Paper Group ANR 826
Pyramid Network with Online Hard Example Mining for Accurate Left Atrium Segmentation. In-silico Risk Analysis of Personalized Artificial Pancreas Controllers via Rare-event Simulation. Echo state networks are universal. Convexity Shape Prior for Level Set based Image Segmentation Method. Context-Specific Validation of Data-Driven Models. Asynchron …
Pyramid Network with Online Hard Example Mining for Accurate Left Atrium Segmentation
Title | Pyramid Network with Online Hard Example Mining for Accurate Left Atrium Segmentation |
Authors | Cheng Bian, Xin Yang, Jianqiang Ma, Shen Zheng, Yu-An Liu, Reza Nezafat, Pheng-Ann Heng, Yefeng Zheng |
Abstract | Accurately segmenting left atrium in MR volume can benefit the ablation procedure of atrial fibrillation. Traditional automated solutions often fail in relieving experts from the labor-intensive manual labeling. In this paper, we propose a deep neural network based solution for automated left atrium segmentation in gadolinium-enhanced MR volumes with promising performance. We firstly argue that, for this volumetric segmentation task, networks in 2D fashion can present great superiorities in time efficiency and segmentation accuracy than networks with 3D fashion. Considering the highly varying shape of atrium and the branchy structure of associated pulmonary veins, we propose to adopt a pyramid module to collect semantic cues in feature maps from multiple scales for fine-grained segmentation. Also, to promote our network in classifying the hard examples, we propose an Online Hard Negative Example Mining strategy to identify voxels in slices with low classification certainties and penalize the wrong predictions on them. Finally, we devise a competitive training scheme to further boost the generalization ability of networks. Extensively verified on 20 testing volumes, our proposed framework achieves an average Dice of 92.83% in segmenting the left atria and pulmonary veins. |
Tasks | |
Published | 2018-12-14 |
URL | http://arxiv.org/abs/1812.05802v1 |
http://arxiv.org/pdf/1812.05802v1.pdf | |
PWC | https://paperswithcode.com/paper/pyramid-network-with-online-hard-example |
Repo | |
Framework | |
In-silico Risk Analysis of Personalized Artificial Pancreas Controllers via Rare-event Simulation
Title | In-silico Risk Analysis of Personalized Artificial Pancreas Controllers via Rare-event Simulation |
Authors | Matthew O’Kelly, Aman Sinha, Justin Norden, Hongseok Namkoong |
Abstract | Modern treatments for Type 1 diabetes (T1D) use devices known as artificial pancreata (APs), which combine an insulin pump with a continuous glucose monitor (CGM) operating in a closed-loop manner to control blood glucose levels. In practice, poor performance of APs (frequent hyper- or hypoglycemic events) is common enough at a population level that many T1D patients modify the algorithms on existing AP systems with unregulated open-source software. Anecdotally, the patients in this group have shown superior outcomes compared with standard of care, yet we do not understand how safe any AP system is since adverse outcomes are rare. In this paper, we construct generative models of individual patients’ physiological characteristics and eating behaviors. We then couple these models with a T1D simulator approved for pre-clinical trials by the FDA. Given the ability to simulate patient outcomes in-silico, we utilize techniques from rare-event simulation theory in order to efficiently quantify the performance of a device with respect to a particular patient. We show a 72,000$\times$ speedup in simulation speed over real-time and up to 2-10 times increase in the frequency which we are able to sample adverse conditions relative to standard Monte Carlo sampling. In practice our toolchain enables estimates of the likelihood of hypoglycemic events with approximately an order of magnitude fewer simulations. |
Tasks | |
Published | 2018-12-02 |
URL | http://arxiv.org/abs/1812.00293v1 |
http://arxiv.org/pdf/1812.00293v1.pdf | |
PWC | https://paperswithcode.com/paper/in-silico-risk-analysis-of-personalized |
Repo | |
Framework | |
Echo state networks are universal
Title | Echo state networks are universal |
Authors | Lyudmila Grigoryeva, Juan-Pablo Ortega |
Abstract | This paper shows that echo state networks are universal uniform approximants in the context of discrete-time fading memory filters with uniformly bounded inputs defined on negative infinite times. This result guarantees that any fading memory input/output system in discrete time can be realized as a simple finite-dimensional neural network-type state-space model with a static linear readout map. This approximation is valid for infinite time intervals. The proof of this statement is based on fundamental results, also presented in this work, about the topological nature of the fading memory property and about reservoir computing systems generated by continuous reservoir maps. |
Tasks | |
Published | 2018-06-03 |
URL | http://arxiv.org/abs/1806.00797v2 |
http://arxiv.org/pdf/1806.00797v2.pdf | |
PWC | https://paperswithcode.com/paper/echo-state-networks-are-universal |
Repo | |
Framework | |
Convexity Shape Prior for Level Set based Image Segmentation Method
Title | Convexity Shape Prior for Level Set based Image Segmentation Method |
Authors | Shi Yan, Xue-cheng Tai, Jun Liu, Hai-yang Huang |
Abstract | We propose a geometric convexity shape prior preservation method for variational level set based image segmentation methods. Our method is built upon the fact that the level set of a convex signed distanced function must be convex. This property enables us to transfer a complicated geometrical convexity prior into a simple inequality constraint on the function. An active set based Gauss-Seidel iteration is used to handle this constrained minimization problem to get an efficient algorithm. We apply our method to region and edge based level set segmentation models including Chan-Vese (CV) model with guarantee that the segmented region will be convex. Experimental results show the effectiveness and quality of the proposed model and algorithm. |
Tasks | Semantic Segmentation |
Published | 2018-05-22 |
URL | http://arxiv.org/abs/1805.08676v1 |
http://arxiv.org/pdf/1805.08676v1.pdf | |
PWC | https://paperswithcode.com/paper/convexity-shape-prior-for-level-set-based |
Repo | |
Framework | |
Context-Specific Validation of Data-Driven Models
Title | Context-Specific Validation of Data-Driven Models |
Authors | Somil Bansal, Shromona Ghosh, Alberto Sangiovanni-Vincentelli, Sanjit A. Seshia, Claire J. Tomlin |
Abstract | With an increasing use of data-driven models to control robotic systems, it has become important to develop a methodology for validating such models before they can be deployed to design a controller for the actual system. Specifically, it must be ensured that the controller designed for a learned model would perform as expected on the actual physical system. We propose a context-specific validation framework to quantify the quality of a learned model based on a distance measure between the closed-loop actual system and the learned model. We then propose an active sampling scheme to compute a probabilistic upper bound on this distance in a sample-efficient manner. The proposed framework validates the learned model against only those behaviors of the system that are relevant for the purpose for which we intend to use this model, and does not require any a priori knowledge of the system dynamics. Several simulations illustrate the practicality of the proposed framework for validating the models of real-world systems, and consequently, for controller synthesis. |
Tasks | |
Published | 2018-02-14 |
URL | http://arxiv.org/abs/1802.04929v2 |
http://arxiv.org/pdf/1802.04929v2.pdf | |
PWC | https://paperswithcode.com/paper/context-specific-validation-of-data-driven |
Repo | |
Framework | |
Asynchronous Advantage Actor-Critic Agent for Starcraft II
Title | Asynchronous Advantage Actor-Critic Agent for Starcraft II |
Authors | Basel Alghanem, Keerthana P G |
Abstract | Deep reinforcement learning, and especially the Asynchronous Advantage Actor-Critic algorithm, has been successfully used to achieve super-human performance in a variety of video games. Starcraft II is a new challenge for the reinforcement learning community with the release of pysc2 learning environment proposed by Google Deepmind and Blizzard Entertainment. Despite being a target for several AI developers, few have achieved human level performance. In this project we explain the complexities of this environment and discuss the results from our experiments on the environment. We have compared various architectures and have proved that transfer learning can be an effective paradigm in reinforcement learning research for complex scenarios requiring skill transfer. |
Tasks | Starcraft, Starcraft II, Transfer Learning |
Published | 2018-07-22 |
URL | http://arxiv.org/abs/1807.08217v1 |
http://arxiv.org/pdf/1807.08217v1.pdf | |
PWC | https://paperswithcode.com/paper/asynchronous-advantage-actor-critic-agent-for |
Repo | |
Framework | |
Motion-Appearance Co-Memory Networks for Video Question Answering
Title | Motion-Appearance Co-Memory Networks for Video Question Answering |
Authors | Jiyang Gao, Runzhou Ge, Kan Chen, Ram Nevatia |
Abstract | Video Question Answering (QA) is an important task in understanding video temporal structure. We observe that there are three unique attributes of video QA compared with image QA: (1) it deals with long sequences of images containing richer information not only in quantity but also in variety; (2) motion and appearance information are usually correlated with each other and able to provide useful attention cues to the other; (3) different questions require different number of frames to infer the answer. Based these observations, we propose a motion-appearance comemory network for video QA. Our networks are built on concepts from Dynamic Memory Network (DMN) and introduces new mechanisms for video QA. Specifically, there are three salient aspects: (1) a co-memory attention mechanism that utilizes cues from both motion and appearance to generate attention; (2) a temporal conv-deconv network to generate multi-level contextual facts; (3) a dynamic fact ensemble method to construct temporal representation dynamically for different questions. We evaluate our method on TGIF-QA dataset, and the results outperform state-of-the-art significantly on all four tasks of TGIF-QA. |
Tasks | Question Answering, Video Question Answering, Visual Question Answering |
Published | 2018-03-29 |
URL | http://arxiv.org/abs/1803.10906v1 |
http://arxiv.org/pdf/1803.10906v1.pdf | |
PWC | https://paperswithcode.com/paper/motion-appearance-co-memory-networks-for |
Repo | |
Framework | |
Practical Contextual Bandits with Regression Oracles
Title | Practical Contextual Bandits with Regression Oracles |
Authors | Dylan J. Foster, Alekh Agarwal, Miroslav Dudík, Haipeng Luo, Robert E. Schapire |
Abstract | A major challenge in contextual bandits is to design general-purpose algorithms that are both practically useful and theoretically well-founded. We present a new technique that has the empirical and computational advantages of realizability-based approaches combined with the flexibility of agnostic methods. Our algorithms leverage the availability of a regression oracle for the value-function class, a more realistic and reasonable oracle than the classification oracles over policies typically assumed by agnostic methods. Our approach generalizes both UCB and LinUCB to far more expressive possible model classes and achieves low regret under certain distributional assumptions. In an extensive empirical evaluation, compared to both realizability-based and agnostic baselines, we find that our approach typically gives comparable or superior results. |
Tasks | Multi-Armed Bandits |
Published | 2018-03-03 |
URL | http://arxiv.org/abs/1803.01088v1 |
http://arxiv.org/pdf/1803.01088v1.pdf | |
PWC | https://paperswithcode.com/paper/practical-contextual-bandits-with-regression |
Repo | |
Framework | |
OMG - Emotion Challenge Solution
Title | OMG - Emotion Challenge Solution |
Authors | Yuqi Cui, Xiao Zhang, Yang Wang, Chenfeng Guo, Dongrui Wu |
Abstract | This short paper describes our solution to the 2018 IEEE World Congress on Computational Intelligence One-Minute Gradual-Emotional Behavior Challenge, whose goal was to estimate continuous arousal and valence values from short videos. We designed four base regression models using visual and audio features, and then used a spectral approach to fuse them to obtain improved performance. |
Tasks | |
Published | 2018-04-30 |
URL | http://arxiv.org/abs/1805.00348v1 |
http://arxiv.org/pdf/1805.00348v1.pdf | |
PWC | https://paperswithcode.com/paper/omg-emotion-challenge-solution |
Repo | |
Framework | |
Shamap: Shape-based Manifold Learning
Title | Shamap: Shape-based Manifold Learning |
Authors | Fenglei Fan, Ziyu Su, Yueyang Teng, Ge Wang |
Abstract | For manifold learning, it is assumed that high-dimensional sample/data points are embedded on a low-dimensional manifold. Usually, distances among samples are computed to capture an underlying data structure. Here we propose a metric according to angular changes along a geodesic line, thereby reflecting the underlying shape-oriented information or a topological similarity between high- and low-dimensional representations of a data cloud. Our results demonstrate the feasibility and merits of the proposed dimensionality reduction scheme. |
Tasks | Dimensionality Reduction |
Published | 2018-02-15 |
URL | https://arxiv.org/abs/1802.05386v2 |
https://arxiv.org/pdf/1802.05386v2.pdf | |
PWC | https://paperswithcode.com/paper/shamap-shape-based-manifold-learning |
Repo | |
Framework | |
MDGAN: Boosting Anomaly Detection Using \Multi-Discriminator Generative Adversarial Networks
Title | MDGAN: Boosting Anomaly Detection Using \Multi-Discriminator Generative Adversarial Networks |
Authors | Yotam Intrator, Gilad Katz, Asaf Shabtai |
Abstract | Anomaly detection is often considered a challenging field of machine learning due to the difficulty of obtaining anomalous samples for training and the need to obtain a sufficient amount of training data. In recent years, autoencoders have been shown to be effective anomaly detectors that train only on “normal” data. Generative adversarial networks (GANs) have been used to generate additional training samples for classifiers, thus making them more accurate and robust. However, in anomaly detection GANs are only used to reconstruct existing samples rather than to generate additional ones. This stems both from the small amount and lack of diversity of anomalous data in most domains. In this study we propose MDGAN, a novel GAN architecture for improving anomaly detection through the generation of additional samples. Our approach uses two discriminators: a dense network for determining whether the generated samples are of sufficient quality (i.e., valid) and an autoencoder that serves as an anomaly detector. MDGAN enables us to reconcile two conflicting goals: 1) generate high-quality samples that can fool the first discriminator, and 2) generate samples that can eventually be effectively reconstructed by the second discriminator, thus improving its performance. Empirical evaluation on a diverse set of datasets demonstrates the merits of our approach. |
Tasks | Anomaly Detection |
Published | 2018-10-11 |
URL | http://arxiv.org/abs/1810.05221v1 |
http://arxiv.org/pdf/1810.05221v1.pdf | |
PWC | https://paperswithcode.com/paper/mdgan-boosting-anomaly-detection-using-multi |
Repo | |
Framework | |
Linear Combination of Distance Measures for Surrogate Models in Genetic Programming
Title | Linear Combination of Distance Measures for Surrogate Models in Genetic Programming |
Authors | Martin Zaefferer, Jörg Stork, Oliver Flasch, Thomas Bartz-Beielstein |
Abstract | Surrogate models are a well established approach to reduce the number of expensive function evaluations in continuous optimization. In the context of genetic programming, surrogate modeling still poses a challenge, due to the complex genotype-phenotype relationships. We investigate how different genotypic and phenotypic distance measures can be used to learn Kriging models as surrogates. We compare the measures and suggest to use their linear combination in a kernel. We test the resulting model in an optimization framework, using symbolic regression problem instances as a benchmark. Our experiments show that the model provides valuable information. Firstly, the model enables an improved optimization performance compared to a model-free algorithm. Furthermore, the model provides information on the contribution of different distance measures. The data indicates that a phenotypic distance measure is important during the early stages of an optimization run when less data is available. In contrast, genotypic measures, such as the tree edit distance, contribute more during the later stages. |
Tasks | |
Published | 2018-07-03 |
URL | http://arxiv.org/abs/1807.01019v1 |
http://arxiv.org/pdf/1807.01019v1.pdf | |
PWC | https://paperswithcode.com/paper/linear-combination-of-distance-measures-for |
Repo | |
Framework | |
Emerging Language Spaces Learned From Massively Multilingual Corpora
Title | Emerging Language Spaces Learned From Massively Multilingual Corpora |
Authors | Jörg Tiedemann |
Abstract | Translations capture important information about languages that can be used as implicit supervision in learning linguistic properties and semantic representations. In an information-centric view, translated texts may be considered as semantic mirrors of the original text and the significant variations that we can observe across various languages can be used to disambiguate a given expression using the linguistic signal that is grounded in translation. Parallel corpora consisting of massive amounts of human translations with a large linguistic variation can be applied to increase abstractions and we propose the use of highly multilingual machine translation models to find language-independent meaning representations. Our initial experiments show that neural machine translation models can indeed learn in such a setup and we can show that the learning algorithm picks up information about the relation between languages in order to optimize transfer leaning with shared parameters. The model creates a continuous language space that represents relationships in terms of geometric distances, which we can visualize to illustrate how languages cluster according to language families and groups. Does this open the door for new ideas of data-driven language typology with promising models and techniques in empirical cross-linguistic research? |
Tasks | Machine Translation |
Published | 2018-02-01 |
URL | http://arxiv.org/abs/1802.00273v1 |
http://arxiv.org/pdf/1802.00273v1.pdf | |
PWC | https://paperswithcode.com/paper/emerging-language-spaces-learned-from |
Repo | |
Framework | |
Learning to Refine Source Representations for Neural Machine Translation
Title | Learning to Refine Source Representations for Neural Machine Translation |
Authors | Xinwei Geng, Longyue Wang, Xing Wang, Bing Qin, Ting Liu, Zhaopeng Tu |
Abstract | Neural machine translation (NMT) models generally adopt an encoder-decoder architecture for modeling the entire translation process. The encoder summarizes the representation of input sentence from scratch, which is potentially a problem if the sentence is ambiguous. When translating a text, humans often create an initial understanding of the source sentence and then incrementally refine it along the translation on the target side. Starting from this intuition, we propose a novel encoder-refiner-decoder framework, which dynamically refines the source representations based on the generated target-side information at each decoding step. Since the refining operations are time-consuming, we propose a strategy, leveraging the power of reinforcement learning models, to decide when to refine at specific decoding steps. Experimental results on both Chinese-English and English-German translation tasks show that the proposed approach significantly and consistently improves translation performance over the standard encoder-decoder framework. Furthermore, when refining strategy is applied, results still show reasonable improvement over the baseline without much decrease in decoding speed. |
Tasks | Machine Translation |
Published | 2018-12-26 |
URL | http://arxiv.org/abs/1812.10230v1 |
http://arxiv.org/pdf/1812.10230v1.pdf | |
PWC | https://paperswithcode.com/paper/learning-to-refine-source-representations-for |
Repo | |
Framework | |
Probabilistic and Regularized Graph Convolutional Networks
Title | Probabilistic and Regularized Graph Convolutional Networks |
Authors | Sean Billings |
Abstract | This paper explores the recently proposed Graph Convolutional Network architecture proposed in (Kipf & Welling, 2016) The key points of their work is summarized and their results are reproduced. Graph regularization and alternative graph convolution approaches are explored. I find that explicit graph regularization was correctly rejected by (Kipf & Welling, 2016). I attempt to improve the performance of GCN by approximating a k-step transition matrix in place of the normalized graph laplacian, but I fail to find positive results. Nonetheless, the performance of several configurations of this GCN variation is shown for the Cora, Citeseer, and Pubmed datasets. |
Tasks | |
Published | 2018-03-12 |
URL | http://arxiv.org/abs/1803.04489v1 |
http://arxiv.org/pdf/1803.04489v1.pdf | |
PWC | https://paperswithcode.com/paper/probabilistic-and-regularized-graph |
Repo | |
Framework | |