Paper Group ANR 876
Examining the Capability of GANs to Replace Real Biomedical Images in Classification Models Training. ÆTHEL: Automatically Extracted Typelogical Derivations for Dutch. Online Predictive Optimization Framework for Stochastic Demand-Responsive Transit Services. Blang: Bayesian declarative modelling of arbitrary data structures. SymNet: Symmetrical Fi …
Examining the Capability of GANs to Replace Real Biomedical Images in Classification Models Training
| Title | Examining the Capability of GANs to Replace Real Biomedical Images in Classification Models Training |
| Authors | Vassili Kovalev, Siarhei Kazlouski |
| Abstract | In this paper, we explore the possibility of generating artificial biomedical images that can be used as a substitute for real image datasets in applied machine learning tasks. We are focusing on generation of realistic chest X-ray images as well as on the lymph node histology images using the two recent GAN architectures including DCGAN and PGGAN. The possibility of the use of artificial images instead of real ones for training machine learning models was examined by benchmark classification tasks being solved using conventional and deep learning methods. In particular, a comparison was made by replacing real images with synthetic ones at the model training stage and comparing the prediction results with the ones obtained while training on the real image data. It was found that the drop of classification accuracy caused by such training data substitution ranged between 2.2% and 3.5% for deep learning models and between 5.5% and 13.25% for conventional methods such as LBP + Random Forests. |
| Tasks | |
| Published | 2019-04-18 |
| URL | http://arxiv.org/abs/1904.08688v1 |
| http://arxiv.org/pdf/1904.08688v1.pdf | |
| PWC | https://paperswithcode.com/paper/examining-the-capability-of-gans-to-replace |
| Repo | |
| Framework | |
ÆTHEL: Automatically Extracted Typelogical Derivations for Dutch
| Title | ÆTHEL: Automatically Extracted Typelogical Derivations for Dutch |
| Authors | Konstantinos Kogkalidis, Michael Moortgat, Richard Moot |
| Abstract | We present {\AE}THEL, a semantic compositionality dataset for written Dutch. {\AE}THEL consists of two parts. First, it contains a lexicon of supertags for about 900 000 words in context. The supertags correspond to types of the simply typed linear lambda-calculus, enhanced with dependency decorations that capture grammatical roles supplementary to function-argument structures. On the basis of these types, {\AE}THEL further provides 72 192 validated derivations, presented in four formats: natural-deduction and sequent-style proofs, linear logic proofnets and the associated programs (lambda terms) for meaning composition. {\AE}THEL’s types and derivations are obtained by means of an extraction algorithm applied to the syntactic analyses of LASSY Small, the gold standard corpus of written Dutch. We discuss the extraction algorithm and show how `virtual elements’ in the original LASSY annotation of unbounded dependencies and coordination phenomena give rise to higher-order types. We suggest some example usecases highlighting the benefits of a type-driven approach at the syntax semantics interface. The following resources are open-sourced with {\AE}THEL: the lexical mappings between words and types, a subset of the dataset consisting of 7 924 semantic parses, and the Python code that implements the extraction algorithm. | |
| Tasks | |
| Published | 2019-12-29 |
| URL | https://arxiv.org/abs/1912.12635v2 |
| https://arxiv.org/pdf/1912.12635v2.pdf | |
| PWC | https://paperswithcode.com/paper/thel-automatically-extracted-type-logical |
| Repo | |
| Framework | |
Online Predictive Optimization Framework for Stochastic Demand-Responsive Transit Services
| Title | Online Predictive Optimization Framework for Stochastic Demand-Responsive Transit Services |
| Authors | Inon Peled, Kelvin Lee, Yu Jiang, Justin Dauwels, Francisco C. Pereira |
| Abstract | This study develops an online predictive optimization framework for dynamically operating a transit service in an area of crowd movements. The proposed framework integrates demand prediction and supply optimization to periodically redesign the service routes based on recently observed demand. To predict demand for the service, we use Quantile Regression to estimate the marginal distribution of movement counts between each pair of serviced locations. The framework then combines these marginals into a joint demand distribution by constructing a Gaussian copula, which captures the structure of correlation between the marginals. For supply optimization, we devise a linear programming model, which simultaneously determines the route structure and the service frequency according to the predicted demand. Importantly, our framework both preserves the uncertainty structure of future demand and leverages this for robust route optimization, while keeping both components decoupled. We evaluate our framework using a real-world case study of autonomous mobility in a university campus in Denmark. The results show that our framework often obtains the ground truth optimal solution, and can outperform conventional methods for route optimization, which do not leverage full predictive distributions. |
| Tasks | Autonomous Vehicles |
| Published | 2019-02-26 |
| URL | https://arxiv.org/abs/1902.09745v2 |
| https://arxiv.org/pdf/1902.09745v2.pdf | |
| PWC | https://paperswithcode.com/paper/online-framework-for-demand-responsive |
| Repo | |
| Framework | |
Blang: Bayesian declarative modelling of arbitrary data structures
| Title | Blang: Bayesian declarative modelling of arbitrary data structures |
| Authors | Alexandre Bouchard-Côté, Kevin Chern, Davor Cubranic, Sahand Hosseini, Justin Hume, Matteo Lepur, Zihui Ouyang, Giorgio Sgarbi |
| Abstract | Consider a Bayesian inference problem where a variable of interest does not take values in a Euclidean space. These “non-standard” data structures are in reality fairly common. They are frequently used in problems involving latent discrete factor models, networks, and domain specific problems such as sequence alignments and reconstructions, pedigrees, and phylogenies. In principle, Bayesian inference should be particularly well-suited in such scenarios, as the Bayesian paradigm provides a principled way to obtain confidence assessment for random variables of any type. However, much of the recent work on making Bayesian analysis more accessible and computationally efficient has focused on inference in Euclidean spaces. In this paper, we introduce Blang, a domain specific language (DSL) and library aimed at bridging this gap. Blang allows users to perform Bayesian analysis on arbitrary data types while using a declarative syntax similar to BUGS. Blang is augmented with intuitive language additions to invent data types of the user’s choosing. To perform inference at scale on such arbitrary state spaces, Blang leverages recent advances in parallelizable, non-reversible Markov chain Monte Carlo methods. |
| Tasks | Bayesian Inference |
| Published | 2019-12-22 |
| URL | https://arxiv.org/abs/1912.10396v1 |
| https://arxiv.org/pdf/1912.10396v1.pdf | |
| PWC | https://paperswithcode.com/paper/blang-bayesian-declarative-modelling-of |
| Repo | |
| Framework | |
SymNet: Symmetrical Filters in Convolutional Neural Networks
| Title | SymNet: Symmetrical Filters in Convolutional Neural Networks |
| Authors | Gregory Dzhezyan, Hubert Cecotti |
| Abstract | Symmetry is present in nature and science. In image processing, kernels for spatial filtering possess some symmetry (e.g. Sobel operators, Gaussian, Laplacian). Convolutional layers in artificial feed-forward neural networks have typically considered the kernel weights without any constraint. In this paper, we propose to investigate the impact of a symmetry constraint in convolutional layers for image classification tasks, taking our inspiration from the processes involved in the primary visual cortex and common image processing techniques. The goal is to assess the extent to which it is possible to enforce symmetrical constraints on the filters throughout the training process of a convolutional neural network (CNN) by modifying the weight update preformed during the backpropagation algorithm and to evaluate the change in performance. The main hypothesis of this paper is that the symmetrical constraint reduces the number of free parameters in the network, and it is able to achieve near identical performance to the modern methodology of training. In particular, we address the following cases: x/y-axis symmetry, point reflection, and anti-point reflection. The performance has been evaluated on four databases of images. The results support the conclusion that while random weights offer more freedom to the model, the symmetry constraint provides a similar level of performance while decreasing substantially the number of free parameters in the model. Such an approach can be valuable in phase-sensitive applications that require a linear phase property throughout the feature extraction process. |
| Tasks | Image Classification |
| Published | 2019-06-10 |
| URL | https://arxiv.org/abs/1906.04252v1 |
| https://arxiv.org/pdf/1906.04252v1.pdf | |
| PWC | https://paperswithcode.com/paper/symnet-symmetrical-filters-in-convolutional |
| Repo | |
| Framework | |
Formalism for Supporting the Development of Verifiably Safe Medical Guidelines with Statecharts
| Title | Formalism for Supporting the Development of Verifiably Safe Medical Guidelines with Statecharts |
| Authors | Chunhui Guo, Zhicheng Fu, Zhenyu Zhang, Shangping Ren, Lui Sha |
| Abstract | Improving the effectiveness and safety of patient care is the ultimate objective for medical cyber-physical systems. Many medical best practice guidelines exist, but most of the existing guidelines in handbooks are difficult for medical staff to remember and apply clinically. Furthermore, although the guidelines have gone through clinical validations, validations by medical professionals alone do not provide guarantees for the safety of medical cyber-physical systems. Hence, formal verification is also needed. The paper presents the formal semantics for a framework that we developed to support the development of verifiably safe medical guidelines. The framework allows computer scientists to work together with medical professionals to transform medical best practice guidelines into executable statechart models, Yakindu in particular, so that medical functionalities and properties can be quickly prototyped and validated. Existing formal verification technologies, UPPAAL timed automata in particular, is integrated into the framework to provide formal verification capabilities to verify safety properties. However, some components used/built into the framework, such as the open-source Yakindu statecharts as well as the transformation rules from statecharts to timed automata, do not have built-in semantics. The ambiguity becomes unavoidable unless formal semantics is defined for the framework, which is what the paper is to present. |
| Tasks | |
| Published | 2019-09-23 |
| URL | https://arxiv.org/abs/1909.10493v1 |
| https://arxiv.org/pdf/1909.10493v1.pdf | |
| PWC | https://paperswithcode.com/paper/190910493 |
| Repo | |
| Framework | |
Identifying Classes Susceptible to Adversarial Attacks
| Title | Identifying Classes Susceptible to Adversarial Attacks |
| Authors | Rangeet Pan, Md Johirul Islam, Shibbir Ahmed, Hridesh Rajan |
| Abstract | Despite numerous attempts to defend deep learning based image classifiers, they remain susceptible to the adversarial attacks. This paper proposes a technique to identify susceptible classes, those classes that are more easily subverted. To identify the susceptible classes we use distance-based measures and apply them on a trained model. Based on the distance among original classes, we create mapping among original classes and adversarial classes that helps to reduce the randomness of a model to a significant amount in an adversarial setting. We analyze the high dimensional geometry among the feature classes and identify the k most susceptible target classes in an adversarial attack. We conduct experiments using MNIST, Fashion MNIST, CIFAR-10 (ImageNet and ResNet-32) datasets. Finally, we evaluate our techniques in order to determine which distance-based measure works best and how the randomness of a model changes with perturbation. |
| Tasks | Adversarial Attack |
| Published | 2019-05-30 |
| URL | https://arxiv.org/abs/1905.13284v1 |
| https://arxiv.org/pdf/1905.13284v1.pdf | |
| PWC | https://paperswithcode.com/paper/identifying-classes-susceptible-to |
| Repo | |
| Framework | |
A Statistical View on Synthetic Aperture Imaging for Occlusion Removal
| Title | A Statistical View on Synthetic Aperture Imaging for Occlusion Removal |
| Authors | Indrajit Kurmi, David C. Schedl, Oliver Bimber |
| Abstract | Synthetic apertures find applications in many fields, such as radar, radio telescopes, microscopy, sonar, ultrasound, LiDAR, and optical imaging. They approximate the signal of a single hypothetical wide aperture sensor with either an array of static small aperture sensors or a single moving small aperture sensor. Common sense in synthetic aperture sampling is that a dense sampling pattern within a wide aperture is required to reconstruct a clear signal. In this article we show that there exists practical limits to both, synthetic aperture size and number of samples for the application of occlusion removal. This leads to an understanding on how to design synthetic aperture sampling patterns and sensors in a most optimal and practically efficient way. We apply our findings to airborne optical sectioning which uses camera drones and synthetic aperture imaging to computationally remove occluding vegetation or trees for inspecting ground surfaces. |
| Tasks | Common Sense Reasoning |
| Published | 2019-06-15 |
| URL | https://arxiv.org/abs/1906.06600v1 |
| https://arxiv.org/pdf/1906.06600v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-statistical-view-on-synthetic-aperture |
| Repo | |
| Framework | |
Automated Estimation of the Spinal Curvature via Spine Centerline Extraction with Ensembles of Cascaded Neural Networks
| Title | Automated Estimation of the Spinal Curvature via Spine Centerline Extraction with Ensembles of Cascaded Neural Networks |
| Authors | Florian Dubost, Benjamin Collery, Antonin Renaudier, Axel Roc, Nicolas Posocco, Gerda Bortsova, Wiro Niessen, Marleen de Bruijne |
| Abstract | Scoliosis is a condition defined by an abnormal spinal curvature. For diagnosis and treatment planning of scoliosis, spinal curvature can be estimated using Cobb angles. We propose an automated method for the estimation of Cobb angles from X-ray scans. First, the centerline of the spine was segmented using a cascade of two convolutional neural networks. After smoothing the centerline, Cobb angles were automatically estimated using the derivative of the centerline. We evaluated the results using the mean absolute error and the average symmetric mean absolute percentage error between the manual assessment by experts and the automated predictions. For optimization, we used 609 X-ray scans from the London Health Sciences Center, and for evaluation, we participated in the international challenge “Accurate Automated Spinal Curvature Estimation, MICCAI 2019” (100 scans). On the challenge’s test set, we obtained an average symmetric mean absolute percentage error of 22.96. |
| Tasks | |
| Published | 2019-11-04 |
| URL | https://arxiv.org/abs/1911.01126v2 |
| https://arxiv.org/pdf/1911.01126v2.pdf | |
| PWC | https://paperswithcode.com/paper/automated-estimation-of-the-spinal-curvature |
| Repo | |
| Framework | |
Learned Collaborative Stereo Refinement
| Title | Learned Collaborative Stereo Refinement |
| Authors | Patrick Knöbelreiter, Thomas Pock |
| Abstract | In this work, we propose a learning-based method to denoise and refine disparity maps of a given stereo method. The proposed variational network arises naturally from unrolling the iterates of a proximal gradient method applied to a variational energy defined in a joint disparity, color, and confidence image space. Our method allows to learn a robust collaborative regularizer leveraging the joint statistics of the color image, the confidence map and the disparity map. Due to the variational structure of our method, the individual steps can be easily visualized, thus enabling interpretability of the method. We can therefore provide interesting insights into how our method refines and denoises disparity maps. The efficiency of our method is demonstrated by the publicly available stereo benchmarks Middlebury 2014 and Kitti 2015. |
| Tasks | |
| Published | 2019-07-31 |
| URL | https://arxiv.org/abs/1907.13391v1 |
| https://arxiv.org/pdf/1907.13391v1.pdf | |
| PWC | https://paperswithcode.com/paper/learned-collaborative-stereo-refinement |
| Repo | |
| Framework | |
Training Decision Trees as Replacement for Convolution Layers
| Title | Training Decision Trees as Replacement for Convolution Layers |
| Authors | Wolfgang Fuhl, Gjergji Kasneci, Wolfgang Rosenstiel, Enkelejda Kasneci |
| Abstract | We present an alternative layer to convolution layers in convolutional neural networks (CNNs). Our approach reduces the complexity of convolutions by replacing it with binary decisions. Those binary decisions are used as indexes to conditional distributions where each weight represents a leaf in a decision tree. This means that only the indices to the weights need to be determined once, thus reducing the complexity of convolutions by the depth of the output tensor. Index computation is performed by simple binary decisions that require fewer cycles compared to conventionally used multiplications. In addition, we show how convolutions can be replaced by binary decisions. These binary decisions form indices in the conditional distributions and we show how they are used to replace 2D weight matrices as well as 3D weight tensors. These new layers can be trained like convolution layers in CNNs based on the backpropagation algorithm, for which we provide a formalization. Our results on multiple publicly available data sets show that our approach performs similar to conventional neuronal networks. Beyond the formalized reduction of complexity and the improved qualitative performance, we show the runtime improvement empirically compared to convolution layers. |
| Tasks | |
| Published | 2019-05-24 |
| URL | https://arxiv.org/abs/1905.10073v4 |
| https://arxiv.org/pdf/1905.10073v4.pdf | |
| PWC | https://paperswithcode.com/paper/training-decision-trees-as-replacement-for |
| Repo | |
| Framework | |
A Driving Intention Prediction Method Based on Hidden Markov Model for Autonomous Driving
| Title | A Driving Intention Prediction Method Based on Hidden Markov Model for Autonomous Driving |
| Authors | Shiwen Liu, Kan Zheng, Long Zhao, Pingzhi Fan |
| Abstract | In a mixed-traffic scenario where both autonomous vehicles and human-driving vehicles exist, a timely prediction of driving intentions of nearby human-driving vehicles is essential for the safe and efficient driving of an autonomous vehicle. In this paper, a driving intention prediction method based on Hidden Markov Model (HMM) is proposed for autonomous vehicles. HMMs representing different driving intentions are trained and tested with field collected data from a flyover. When training the models, either discrete or continuous characterization of the mobility features of vehicles is applied. Experimental results show that the HMMs trained with the continuous characterization of mobility features can give a higher prediction accuracy when they are used for predicting driving intentions. Moreover, when the surrounding traffic of the vehicle is taken into account, the performances of the proposed prediction method are further improved. |
| Tasks | Autonomous Driving, Autonomous Vehicles |
| Published | 2019-02-25 |
| URL | http://arxiv.org/abs/1902.09068v1 |
| http://arxiv.org/pdf/1902.09068v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-driving-intention-prediction-method-based |
| Repo | |
| Framework | |
Towards Visually Grounded Sub-Word Speech Unit Discovery
| Title | Towards Visually Grounded Sub-Word Speech Unit Discovery |
| Authors | David Harwath, James Glass |
| Abstract | In this paper, we investigate the manner in which interpretable sub-word speech units emerge within a convolutional neural network model trained to associate raw speech waveforms with semantically related natural image scenes. We show how diphone boundaries can be superficially extracted from the activation patterns of intermediate layers of the model, suggesting that the model may be leveraging these events for the purpose of word recognition. We present a series of experiments investigating the information encoded by these events. |
| Tasks | |
| Published | 2019-02-21 |
| URL | http://arxiv.org/abs/1902.08213v1 |
| http://arxiv.org/pdf/1902.08213v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-visually-grounded-sub-word-speech |
| Repo | |
| Framework | |
Double Anchor R-CNN for Human Detection in a Crowd
| Title | Double Anchor R-CNN for Human Detection in a Crowd |
| Authors | Kevin Zhang, Feng Xiong, Peize Sun, Li Hu, Boxun Li, Gang Yu |
| Abstract | Detecting human in a crowd is a challenging problem due to the uncertainties of occlusion patterns. In this paper, we propose to handle the crowd occlusion problem in human detection by leveraging the head part. Double Anchor RPN is developed to capture body and head parts in pairs. A proposal crossover strategy is introduced to generate high-quality proposals for both parts as a training augmentation. Features of coupled proposals are then aggregated efficiently to exploit the inherent relationship. Finally, a Joint NMS module is developed for robust post-processing. The proposed framework, called Double Anchor R-CNN, is able to detect the body and head for each person simultaneously in crowded scenarios. State-of-the-art results are reported on challenging human detection datasets. Our model yields log-average miss rates (MR) of 51.79pp on CrowdHuman, 55.01pp on COCOPersons~(crowded sub-dataset) and 40.02pp on CrowdPose~(crowded sub-dataset), which outperforms previous baseline detectors by 3.57pp, 3.82pp, and 4.24pp, respectively. We hope our simple and effective approach will serve as a solid baseline and help ease future research in crowded human detection. |
| Tasks | Human Detection |
| Published | 2019-09-22 |
| URL | https://arxiv.org/abs/1909.09998v1 |
| https://arxiv.org/pdf/1909.09998v1.pdf | |
| PWC | https://paperswithcode.com/paper/190909998 |
| Repo | |
| Framework | |
Multi-Modal Graph Interaction for Multi-Graph Convolution Network in Urban Spatiotemporal Forecasting
| Title | Multi-Modal Graph Interaction for Multi-Graph Convolution Network in Urban Spatiotemporal Forecasting |
| Authors | Xu Geng, Xiyu Wu, Lingyu Zhang, Qiang Yang, Yan Liu, Jieping Ye |
| Abstract | Graph convolution network based approaches have been recently used to model region-wise relationships in region-level prediction problems in urban computing. Each relationship represents a kind of spatial dependency, like region-wise distance or functional similarity. To incorporate multiple relationships into spatial feature extraction, we define the problem as a multi-modal machine learning problem on multi-graph convolution networks. Leveraging the advantage of multi-modal machine learning, we propose to develop modality interaction mechanisms for this problem, in order to reduce generalization error by reinforcing the learning of multimodal coordinated representations. In this work, we propose two interaction techniques for handling features in lower layers and higher layers respectively. In lower layers, we propose grouped GCN to combine the graph connectivity from different modalities for more complete spatial feature extraction. In higher layers, we adapt multi-linear relationship networks to GCN by exploring the dimension transformation and freezing part of the covariance structure. The adapted approach, called multi-linear relationship GCN, learns more generalized features to overcome the train-test divergence induced by time shifting. We evaluated our model on ridehailing demand forecasting problem using two real-world datasets. The proposed technique outperforms state-of-the art baselines in terms of prediction accuracy, training efficiency, interpretability and model robustness. |
| Tasks | |
| Published | 2019-05-27 |
| URL | https://arxiv.org/abs/1905.11395v1 |
| https://arxiv.org/pdf/1905.11395v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-modal-graph-interaction-for-multi-graph |
| Repo | |
| Framework | |
