J. Paul |
| Abstract | Multilingual topic models enable crosslingual tasks by extracting consistent topics from multilingual corpora. Most models require parallel or comparable training corpora, which limits their ability to generalize. In this paper, we first demystify the knowledge transfer mechanism behind multilingual topic models by defining an alternative but equivalent formulation. Based on this analysis, we then relax the assumption of training data required by most existing models, creating a model that only requires a dictionary for training. Experiments show that our new method effectively learns coherent multilingual topics from partially and fully incomparable corpora with limited amounts of dictionary resources. |
| Tasks | Topic Models, Transfer Learning |
| Published | 2018-06-11 |
| URL | http://arxiv.org/abs/1806.04270v1 |
| http://arxiv.org/pdf/1806.04270v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-multilingual-topics-from |
| Repo | |
| Framework | |
Classification of 12-Lead ECG Signals with Bi-directional LSTM Network
| Title | Classification of 12-Lead ECG Signals with Bi-directional LSTM Network |
| Authors | Ahmed Mostayed, Junye Luo, Xingliang Shu, William Wee |
| Abstract | We propose a recurrent neural network classifier to detect pathologies in 12-lead ECG signals and train and validate the classifier with the Chinese physiological signal challenge dataset (http://www.icbeb.org/Challenge.html). The recurrent neural network consists of two bi-directional LSTM layers and can train on arbitrary-length ECG signals. Our best trained model achieved an average F1 score of 74.15% on the validation set. Keywords: ECG classification, Deep learning, RNN, Bi-directional LSTM, QRS detection. |
| Tasks | ECG Classification |
| Published | 2018-11-05 |
| URL | http://arxiv.org/abs/1811.02090v1 |
| http://arxiv.org/pdf/1811.02090v1.pdf | |
| PWC | https://paperswithcode.com/paper/classification-of-12-lead-ecg-signals-with-bi |
| Repo | |
| Framework | |
Region of Interest Detection in Dermoscopic Images for Natural Data-augmentation
| Title | Region of Interest Detection in Dermoscopic Images for Natural Data-augmentation |
| Authors | Manu Goyal, Saeed Hassanpour, Moi Hoon Yap |
| Abstract | With the rapid growth of medical imaging research, there is a great interest in the automated detection of skin lesions with computer algorithms. The state-of-the-art datasets for skin lesions are often accompanied with very limited amount of ground truth labeling as it is laborious and expensive. The Region Of Interest (ROI) detection is vital to locate the lesion accurately and must be robust to subtle features of different skin lesion types. In this work, we propose the use of two object localization meta-architectures for end-to-end ROI skin lesion detection in dermoscopic images. We trained the Faster-RCNN-InceptionV2 and SSD-InceptionV2 on the ISBI-2017 training dataset and evaluated their performance on the ISBI-2017 testing set, PH2 and HAM10000 datasets. Since there was no earlier work in ROI detection for skin lesion with CNNs, we compared the performance of skin localization methods with the state-of-the-art segmentation method. The localization methods proved superior to the segmentation method in ROI detection on skin lesion datasets. In addition, based on the detected ROI, an automated natural data-augmentation method is proposed and used as pre-processing in the lesion diagnosis and segmentation task. To further demonstrate the potential of our work, we developed a real-time smart-phone application for automated skin lesions detection. |
| Tasks | Data Augmentation, Object Localization |
| Published | 2018-07-27 |
| URL | https://arxiv.org/abs/1807.10711v2 |
| https://arxiv.org/pdf/1807.10711v2.pdf | |
| PWC | https://paperswithcode.com/paper/region-of-interest-detection-in-dermoscopic |
| Repo | |
| Framework | |
Fruit and Vegetable Identification Using Machine Learning for Retail Applications
| Title | Fruit and Vegetable Identification Using Machine Learning for Retail Applications |
| Authors | Frida Femling, Adam Olsson, Fernando Alonso-Fernandez |
| Abstract | This paper describes an approach of creating a system identifying fruit and vegetables in the retail market using images captured with a video camera attached to the system. The system helps the customers to label desired fruits and vegetables with a price according to its weight. The purpose of the system is to minimize the number of human computer interactions, speed up the identification process and improve the usability of the graphical user interface compared to existing manual systems. The hardware of the system is constituted by a Raspberry Pi, camera, display, load cell and a case. To classify an object, different convolutional neural networks have been tested and retrained. To test the usability, a heuristic evaluation has been performed with several users, concluding that the implemented system is more user friendly compared to existing systems. |
| Tasks | |
| Published | 2018-10-23 |
| URL | http://arxiv.org/abs/1810.09811v1 |
| http://arxiv.org/pdf/1810.09811v1.pdf | |
| PWC | https://paperswithcode.com/paper/fruit-and-vegetable-identification-using |
| Repo | |
| Framework | |
Logistic Regression: The Importance of Being Improper
| Title | Logistic Regression: The Importance of Being Improper |
| Authors | Dylan J. Foster, Satyen Kale, Haipeng Luo, Mehryar Mohri, Karthik Sridharan |
| Abstract | Learning linear predictors with the logistic loss—both in stochastic and online settings—is a fundamental task in machine learning and statistics, with direct connections to classification and boosting. Existing “fast rates” for this setting exhibit exponential dependence on the predictor norm, and Hazan et al. (2014) showed that this is unfortunately unimprovable. Starting with the simple observation that the logistic loss is $1$-mixable, we design a new efficient improper learning algorithm for online logistic regression that circumvents the aforementioned lower bound with a regret bound exhibiting a doubly-exponential improvement in dependence on the predictor norm. This provides a positive resolution to a variant of the COLT 2012 open problem of McMahan and Streeter (2012) when improper learning is allowed. This improvement is obtained both in the online setting and, with some extra work, in the batch statistical setting with high probability. We also show that the improved dependence on predictor norm is near-optimal. Leveraging this improved dependency on the predictor norm yields the following applications: (a) we give algorithms for online bandit multiclass learning with the logistic loss with an $\tilde{O}(\sqrt{n})$ relative mistake bound across essentially all parameter ranges, thus providing a solution to the COLT 2009 open problem of Abernethy and Rakhlin (2009), and (b) we give an adaptive algorithm for online multiclass boosting with optimal sample complexity, thus partially resolving an open problem of Beygelzimer et al. (2015) and Jung et al. (2017). Finally, we give information-theoretic bounds on the optimal rates for improper logistic regression with general function classes, thereby characterizing the extent to which our improvement for linear classes extends to other parametric and even nonparametric settings. |
| Tasks | |
| Published | 2018-03-25 |
| URL | http://arxiv.org/abs/1803.09349v2 |
| http://arxiv.org/pdf/1803.09349v2.pdf | |
| PWC | https://paperswithcode.com/paper/logistic-regression-the-importance-of-being |
| Repo | |
| Framework | |
Coordinated exploration for labyrinthine environments with application to the Pursuit-Evasion problem
| Title | Coordinated exploration for labyrinthine environments with application to the Pursuit-Evasion problem |
| Authors | Damien Pellier, Humbert Fiorino |
| Abstract | This paper introduces a multirobot cooperation approach to solve the “pursuit evasion” problem for mobile robots that have omnidirectional vision sensors. The main characteristic of this approach is to implement a real cooperation between robots based on knowledge sharing and makes them work as a team. A complete algorithm for computing a motion strategy of robots is also presented. This algorithm is based on searching critical points in the environment. Finally, the deliberation protocol which distributes the exploration task among the team and takes the best possible outcome from the robots resources is presented. |
| Tasks | |
| Published | 2018-10-19 |
| URL | http://arxiv.org/abs/1810.08438v1 |
| http://arxiv.org/pdf/1810.08438v1.pdf | |
| PWC | https://paperswithcode.com/paper/coordinated-exploration-for-labyrinthine |
| Repo | |
| Framework | |
Accelerating recurrent neural network language model based online speech recognition system
| Title | Accelerating recurrent neural network language model based online speech recognition system |
| Authors | Kyungmin Lee, Chiyoun Park, Namhoon Kim, Jaewon Lee |
| Abstract | This paper presents methods to accelerate recurrent neural network based language models (RNNLMs) for online speech recognition systems. Firstly, a lossy compression of the past hidden layer outputs (history vector) with caching is introduced in order to reduce the number of LM queries. Next, RNNLM computations are deployed in a CPU-GPU hybrid manner, which computes each layer of the model on a more advantageous platform. The added overhead by data exchanges between CPU and GPU is compensated through a frame-wise batching strategy. The performance of the proposed methods evaluated on LibriSpeech test sets indicates that the reduction in history vector precision improves the average recognition speed by 1.23 times with minimum degradation in accuracy. On the other hand, the CPU-GPU hybrid parallelization enables RNNLM based real-time recognition with a four times improvement in speed. |
| Tasks | Language Modelling, Speech Recognition |
| Published | 2018-01-30 |
| URL | http://arxiv.org/abs/1801.09866v1 |
| http://arxiv.org/pdf/1801.09866v1.pdf | |
| PWC | https://paperswithcode.com/paper/accelerating-recurrent-neural-network-1 |
| Repo | |
| Framework | |
Deep Net Features for Complex Emotion Recognition
| Title | Deep Net Features for Complex Emotion Recognition |
| Authors | Bhalaji Nagarajan, V Ramana Murthy Oruganti |
| Abstract | This paper investigates the influence of different acoustic features, audio-events based features and automatic speech translation based lexical features in complex emotion recognition such as curiosity. Pretrained networks, namely, AudioSet Net, VoxCeleb Net and Deep Speech Net trained extensively for different speech based applications are studied for this objective. Information from deep layers of these networks are considered as descriptors and encoded into feature vectors. Experimental results on the EmoReact dataset consisting of 8 complex emotions show the effectiveness, yielding highest F1 score of 0.85 as against the baseline of 0.69 in the literature. |
| Tasks | Emotion Recognition |
| Published | 2018-10-31 |
| URL | http://arxiv.org/abs/1811.00003v2 |
| http://arxiv.org/pdf/1811.00003v2.pdf | |
| PWC | https://paperswithcode.com/paper/deep-net-features-for-complex-emotion |
| Repo | |
| Framework | |
Generating Image Sequence from Description with LSTM Conditional GAN
| Title | Generating Image Sequence from Description with LSTM Conditional GAN |
| Authors | Xu Ouyang, Xi Zhang, Di Ma, Gady Agam |
| Abstract | Generating images from word descriptions is a challenging task. Generative adversarial networks(GANs) are shown to be able to generate realistic images of real-life objects. In this paper, we propose a new neural network architecture of LSTM Conditional Generative Adversarial Networks to generate images of real-life objects. Our proposed model is trained on the Oxford-102 Flowers and Caltech-UCSD Birds-200-2011 datasets. We demonstrate that our proposed model produces the better results surpassing other state-of-art approaches. |
| Tasks | |
| Published | 2018-06-08 |
| URL | http://arxiv.org/abs/1806.03027v1 |
| http://arxiv.org/pdf/1806.03027v1.pdf | |
| PWC | https://paperswithcode.com/paper/generating-image-sequence-from-description |
| Repo | |
| Framework | |
Segmentation of Overlapped Steatosis in Whole-Slide Liver Histopathology Microscopy Images
| Title | Segmentation of Overlapped Steatosis in Whole-Slide Liver Histopathology Microscopy Images |
| Authors | Mousumi Roy, Fusheng Wang, George Teodoro, Miriam B Vos, Alton Brad Farris, Jun Kong |
| Abstract | An accurate steatosis quantification with pathology tissue samples is of high clinical importance. However, such pathology measurement is manually made in most clinical practices, subject to severe reader variability due to large sampling bias and poor reproducibility. Although some computerized automated methods are developed to quantify the steatosis regions, they present limited analysis capacity for high resolution whole-slide microscopy images and accurate overlapped steatosis division. In this paper, we propose a method that extracts an individual whole tissue piece at high resolution with minimum background area by estimating tissue bounding box and rotation angle. This is followed by the segmentation and segregation of steatosis regions with high curvature point detection and an ellipse fitting quality assessment method. We validate our method with isolated and overlapped steatosis regions in liver tissue images of 11 patients. The experimental results suggest that our method is promising for enhanced support of steatosis quantization during the pathology review for liver disease treatment. |
| Tasks | Quantization |
| Published | 2018-06-24 |
| URL | http://arxiv.org/abs/1806.09090v1 |
| http://arxiv.org/pdf/1806.09090v1.pdf | |
| PWC | https://paperswithcode.com/paper/segmentation-of-overlapped-steatosis-in-whole |
| Repo | |
| Framework | |
Using Deep Neural Networks to Translate Multi-lingual Threat Intelligence
| Title | Using Deep Neural Networks to Translate Multi-lingual Threat Intelligence |
| Authors | Priyanka Ranade, Sudip Mittal, Anupam Joshi, Karuna Joshi |
| Abstract | The multilingual nature of the Internet increases complications in the cybersecurity community’s ongoing efforts to strategically mine threat intelligence from OSINT data on the web. OSINT sources such as social media, blogs, and dark web vulnerability markets exist in diverse languages and hinder security analysts, who are unable to draw conclusions from intelligence in languages they don’t understand. Although third party translation engines are growing stronger, they are unsuited for private security environments. First, sensitive intelligence is not a permitted input to third party engines due to privacy and confidentiality policies. In addition, third party engines produce generalized translations that tend to lack exclusive cybersecurity terminology. In this paper, we address these issues and describe our system that enables threat intelligence understanding across unfamiliar languages. We create a neural network based system that takes in cybersecurity data in a different language and outputs the respective English translation. The English translation can then be understood by an analyst, and can also serve as input to an AI based cyber-defense system that can take mitigative action. As a proof of concept, we have created a pipeline which takes Russian threats and generates its corresponding English, RDF, and vectorized representations. Our network optimizes translations on specifically, cybersecurity data. |
| Tasks | |
| Published | 2018-07-19 |
| URL | http://arxiv.org/abs/1807.07517v1 |
| http://arxiv.org/pdf/1807.07517v1.pdf | |
| PWC | https://paperswithcode.com/paper/using-deep-neural-networks-to-translate-multi |
| Repo | |
| Framework | |
Cascade context encoder for improved inpainting
| Title | Cascade context encoder for improved inpainting |
| Authors | Bartosz Zieliński, Łukasz Struski, Marek Śmieja, Jacek Tabor |
| Abstract | In this paper, we analyze if cascade usage of the context encoder with increasing input can improve the results of the inpainting. For this purpose, we train context encoder for 64x64 pixels images in a standard way and use its resized output to fill in the missing input region of the 128x128 context encoder, both in training and evaluation phase. As the result, the inpainting is visibly more plausible. In order to thoroughly verify the results, we introduce normalized squared-distortion, a measure for quantitative inpainting evaluation, and we provide its mathematical explanation. This is the first attempt to formalize the inpainting measure, which is based on the properties of latent feature representation, instead of L2 reconstruction loss. |
| Tasks | |
| Published | 2018-03-11 |
| URL | http://arxiv.org/abs/1803.04033v1 |
| http://arxiv.org/pdf/1803.04033v1.pdf | |
| PWC | https://paperswithcode.com/paper/cascade-context-encoder-for-improved |
| Repo | |
| Framework | |
Machine Learning Methods for Solving Assignment Problems in Multi-Target Tracking
| Title | Machine Learning Methods for Solving Assignment Problems in Multi-Target Tracking |
| Authors | Patrick Emami, Panos M. Pardalos, Lily Elefteriadou, Sanjay Ranka |
| Abstract | Data association and track-to-track association, two fundamental problems in single-sensor and multi-sensor multi-target tracking, are instances of an NP-hard combinatorial optimization problem known as the multidimensional assignment problem (MDAP). Over the last few years, data-driven approaches to tackling MDAPs in tracking have become increasingly popular. We argue that viewing multi-target tracking as an assignment problem conceptually unifies the wide variety of machine learning methods that have been proposed for data association and track-to-track association. In this survey, we review recent literature, provide rigorous formulations of the assignment problems encountered in multi-target tracking, and review classic approaches used prior to the shift towards data-driven techniques. Recent attempts at using deep learning to solve NP-hard combinatorial optimization problems, including data association, are discussed as well. We highlight representation learning methods for multi-sensor applications and conclude by providing an overview of current multi-target tracking benchmarks. |
| Tasks | Combinatorial Optimization, Representation Learning |
| Published | 2018-02-19 |
| URL | http://arxiv.org/abs/1802.06897v1 |
| http://arxiv.org/pdf/1802.06897v1.pdf | |
| PWC | https://paperswithcode.com/paper/machine-learning-methods-for-solving |
| Repo | |
| Framework | |
News-based trading strategies
| Title | News-based trading strategies |
| Authors | Stefan Feuerriegel, Helmut Prendinger |
| Abstract | The marvel of markets lies in the fact that dispersed information is instantaneously processed and used to adjust the price of goods, services and assets. Financial markets are particularly efficient when it comes to processing information; such information is typically embedded in textual news that is then interpreted by investors. Quite recently, researchers have started to automatically determine news sentiment in order to explain stock price movements. Interestingly, this so-called news sentiment works fairly well in explaining stock returns. In this paper, we design trading strategies that utilize textual news in order to obtain profits on the basis of novel information entering the market. We thus propose approaches for automated decision-making based on supervised and reinforcement learning. Altogether, we demonstrate how news-based data can be incorporated into an investment system. |
| Tasks | Decision Making |
| Published | 2018-07-18 |
| URL | http://arxiv.org/abs/1807.06824v1 |
| http://arxiv.org/pdf/1807.06824v1.pdf | |
| PWC | https://paperswithcode.com/paper/news-based-trading-strategies |
| Repo | |
| Framework | |
