Paper Group ANR 1031
Automatic 3D bi-ventricular segmentation of cardiac images by a shape-refined multi-task deep learning approach. A volumetric deep Convolutional Neural Network for simulation of mock dark matter halo catalogues. Iris and periocular recognition in arabian race horses using deep convolutional neural networks. Recommendation System based on Semantic S …
Automatic 3D bi-ventricular segmentation of cardiac images by a shape-refined multi-task deep learning approach
Title | Automatic 3D bi-ventricular segmentation of cardiac images by a shape-refined multi-task deep learning approach |
Authors | Jinming Duan, Ghalib Bello, Jo Schlemper, Wenjia Bai, Timothy J W Dawes, Carlo Biffi, Antonio de Marvao, Georgia Doumou, Declan P O’Regan, Daniel Rueckert |
Abstract | Deep learning approaches have achieved state-of-the-art performance in cardiac magnetic resonance (CMR) image segmentation. However, most approaches have focused on learning image intensity features for segmentation, whereas the incorporation of anatomical shape priors has received less attention. In this paper, we combine a multi-task deep learning approach with atlas propagation to develop a shape-constrained bi-ventricular segmentation pipeline for short-axis CMR volumetric images. The pipeline first employs a fully convolutional network (FCN) that learns segmentation and landmark localisation tasks simultaneously. The architecture of the proposed FCN uses a 2.5D representation, thus combining the computational advantage of 2D FCNs networks and the capability of addressing 3D spatial consistency without compromising segmentation accuracy. Moreover, the refinement step is designed to explicitly enforce a shape constraint and improve segmentation quality. This step is effective for overcoming image artefacts (e.g. due to different breath-hold positions and large slice thickness), which preclude the creation of anatomically meaningful 3D cardiac shapes. The proposed pipeline is fully automated, due to network’s ability to infer landmarks, which are then used downstream in the pipeline to initialise atlas propagation. We validate the pipeline on 1831 healthy subjects and 649 subjects with pulmonary hypertension. Extensive numerical experiments on the two datasets demonstrate that our proposed method is robust and capable of producing accurate, high-resolution and anatomically smooth bi-ventricular 3D models, despite the artefacts in input CMR volumes. |
Tasks | Semantic Segmentation |
Published | 2018-08-26 |
URL | https://arxiv.org/abs/1808.08578v3 |
https://arxiv.org/pdf/1808.08578v3.pdf | |
PWC | https://paperswithcode.com/paper/automatic-3d-bi-ventricular-segmentation-of |
Repo | |
Framework | |
A volumetric deep Convolutional Neural Network for simulation of mock dark matter halo catalogues
Title | A volumetric deep Convolutional Neural Network for simulation of mock dark matter halo catalogues |
Authors | Philippe Berger, George Stein |
Abstract | For modern large-scale structure survey techniques it has become standard practice to test data analysis pipelines on large suites of mock simulations, a task which is currently prohibitively expensive for full N-body simulations. Instead of calculating this costly gravitational evolution, we have trained a three-dimensional deep Convolutional Neural Network (CNN) to identify dark matter protohalos directly from the cosmological initial conditions. Training on halo catalogues from the Peak Patch semi-analytic code, we test various CNN architectures and find they generically achieve a Dice coefficient of ~92% in only 24 hours of training. We present a simple and fast geometric halo finding algorithm to extract halos from this powerful pixel-wise binary classifier and find that the predicted catalogues match the mass function and power spectra of the ground truth simulations to within ~10%. We investigate the effect of long-range tidal forces on an object-by-object basis and find that the network’s predictions are consistent with the non-linear ellipsoidal collapse equations used explicitly by the Peak Patch algorithm. |
Tasks | |
Published | 2018-05-11 |
URL | http://arxiv.org/abs/1805.04537v2 |
http://arxiv.org/pdf/1805.04537v2.pdf | |
PWC | https://paperswithcode.com/paper/a-volumetric-deep-convolutional-neural |
Repo | |
Framework | |
Iris and periocular recognition in arabian race horses using deep convolutional neural networks
Title | Iris and periocular recognition in arabian race horses using deep convolutional neural networks |
Authors | Mateusz Trokielewicz, Mateusz Szadkowski |
Abstract | This paper presents a study devoted to recognizing horses by means of their iris and periocular features using deep convolutional neural networks (DCNNs). Identification of race horses is crucial for animal identity confirmation prior to racing. As this is usually done shortly before a race, fast and reliable methods that are friendly and inflict no harm upon animals are important. Iris recognition has been shown to work with horse irides, provided that algorithms deployed for such task are fine-tuned for horse irides and input data is of very high quality. In our work, we examine a possibility of utilizing deep convolutional neural networks for a fusion of both iris and periocular region features. With such methodology, ocular biometrics in horses could perform well without employing complicated algorithms that require a lot of fine-tuning and prior knowledge of the input image, while at the same time being rotation, translation, and to some extent also image quality invariant. We were able to achieve promising results, with EER=9.5% using two network architectures with score-level fusion. |
Tasks | Iris Recognition |
Published | 2018-09-01 |
URL | http://arxiv.org/abs/1809.00213v1 |
http://arxiv.org/pdf/1809.00213v1.pdf | |
PWC | https://paperswithcode.com/paper/iris-and-periocular-recognition-in-arabian |
Repo | |
Framework | |
Recommendation System based on Semantic Scholar Mining and Topic modeling: A behavioral analysis of researchers from six conferences
Title | Recommendation System based on Semantic Scholar Mining and Topic modeling: A behavioral analysis of researchers from six conferences |
Authors | Hamed Jelodar, Yongli Wang, Mahdi Rabbani, Ru-xin Zhao, Seyedvalyallah Ayobi, Peng Hu, Isma Masood |
Abstract | Recommendation systems have an important place to help online users in the internet society. Recommendation Systems in computer science are of very practical use these days in various aspects of the Internet portals, such as social networks, and library websites. There are several approaches to implement recommendation systems, Latent Dirichlet Allocation (LDA) is one the popular techniques in Topic Modeling. Recently, researchers have proposed many approaches based on Recommendation Systems and LDA. According to importance of the subject, in this paper we discover the trends of the topics and find relationship between LDA topics and Scholar-Context-documents. In fact, We apply probabilistic topic modeling based on Gibbs sampling algorithms for a semantic mining from six conference publications in computer science from DBLP dataset. According to our experimental results, our semantic framework can be effective to help organizations to better organize these conferences and cover future research topics. |
Tasks | Recommendation Systems |
Published | 2018-12-20 |
URL | http://arxiv.org/abs/1812.08304v1 |
http://arxiv.org/pdf/1812.08304v1.pdf | |
PWC | https://paperswithcode.com/paper/recommendation-system-based-on-semantic |
Repo | |
Framework | |
Training Recurrent Neural Networks as a Constraint Satisfaction Problem
Title | Training Recurrent Neural Networks as a Constraint Satisfaction Problem |
Authors | Hamid Khodabandehlou, M. Sami Fadali |
Abstract | This paper presents a new approach for training artificial neural networks using techniques for solving the constraint satisfaction problem (CSP). The quotient gradient system (QGS) is a trajectory-based method for solving the CSP. This study converts the training set of a neural network into a CSP and uses the QGS to find its solutions. The QGS finds the global minimum of the optimization problem by tracking trajectories of a nonlinear dynamical system and does not stop at a local minimum of the optimization problem. Lyapunov theory is used to prove the asymptotic stability of the solutions with and without the presence of measurement errors. Numerical examples illustrate the effectiveness of the proposed methodology and compare it to a genetic algorithm and error backpropagation. |
Tasks | |
Published | 2018-03-20 |
URL | http://arxiv.org/abs/1803.07200v7 |
http://arxiv.org/pdf/1803.07200v7.pdf | |
PWC | https://paperswithcode.com/paper/training-recurrent-neural-networks-as-a |
Repo | |
Framework | |
Generating Plans that Predict Themselves
Title | Generating Plans that Predict Themselves |
Authors | Jaime F. Fisac, Chang Liu, Jessica B. Hamrick, S. Shankar Sastry, J. Karl Hedrick, Thomas L. Griffiths, Anca D. Dragan |
Abstract | Collaboration requires coordination, and we coordinate by anticipating our teammates’ future actions and adapting to their plan. In some cases, our teammates’ actions early on can give us a clear idea of what the remainder of their plan is, i.e. what action sequence we should expect. In others, they might leave us less confident, or even lead us to the wrong conclusion. Our goal is for robot actions to fall in the first category: we want to enable robots to select their actions in such a way that human collaborators can easily use them to correctly anticipate what will follow. While previous work has focused on finding initial plans that convey a set goal, here we focus on finding two portions of a plan such that the initial portion conveys the final one. We introduce $t$-\ACty{}: a measure that quantifies the accuracy and confidence with which human observers can predict the remaining robot plan from the overall task goal and the observed initial $t$ actions in the plan. We contribute a method for generating $t$-predictable plans: we search for a full plan that accomplishes the task, but in which the first $t$ actions make it as easy as possible to infer the remaining ones. The result is often different from the most efficient plan, in which the initial actions might leave a lot of ambiguity as to how the task will be completed. Through an online experiment and an in-person user study with physical robots, we find that our approach outperforms a traditional efficiency-based planner in objective and subjective collaboration metrics. |
Tasks | |
Published | 2018-02-14 |
URL | http://arxiv.org/abs/1802.05250v1 |
http://arxiv.org/pdf/1802.05250v1.pdf | |
PWC | https://paperswithcode.com/paper/generating-plans-that-predict-themselves |
Repo | |
Framework | |
Learning Illuminant Estimation from Object Recognition
Title | Learning Illuminant Estimation from Object Recognition |
Authors | Marco Buzzelli, Joost van de Weijer, Raimondo Schettini |
Abstract | In this paper we present a deep learning method to estimate the illuminant of an image. Our model is not trained with illuminant annotations, but with the objective of improving performance on an auxiliary task such as object recognition. To the best of our knowledge, this is the first example of a deep learning architecture for illuminant estimation that is trained without ground truth illuminants. We evaluate our solution on standard datasets for color constancy, and compare it with state of the art methods. Our proposal is shown to outperform most deep learning methods in a cross-dataset evaluation setup, and to present competitive results in a comparison with parametric solutions. |
Tasks | Color Constancy, Object Recognition |
Published | 2018-05-23 |
URL | http://arxiv.org/abs/1805.09264v1 |
http://arxiv.org/pdf/1805.09264v1.pdf | |
PWC | https://paperswithcode.com/paper/learning-illuminant-estimation-from-object |
Repo | |
Framework | |
Shifting the Baseline: Single Modality Performance on Visual Navigation & QA
Title | Shifting the Baseline: Single Modality Performance on Visual Navigation & QA |
Authors | Jesse Thomason, Daniel Gordon, Yonatan Bisk |
Abstract | We demonstrate the surprising strength of unimodal baselines in multimodal domains, and make concrete recommendations for best practices in future research. Where existing work often compares against random or majority class baselines, we argue that unimodal approaches better capture and reflect dataset biases and therefore provide an important comparison when assessing the performance of multimodal techniques. We present unimodal ablations on three recent datasets in visual navigation and QA, seeing an up to 29% absolute gain in performance over published baselines. |
Tasks | Question Answering, Visual Navigation |
Published | 2018-11-01 |
URL | http://arxiv.org/abs/1811.00613v3 |
http://arxiv.org/pdf/1811.00613v3.pdf | |
PWC | https://paperswithcode.com/paper/shifting-the-baseline-single-modality |
Repo | |
Framework | |
Deep Poisson gamma dynamical systems
Title | Deep Poisson gamma dynamical systems |
Authors | Dandan Guo, Bo Chen, Hao Zhang, Mingyuan Zhou |
Abstract | We develop deep Poisson-gamma dynamical systems (DPGDS) to model sequentially observed multivariate count data, improving previously proposed models by not only mining deep hierarchical latent structure from the data, but also capturing both first-order and long-range temporal dependencies. Using sophisticated but simple-to-implement data augmentation techniques, we derived closed-form Gibbs sampling update equations by first backward and upward propagating auxiliary latent counts, and then forward and downward sampling latent variables. Moreover, we develop stochastic gradient MCMC inference that is scalable to very long multivariate count time series. Experiments on both synthetic and a variety of real-world data demonstrate that the proposed model not only has excellent predictive performance, but also provides highly interpretable multilayer latent structure to represent hierarchical and temporal information propagation. |
Tasks | Data Augmentation, Time Series |
Published | 2018-10-26 |
URL | http://arxiv.org/abs/1810.11209v2 |
http://arxiv.org/pdf/1810.11209v2.pdf | |
PWC | https://paperswithcode.com/paper/deep-poisson-gamma-dynamical-systems |
Repo | |
Framework | |
Learning and Planning with a Semantic Model
Title | Learning and Planning with a Semantic Model |
Authors | Yi Wu, Yuxin Wu, Aviv Tamar, Stuart Russell, Georgia Gkioxari, Yuandong Tian |
Abstract | Building deep reinforcement learning agents that can generalize and adapt to unseen environments remains a fundamental challenge for AI. This paper describes progresses on this challenge in the context of man-made environments, which are visually diverse but contain intrinsic semantic regularities. We propose a hybrid model-based and model-free approach, LEArning and Planning with Semantics (LEAPS), consisting of a multi-target sub-policy that acts on visual inputs, and a Bayesian model over semantic structures. When placed in an unseen environment, the agent plans with the semantic model to make high-level decisions, proposes the next sub-target for the sub-policy to execute, and updates the semantic model based on new observations. We perform experiments in visual navigation tasks using House3D, a 3D environment that contains diverse human-designed indoor scenes with real-world objects. LEAPS outperforms strong baselines that do not explicitly plan using the semantic content. |
Tasks | Visual Navigation |
Published | 2018-09-28 |
URL | http://arxiv.org/abs/1809.10842v1 |
http://arxiv.org/pdf/1809.10842v1.pdf | |
PWC | https://paperswithcode.com/paper/learning-and-planning-with-a-semantic-model |
Repo | |
Framework | |
A Novel Deep Neural Network Architecture for Mars Visual Navigation
Title | A Novel Deep Neural Network Architecture for Mars Visual Navigation |
Authors | Jiang Zhang, Yuanqing Xia, Ganghui Shen |
Abstract | In this paper, emerging deep learning techniques are leveraged to deal with Mars visual navigation problem. Specifically, to achieve precise landing and autonomous navigation, a novel deep neural network architecture with double branches and non-recurrent structure is designed, which can represent both global and local deep features of Martian environment images effectively. By employing this architecture, Mars rover can determine the optimal navigation policy to the target point directly from original Martian environment images. Moreover, compared with the existing state-of-the-art algorithm, the training time is reduced by 45.8%. Finally, experiment results demonstrate that the proposed deep neural network architecture achieves better performance and faster convergence than the existing ones and generalizes well to unknown environment. |
Tasks | Autonomous Navigation, Visual Navigation |
Published | 2018-08-25 |
URL | http://arxiv.org/abs/1808.08395v1 |
http://arxiv.org/pdf/1808.08395v1.pdf | |
PWC | https://paperswithcode.com/paper/a-novel-deep-neural-network-architecture-for |
Repo | |
Framework | |
Detecting weak and strong Islamophobic hate speech on social media
Title | Detecting weak and strong Islamophobic hate speech on social media |
Authors | Bertie Vidgen, Taha Yasseri |
Abstract | Islamophobic hate speech on social media inflicts considerable harm on both targeted individuals and wider society, and also risks reputational damage for the host platforms. Accordingly, there is a pressing need for robust tools to detect and classify Islamophobic hate speech at scale. Previous research has largely approached the detection of Islamophobic hate speech on social media as a binary task. However, the varied nature of Islamophobia means that this is often inappropriate for both theoretically-informed social science and effectively monitoring social media. Drawing on in-depth conceptual work we build a multi-class classifier which distinguishes between non-Islamophobic, weak Islamophobic and strong Islamophobic content. Accuracy is 77.6% and balanced accuracy is 83%. We apply the classifier to a dataset of 109,488 tweets produced by far right Twitter accounts during 2017. Whilst most tweets are not Islamophobic, weak Islamophobia is considerably more prevalent (36,963 tweets) than strong (14,895 tweets). Our main input feature is a gloVe word embeddings model trained on a newly collected corpus of 140 million tweets. It outperforms a generic word embeddings model by 5.9 percentage points, demonstrating the importan4ce of context. Unexpectedly, we also find that a one-against-one multi class SVM outperforms a deep learning algorithm. |
Tasks | Word Embeddings |
Published | 2018-12-12 |
URL | http://arxiv.org/abs/1812.10400v1 |
http://arxiv.org/pdf/1812.10400v1.pdf | |
PWC | https://paperswithcode.com/paper/detecting-weak-and-strong-islamophobic-hate |
Repo | |
Framework | |
DARTS: Deceiving Autonomous Cars with Toxic Signs
Title | DARTS: Deceiving Autonomous Cars with Toxic Signs |
Authors | Chawin Sitawarin, Arjun Nitin Bhagoji, Arsalan Mosenia, Mung Chiang, Prateek Mittal |
Abstract | Sign recognition is an integral part of autonomous cars. Any misclassification of traffic signs can potentially lead to a multitude of disastrous consequences, ranging from a life-threatening accident to even a large-scale interruption of transportation services relying on autonomous cars. In this paper, we propose and examine security attacks against sign recognition systems for Deceiving Autonomous caRs with Toxic Signs (we call the proposed attacks DARTS). In particular, we introduce two novel methods to create these toxic signs. First, we propose Out-of-Distribution attacks, which expand the scope of adversarial examples by enabling the adversary to generate these starting from an arbitrary point in the image space compared to prior attacks which are restricted to existing training/test data (In-Distribution). Second, we present the Lenticular Printing attack, which relies on an optical phenomenon to deceive the traffic sign recognition system. We extensively evaluate the effectiveness of the proposed attacks in both virtual and real-world settings and consider both white-box and black-box threat models. Our results demonstrate that the proposed attacks are successful under both settings and threat models. We further show that Out-of-Distribution attacks can outperform In-Distribution attacks on classifiers defended using the adversarial training defense, exposing a new attack vector for these defenses. |
Tasks | Traffic Sign Recognition |
Published | 2018-02-18 |
URL | http://arxiv.org/abs/1802.06430v3 |
http://arxiv.org/pdf/1802.06430v3.pdf | |
PWC | https://paperswithcode.com/paper/darts-deceiving-autonomous-cars-with-toxic |
Repo | |
Framework | |
Bench-Marking Information Extraction in Semi-Structured Historical Handwritten Records
Title | Bench-Marking Information Extraction in Semi-Structured Historical Handwritten Records |
Authors | Animesh Prasad, Hervé Déjean, Jean-Luc Meunier, Max Weidemann, Johannes Michael, Gundram Leifert |
Abstract | In this report, we present our findings from benchmarking experiments for information extraction on historical handwritten marriage records Esposalles from IEHHR - ICDAR 2017 robust reading competition. The information extraction is modeled as semantic labeling of the sequence across 2 set of labels. This can be achieved by sequentially or jointly applying handwritten text recognition (HTR) and named entity recognition (NER). We deploy a pipeline approach where first we use state-of-the-art HTR and use its output as input for NER. We show that given low resource setup and simple structure of the records, high performance of HTR ensures overall high performance. We explore the various configurations of conditional random fields and neural networks to benchmark NER on given certain noisy input. The best model on 10-fold cross-validation as well as blind test data uses n-gram features with bidirectional long short-term memory. |
Tasks | Named Entity Recognition |
Published | 2018-07-17 |
URL | http://arxiv.org/abs/1807.06270v1 |
http://arxiv.org/pdf/1807.06270v1.pdf | |
PWC | https://paperswithcode.com/paper/bench-marking-information-extraction-in-semi |
Repo | |
Framework | |
Efficient and Scalable Multi-task Regression on Massive Number of Tasks
Title | Efficient and Scalable Multi-task Regression on Massive Number of Tasks |
Authors | Xiao He, Francesco Alesiani, Ammar Shaker |
Abstract | Many real-world large-scale regression problems can be formulated as Multi-task Learning (MTL) problems with a massive number of tasks, as in retail and transportation domains. However, existing MTL methods still fail to offer both the generalization performance and the scalability for such problems. Scaling up MTL methods to problems with a tremendous number of tasks is a big challenge. Here, we propose a novel algorithm, named Convex Clustering Multi-Task regression Learning (CCMTL), which integrates with convex clustering on the k-nearest neighbor graph of the prediction models. Further, CCMTL efficiently solves the underlying convex problem with a newly proposed optimization method. CCMTL is accurate, efficient to train, and empirically scales linearly in the number of tasks. On both synthetic and real-world datasets, the proposed CCMTL outperforms seven state-of-the-art (SoA) multi-task learning methods in terms of prediction accuracy as well as computational efficiency. On a real-world retail dataset with 23,812 tasks, CCMTL requires only around 30 seconds to train on a single thread, while the SoA methods need up to hours or even days. |
Tasks | Multi-Task Learning |
Published | 2018-11-14 |
URL | http://arxiv.org/abs/1811.05695v1 |
http://arxiv.org/pdf/1811.05695v1.pdf | |
PWC | https://paperswithcode.com/paper/efficient-and-scalable-multi-task-regression |
Repo | |
Framework | |