Paper Group ANR 156
Code-switching Sentence Generation by Generative Adversarial Networks and its Application to Data Augmentation. Online Convex Optimization for Sequential Decision Processes and Extensive-Form Games. Derivative-free online learning of inverse dynamics models. Real-Time Monocular Object-Model Aware Sparse SLAM. Monocular Object and Plane SLAM in Stru …
Code-switching Sentence Generation by Generative Adversarial Networks and its Application to Data Augmentation
| Title | Code-switching Sentence Generation by Generative Adversarial Networks and its Application to Data Augmentation |
| Authors | Ching-Ting Chang, Shun-Po Chuang, Hung-Yi Lee |
| Abstract | Code-switching is about dealing with alternative languages in speech or text. It is partially speaker-depend and domain-related, so completely explaining the phenomenon by linguistic rules is challenging. Compared to most monolingual tasks, insufficient data is an issue for code-switching. To mitigate the issue without expensive human annotation, we proposed an unsupervised method for code-switching data augmentation. By utilizing a generative adversarial network, we can generate intra-sentential code-switching sentences from monolingual sentences. We applied proposed method on two corpora, and the result shows that the generated code-switching sentences improve the performance of code-switching language models. |
| Tasks | Data Augmentation |
| Published | 2018-11-06 |
| URL | https://arxiv.org/abs/1811.02356v4 |
| https://arxiv.org/pdf/1811.02356v4.pdf | |
| PWC | https://paperswithcode.com/paper/code-switching-sentence-generation-by |
| Repo | |
| Framework | |
Online Convex Optimization for Sequential Decision Processes and Extensive-Form Games
| Title | Online Convex Optimization for Sequential Decision Processes and Extensive-Form Games |
| Authors | Gabriele Farina, Christian Kroer, Tuomas Sandholm |
| Abstract | Regret minimization is a powerful tool for solving large-scale extensive-form games. State-of-the-art methods rely on minimizing regret locally at each decision point. In this work we derive a new framework for regret minimization on sequential decision problems and extensive-form games with general compact convex sets at each decision point and general convex losses, as opposed to prior work which has been for simplex decision points and linear losses. We call our framework laminar regret decomposition. It generalizes the CFR algorithm to this more general setting. Furthermore, our framework enables a new proof of CFR even in the known setting, which is derived from a perspective of decomposing polytope regret, thereby leading to an arguably simpler interpretation of the algorithm. Our generalization to convex compact sets and convex losses allows us to develop new algorithms for several problems: regularized sequential decision making, regularized Nash equilibria in extensive-form games, and computing approximate extensive-form perfect equilibria. Our generalization also leads to the first regret-minimization algorithm for computing reduced-normal-form quantal response equilibria based on minimizing local regrets. Experiments show that our framework leads to algorithms that scale at a rate comparable to the fastest variants of counterfactual regret minimization for computing Nash equilibrium, and therefore our approach leads to the first algorithm for computing quantal response equilibria in extremely large games. Finally we show that our framework enables a new kind of scalable opponent exploitation approach. |
| Tasks | Decision Making |
| Published | 2018-09-10 |
| URL | http://arxiv.org/abs/1809.03075v1 |
| http://arxiv.org/pdf/1809.03075v1.pdf | |
| PWC | https://paperswithcode.com/paper/online-convex-optimization-for-sequential |
| Repo | |
| Framework | |
Derivative-free online learning of inverse dynamics models
| Title | Derivative-free online learning of inverse dynamics models |
| Authors | Diego Romeres, Mattia Zorzi, Raffaello Camoriano, Silvio Traversaro, Alessandro Chiuso |
| Abstract | This paper discusses online algorithms for inverse dynamics modelling in robotics. Several model classes including rigid body dynamics (RBD) models, data-driven models and semiparametric models (which are a combination of the previous two classes) are placed in a common framework. While model classes used in the literature typically exploit joint velocities and accelerations, which need to be approximated resorting to numerical differentiation schemes, in this paper a new derivative-free' framework is proposed that does not require this preprocessing step. An extensive experimental study with real data from the right arm of the iCub robot is presented, comparing different model classes and estimation procedures, showing that the proposed derivative-free’ methods outperform existing methodologies. |
| Tasks | |
| Published | 2018-09-13 |
| URL | http://arxiv.org/abs/1809.05074v1 |
| http://arxiv.org/pdf/1809.05074v1.pdf | |
| PWC | https://paperswithcode.com/paper/derivative-free-online-learning-of-inverse |
| Repo | |
| Framework | |
Real-Time Monocular Object-Model Aware Sparse SLAM
| Title | Real-Time Monocular Object-Model Aware Sparse SLAM |
| Authors | Mehdi Hosseinzadeh, Kejie Li, Yasir Latif, Ian Reid |
| Abstract | Simultaneous Localization And Mapping (SLAM) is a fundamental problem in mobile robotics. While sparse point-based SLAM methods provide accurate camera localization, the generated maps lack semantic information. On the other hand, state of the art object detection methods provide rich information about entities present in the scene from a single image. This work incorporates a real-time deep-learned object detector to the monocular SLAM framework for representing generic objects as quadrics that permit detections to be seamlessly integrated while allowing the real-time performance. Finer reconstruction of an object, learned by a CNN network, is also incorporated and provides a shape prior for the quadric leading further refinement. To capture the dominant structure of the scene, additional planar landmarks are detected by a CNN-based plane detector and modeled as independent landmarks in the map. Extensive experiments support our proposed inclusion of semantic objects and planar structures directly in the bundle-adjustment of SLAM - Semantic SLAM - that enriches the reconstructed map semantically, while significantly improving the camera localization. The performance of our SLAM system is demonstrated in https://youtu.be/UMWXd4sHONw and https://youtu.be/QPQqVrvP0dE . |
| Tasks | Camera Localization, Object Detection, Simultaneous Localization and Mapping |
| Published | 2018-09-24 |
| URL | http://arxiv.org/abs/1809.09149v2 |
| http://arxiv.org/pdf/1809.09149v2.pdf | |
| PWC | https://paperswithcode.com/paper/real-time-monocular-object-model-aware-sparse |
| Repo | |
| Framework | |
Monocular Object and Plane SLAM in Structured Environments
| Title | Monocular Object and Plane SLAM in Structured Environments |
| Authors | Shichao Yang, Sebastian Scherer |
| Abstract | In this paper, we present a monocular Simultaneous Localization and Mapping (SLAM) algorithm using high-level object and plane landmarks. The built map is denser, more compact and semantic meaningful compared to feature point based SLAM. We first propose a high order graphical model to jointly infer the 3D object and layout planes from single images considering occlusions and semantic constraints. The extracted objects and planes are further optimized with camera poses in a unified SLAM framework. Objects and planes can provide more semantic constraints such as Manhattan plane and object supporting relationships compared to points. Experiments on various public and collected datasets including ICL NUIM and TUM Mono show that our algorithm can improve camera localization accuracy compared to state-of-the-art SLAM especially when there is no loop closure, and also generate dense maps robustly in many structured environments. |
| Tasks | Camera Localization, Simultaneous Localization and Mapping |
| Published | 2018-09-10 |
| URL | https://arxiv.org/abs/1809.03415v2 |
| https://arxiv.org/pdf/1809.03415v2.pdf | |
| PWC | https://paperswithcode.com/paper/monocular-object-and-plane-slam-in-structured |
| Repo | |
| Framework | |
Improving utility of brain tumor confocal laser endomicroscopy: objective value assessment and diagnostic frame detection with convolutional neural networks
| Title | Improving utility of brain tumor confocal laser endomicroscopy: objective value assessment and diagnostic frame detection with convolutional neural networks |
| Authors | Mohammadhassan Izadyyazdanabadi, Evgenii Belykh, Nikolay Martirosyan, Jennifer Eschbacher, Peter Nakaji, Yezhou Yang, Mark C. Preul |
| Abstract | Confocal laser endomicroscopy (CLE), although capable of obtaining images at cellular resolution during surgery of brain tumors in real time, creates as many non-diagnostic as diagnostic images. Non-useful images are often distorted due to relative motion between probe and brain or blood artifacts. Many images, however, simply lack diagnostic features immediately informative to the physician. Examining all the hundreds or thousands of images from a single case to discriminate diagnostic images from nondiagnostic ones can be tedious. Providing a real-time diagnostic value assessment of images (fast enough to be used during the surgical acquisition process and accurate enough for the pathologist to rely on) to automatically detect diagnostic frames would streamline the analysis of images and filter useful images for the pathologist/surgeon. We sought to automatically classify images as diagnostic or non-diagnostic. AlexNet, a deep-learning architecture, was used in a 4-fold cross validation manner. Our dataset includes 16,795 images (8572 nondiagnostic and 8223 diagnostic) from 74 CLE-aided brain tumor surgery patients. The ground truth for all the images is provided by the pathologist. Average model accuracy on test data was 91% overall (90.79 % accuracy, 90.94 % sensitivity and 90.87 % specificity). To evaluate the model reliability we also performed receiver operating characteristic (ROC) analysis yielding 0.958 average for the area under ROC curve (AUC). These results demonstrate that a deeply trained AlexNet network can achieve a model that reliably and quickly recognizes diagnostic CLE images. |
| Tasks | |
| Published | 2018-01-06 |
| URL | http://arxiv.org/abs/1801.02101v1 |
| http://arxiv.org/pdf/1801.02101v1.pdf | |
| PWC | https://paperswithcode.com/paper/improving-utility-of-brain-tumor-confocal |
| Repo | |
| Framework | |
DNN-HMM based Speaker Adaptive Emotion Recognition using Proposed Epoch and MFCC Features
| Title | DNN-HMM based Speaker Adaptive Emotion Recognition using Proposed Epoch and MFCC Features |
| Authors | Md. Shah Fahad, Jainath Yadav, Gyadhar Pradhan, Akshay Deepak |
| Abstract | Speech is produced when time varying vocal tract system is excited with time varying excitation source. Therefore, the information present in a speech such as message, emotion, language, speaker is due to the combined effect of both excitation source and vocal tract system. However, there is very less utilization of excitation source features to recognize emotion. In our earlier work, we have proposed a novel method to extract glottal closure instants (GCIs) known as epochs. In this paper, we have explored epoch features namely instantaneous pitch, phase and strength of epochs for discriminating emotions. We have combined the excitation source features and the well known Male-frequency cepstral coefficient (MFCC) features to develop an emotion recognition system with improved performance. DNN-HMM speaker adaptive models have been developed using MFCC, epoch and combined features. IEMOCAP emotional database has been used to evaluate the models. The average accuracy for emotion recognition system when using MFCC and epoch features separately is 59.25% and 54.52% respectively. The recognition performance improves to 64.2% when MFCC and epoch features are combined. |
| Tasks | Emotion Recognition |
| Published | 2018-06-04 |
| URL | http://arxiv.org/abs/1806.00984v1 |
| http://arxiv.org/pdf/1806.00984v1.pdf | |
| PWC | https://paperswithcode.com/paper/dnn-hmm-based-speaker-adaptive-emotion |
| Repo | |
| Framework | |
Cross-Modal Health State Estimation
| Title | Cross-Modal Health State Estimation |
| Authors | Nitish Nag, Vaibhav Pandey, Preston J. Putzel, Hari Bhimaraju, Srikanth Krishnan, Ramesh C. Jain |
| Abstract | Individuals create and consume more diverse data about themselves today than any time in history. Sources of this data include wearable devices, images, social media, geospatial information and more. A tremendous opportunity rests within cross-modal data analysis that leverages existing domain knowledge methods to understand and guide human health. Especially in chronic diseases, current medical practice uses a combination of sparse hospital based biological metrics (blood tests, expensive imaging, etc.) to understand the evolving health status of an individual. Future health systems must integrate data created at the individual level to better understand health status perpetually, especially in a cybernetic framework. In this work we fuse multiple user created and open source data streams along with established biomedical domain knowledge to give two types of quantitative state estimates of cardiovascular health. First, we use wearable devices to calculate cardiorespiratory fitness (CRF), a known quantitative leading predictor of heart disease which is not routinely collected in clinical settings. Second, we estimate inherent genetic traits, living environmental risks, circadian rhythm, and biological metrics from a diverse dataset. Our experimental results on 24 subjects demonstrate how multi-modal data can provide personalized health insight. Understanding the dynamic nature of health status will pave the way for better health based recommendation engines, better clinical decision making and positive lifestyle changes. |
| Tasks | Decision Making |
| Published | 2018-08-07 |
| URL | http://arxiv.org/abs/1808.06462v2 |
| http://arxiv.org/pdf/1808.06462v2.pdf | |
| PWC | https://paperswithcode.com/paper/cross-modal-health-state-estimation |
| Repo | |
| Framework | |
Towards Robotic Eye Surgery: Marker-free, Online Hand-eye Calibration using Optical Coherence Tomography Images
| Title | Towards Robotic Eye Surgery: Marker-free, Online Hand-eye Calibration using Optical Coherence Tomography Images |
| Authors | Mingchuan Zhou, Mahdi Hamad, Jakob Weiss, Abouzar Eslami, Kai Huang, Mathias Maier, Chris P. Lohmann, Nassir Navab, Alois Knoll, M. Ali Nasseri |
| Abstract | Ophthalmic microsurgery is known to be a challenging operation, which requires very precise and dexterous manipulation. Image guided robot-assisted surgery (RAS) is a promising solution that brings significant improvements in outcomes and reduces the physical limitations of human surgeons. However, this technology must be further developed before it can be routinely used in clinics. One of the problems is the lack of proper calibration between the robotic manipulator and appropriate imaging device. In this work, we developed a flexible framework for hand-eye calibration of an ophthalmic robot with a microscope-integrated Optical Coherence Tomography (MIOCT) without any markers. The proposed method consists of three main steps: a) we estimate the OCT calibration parameters; b) with micro-scale displacements controlled by the robot, we detect and segment the needle tip in 3D-OCT volume; c) we find the transformation between the coordinate system of the OCT camera and the coordinate system of the robot. We verified the capability of our framework in ex-vivo pig eye experiments and compared the results with a reference method (marker-based). In all experiments, our method showed a small difference from the marker based method, with a mean calibration error of 9.2 $\mu$m and 7.0 $\mu$m, respectively. Additionally, the noise test shows the robustness of the proposed method. |
| Tasks | Calibration |
| Published | 2018-08-17 |
| URL | http://arxiv.org/abs/1808.05805v1 |
| http://arxiv.org/pdf/1808.05805v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-robotic-eye-surgery-marker-free |
| Repo | |
| Framework | |
Object detection and tracking benchmark in industry based on improved correlation filter
| Title | Object detection and tracking benchmark in industry based on improved correlation filter |
| Authors | Shangzhen Luan, Yan Li, Xiaodi Wang, Baochang Zhang |
| Abstract | Real-time object detection and tracking have shown to be the basis of intelligent production for industrial 4.0 applications. It is a challenging task because of various distorted data in complex industrial setting. The correlation filter (CF) has been used to trade off the low-cost computation and high performance. However, traditional CF training strategy can not get satisfied performance for the various industrial data; because the simple sampling(bagging) during training process will not find the exact solutions in a data space with a large diversity. In this paper, we propose Dijkstra-distance based correlation filters (DBCF), which establishes a new learning framework that embeds distribution-related constraints into the multi-channel correlation filters (MCCF). DBCF is able to handle the huge variations existing in the industrial data by improving those constraints based on the shortest path among all solutions. To evaluate DBCF, we build a new dataset as the benchmark for industrial 4.0 application. Extensive experiments demonstrate that DBCF produces high performance and exceeds the state-of-the-art methods. The dataset and source code can be found at https://github.com/bczhangbczhang |
| Tasks | Object Detection, Real-Time Object Detection |
| Published | 2018-06-11 |
| URL | http://arxiv.org/abs/1806.03853v2 |
| http://arxiv.org/pdf/1806.03853v2.pdf | |
| PWC | https://paperswithcode.com/paper/object-detection-and-tracking-benchmark-in |
| Repo | |
| Framework | |
On the Impact of Various Types of Noise on Neural Machine Translation
| Title | On the Impact of Various Types of Noise on Neural Machine Translation |
| Authors | Huda Khayrallah, Philipp Koehn |
| Abstract | We examine how various types of noise in the parallel training data impact the quality of neural machine translation systems. We create five types of artificial noise and analyze how they degrade performance in neural and statistical machine translation. We find that neural models are generally more harmed by noise than statistical models. For one especially egregious type of noise they learn to just copy the input sentence. |
| Tasks | Machine Translation |
| Published | 2018-05-31 |
| URL | http://arxiv.org/abs/1805.12282v1 |
| http://arxiv.org/pdf/1805.12282v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-impact-of-various-types-of-noise-on |
| Repo | |
| Framework | |
Deep Convolutional Compressed Sensing for LiDAR Depth Completion
| Title | Deep Convolutional Compressed Sensing for LiDAR Depth Completion |
| Authors | Nathaniel Chodosh, Chaoyang Wang, Simon Lucey |
| Abstract | In this paper we consider the problem of estimating a dense depth map from a set of sparse LiDAR points. We use techniques from compressed sensing and the recently developed Alternating Direction Neural Networks (ADNNs) to create a deep recurrent auto-encoder for this task. Our architecture internally performs an algorithm for extracting multi-level convolutional sparse codes from the input which are then used to make a prediction. Our results demonstrate that with only two layers and 1800 parameters we are able to out perform all previously published results, including deep networks with orders of magnitude more parameters. |
| Tasks | Depth Completion |
| Published | 2018-03-23 |
| URL | http://arxiv.org/abs/1803.08949v1 |
| http://arxiv.org/pdf/1803.08949v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-convolutional-compressed-sensing-for |
| Repo | |
| Framework | |
Distinguishing correlation from causation using genome-wide association studies
| Title | Distinguishing correlation from causation using genome-wide association studies |
| Authors | Luke J. O’Connor, Alkes L. Price |
| Abstract | Genome-wide association studies (GWAS) have emerged as a rich source of genetic clues into disease biology, and they have revealed strong genetic correlations among many diseases and traits. Some of these genetic correlations may reflect causal relationships. We developed a method to quantify causal relationships between genetically correlated traits using GWAS summary association statistics. In particular, our method quantifies what part of the genetic component of trait 1 is also causal for trait 2 using mixed fourth moments $E(\alpha_1^2\alpha_1\alpha_2)$ and $E(\alpha_2^2\alpha_1\alpha_2)$ of the bivariate effect size distribution. If trait 1 is causal for trait 2, then SNPs affecting trait 1 (large $\alpha_1^2$) will have correlated effects on trait 2 (large $\alpha_1\alpha_2$), but not vice versa. We validated this approach in extensive simulations. Across 52 traits (average $N=331$k), we identified 30 putative genetically causal relationships, many novel, including an effect of LDL cholesterol on decreased bone mineral density. More broadly, we demonstrate that it is possible to distinguish between genetic correlation and causation using genetic association data. |
| Tasks | |
| Published | 2018-11-21 |
| URL | http://arxiv.org/abs/1811.08803v1 |
| http://arxiv.org/pdf/1811.08803v1.pdf | |
| PWC | https://paperswithcode.com/paper/distinguishing-correlation-from-causation |
| Repo | |
| Framework | |
Deep Learning for End-to-End Atrial Fibrillation Recurrence Estimation
| Title | Deep Learning for End-to-End Atrial Fibrillation Recurrence Estimation |
| Authors | Riddhish Bhalodia, Anupama Goparaju, Tim Sodergren, Alan Morris, Evgueni Kholmovski, Nassir Marrouche, Joshua Cates, Ross Whitaker, Shireen Elhabian |
| Abstract | Left atrium shape has been shown to be an independent predictor of recurrence after atrial fibrillation (AF) ablation. Shape-based representation is imperative to such an estimation process, where correspondence-based representation offers the most flexibility and ease-of-computation for population-level shape statistics. Nonetheless, population-level shape representations in the form of image segmentation and correspondence models derived from cardiac MRI require significant human resources with sufficient anatomy-specific expertise. In this paper, we propose a machine learning approach that uses deep networks to estimate AF recurrence by predicting shape descriptors directly from MRI images, with NO image pre-processing involved. We also propose a novel data augmentation scheme to effectively train a deep network in a limited training data setting. We compare this new method of estimating shape descriptors from images with the state-of-the-art correspondence-based shape modeling that requires image segmentation and correspondence optimization. Results show that the proposed method and the current state-of-the-art produce statistically similar outcomes on AF recurrence, eliminating the need for expensive pre-processing pipelines and associated human labor. |
| Tasks | Atrial Fibrillation Recurrence Estimation, Data Augmentation, Semantic Segmentation |
| Published | 2018-09-30 |
| URL | http://arxiv.org/abs/1810.00475v1 |
| http://arxiv.org/pdf/1810.00475v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-for-end-to-end-atrial |
| Repo | |
| Framework | |
Unsupervised Learning via Meta-Learning
| Title | Unsupervised Learning via Meta-Learning |
| Authors | Kyle Hsu, Sergey Levine, Chelsea Finn |
| Abstract | A central goal of unsupervised learning is to acquire representations from unlabeled data or experience that can be used for more effective learning of downstream tasks from modest amounts of labeled data. Many prior unsupervised learning works aim to do so by developing proxy objectives based on reconstruction, disentanglement, prediction, and other metrics. Instead, we develop an unsupervised meta-learning method that explicitly optimizes for the ability to learn a variety of tasks from small amounts of data. To do so, we construct tasks from unlabeled data in an automatic way and run meta-learning over the constructed tasks. Surprisingly, we find that, when integrated with meta-learning, relatively simple task construction mechanisms, such as clustering embeddings, lead to good performance on a variety of downstream, human-specified tasks. Our experiments across four image datasets indicate that our unsupervised meta-learning approach acquires a learning algorithm without any labeled data that is applicable to a wide range of downstream classification tasks, improving upon the embedding learned by four prior unsupervised learning methods. |
| Tasks | Meta-Learning |
| Published | 2018-10-04 |
| URL | http://arxiv.org/abs/1810.02334v6 |
| http://arxiv.org/pdf/1810.02334v6.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-learning-via-meta-learning |
| Repo | |
| Framework | |
