Paper Group ANR 1083
ScoutBot: A Dialogue System for Collaborative Navigation. Considerations for a PAP Smear Image Analysis System with CNN Features. Distilled Wasserstein Learning for Word Embedding and Topic Modeling. Proceedings of the eleventh Workshop on Answer Set Programming and Other Computing Paradigms 2018. Fast Flexible Function Dispatch in Julia. Learning …
ScoutBot: A Dialogue System for Collaborative Navigation
| Title | ScoutBot: A Dialogue System for Collaborative Navigation |
| Authors | Stephanie M. Lukin, Felix Gervits, Cory J. Hayes, Anton Leuski, Pooja Moolchandani, John G. Rogers III, Carlos Sanchez Amaro, Matthew Marge, Clare R. Voss, David Traum |
| Abstract | ScoutBot is a dialogue interface to physical and simulated robots that supports collaborative exploration of environments. The demonstration will allow users to issue unconstrained spoken language commands to ScoutBot. ScoutBot will prompt for clarification if the user’s instruction needs additional input. It is trained on human-robot dialogue collected from Wizard-of-Oz experiments, where robot responses were initiated by a human wizard in previous interactions. The demonstration will show a simulated ground robot (Clearpath Jackal) in a simulated environment supported by ROS (Robot Operating System). |
| Tasks | |
| Published | 2018-07-21 |
| URL | http://arxiv.org/abs/1807.08074v1 |
| http://arxiv.org/pdf/1807.08074v1.pdf | |
| PWC | https://paperswithcode.com/paper/scoutbot-a-dialogue-system-for-collaborative |
| Repo | |
| Framework | |
Considerations for a PAP Smear Image Analysis System with CNN Features
| Title | Considerations for a PAP Smear Image Analysis System with CNN Features |
| Authors | Srishti Gautam, Harinarayan K. K., Nirmal Jith, Anil K. Sao, Arnav Bhavsar, Adarsh Natarajan |
| Abstract | It has been shown that for automated PAP-smear image classification, nucleus features can be very informative. Therefore, the primary step for automated screening can be cell-nuclei detection followed by segmentation of nuclei in the resulting single cell PAP-smear images. We propose a patch based approach using CNN for segmentation of nuclei in single cell images. We then pose the question of ion of segmentation for classification using representation learning with CNN, and whether low-level CNN features may be useful for classification. We suggest a CNN-based feature level analysis and a transfer learning based approach for classification using both segmented as well full single cell images. We also propose a decision-tree based approach for classification. Experimental results demonstrate the effectiveness of the proposed algorithms individually (with low-level CNN features), and simultaneously proving the sufficiency of cell-nuclei detection (rather than accurate segmentation) for classification. Thus, we propose a system for analysis of multi-cell PAP-smear images consisting of a simple nuclei detection algorithm followed by classification using transfer learning. |
| Tasks | Image Classification, Representation Learning, Transfer Learning |
| Published | 2018-06-23 |
| URL | http://arxiv.org/abs/1806.09025v1 |
| http://arxiv.org/pdf/1806.09025v1.pdf | |
| PWC | https://paperswithcode.com/paper/considerations-for-a-pap-smear-image-analysis |
| Repo | |
| Framework | |
Distilled Wasserstein Learning for Word Embedding and Topic Modeling
| Title | Distilled Wasserstein Learning for Word Embedding and Topic Modeling |
| Authors | Hongteng Xu, Wenlin Wang, Wei Liu, Lawrence Carin |
| Abstract | We propose a novel Wasserstein method with a distillation mechanism, yielding joint learning of word embeddings and topics. The proposed method is based on the fact that the Euclidean distance between word embeddings may be employed as the underlying distance in the Wasserstein topic model. The word distributions of topics, their optimal transports to the word distributions of documents, and the embeddings of words are learned in a unified framework. When learning the topic model, we leverage a distilled underlying distance matrix to update the topic distributions and smoothly calculate the corresponding optimal transports. Such a strategy provides the updating of word embeddings with robust guidance, improving the algorithmic convergence. As an application, we focus on patient admission records, in which the proposed method embeds the codes of diseases and procedures and learns the topics of admissions, obtaining superior performance on clinically-meaningful disease network construction, mortality prediction as a function of admission codes, and procedure recommendation. |
| Tasks | Mortality Prediction, Word Embeddings |
| Published | 2018-09-12 |
| URL | http://arxiv.org/abs/1809.04705v1 |
| http://arxiv.org/pdf/1809.04705v1.pdf | |
| PWC | https://paperswithcode.com/paper/distilled-wasserstein-learning-for-word |
| Repo | |
| Framework | |
Proceedings of the eleventh Workshop on Answer Set Programming and Other Computing Paradigms 2018
| Title | Proceedings of the eleventh Workshop on Answer Set Programming and Other Computing Paradigms 2018 |
| Authors | Jorge Fandinno, Johannes Fichte |
| Abstract | This is the Proceedings of the eleventh Workshop on Answer Set Programming and Other Computing Paradigms (ASPOCP) 2018, which was held in Oxford, UK, July 18th, 2018. |
| Tasks | |
| Published | 2018-12-09 |
| URL | https://arxiv.org/abs/1812.03508v3 |
| https://arxiv.org/pdf/1812.03508v3.pdf | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-eleventh-workshop-on |
| Repo | |
| Framework | |
Fast Flexible Function Dispatch in Julia
| Title | Fast Flexible Function Dispatch in Julia |
| Authors | Jeff Bezanson, Jake Bolewski, Jiahao Chen |
| Abstract | Technical computing is a challenging application area for programming languages to address. This is evinced by the unusually large number of specialized languages in the area (e.g. MATLAB, R), and the complexity of common software stacks, often involving multiple languages and custom code generators. We believe this is ultimately due to key characteristics of the domain: highly complex operators, a need for extensive code specialization for performance, and a desire for permissive high-level programming styles allowing productive experimentation. The Julia language attempts to provide a more effective structure for this kind of programming by allowing programmers to express complex polymorphic behaviors using dynamic multiple dispatch over parametric types. The forms of extension and reuse permitted by this paradigm have proven valuable for technical computing. We report on how this approach has allowed domain experts to express useful abstractions while simultaneously providing a natural path to better performance for high-level technical code. |
| Tasks | |
| Published | 2018-08-09 |
| URL | http://arxiv.org/abs/1808.03370v1 |
| http://arxiv.org/pdf/1808.03370v1.pdf | |
| PWC | https://paperswithcode.com/paper/fast-flexible-function-dispatch-in-julia |
| Repo | |
| Framework | |
Learning One Convolutional Layer with Overlapping Patches
| Title | Learning One Convolutional Layer with Overlapping Patches |
| Authors | Surbhi Goel, Adam Klivans, Raghu Meka |
| Abstract | We give the first provably efficient algorithm for learning a one hidden layer convolutional network with respect to a general class of (potentially overlapping) patches. Additionally, our algorithm requires only mild conditions on the underlying distribution. We prove that our framework captures commonly used schemes from computer vision, including one-dimensional and two-dimensional “patch and stride” convolutions. Our algorithm– $Convotron$ – is inspired by recent work applying isotonic regression to learning neural networks. Convotron uses a simple, iterative update rule that is stochastic in nature and tolerant to noise (requires only that the conditional mean function is a one layer convolutional network, as opposed to the realizable setting). In contrast to gradient descent, Convotron requires no special initialization or learning-rate tuning to converge to the global optimum. We also point out that learning one hidden convolutional layer with respect to a Gaussian distribution and just $one$ disjoint patch $P$ (the other patches may be arbitrary) is $easy$ in the following sense: Convotron can efficiently recover the hidden weight vector by updating $only$ in the direction of $P$. |
| Tasks | |
| Published | 2018-02-07 |
| URL | http://arxiv.org/abs/1802.02547v1 |
| http://arxiv.org/pdf/1802.02547v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-one-convolutional-layer-with |
| Repo | |
| Framework | |
Generative Adversarial Training for MRA Image Synthesis Using Multi-Contrast MRI
| Title | Generative Adversarial Training for MRA Image Synthesis Using Multi-Contrast MRI |
| Authors | Sahin Olut, Yusuf Huseyin Sahin, Ugur Demir, Gozde Unal |
| Abstract | Magnetic Resonance Angiography (MRA) has become an essential MR contrast for imaging and evaluation of vascular anatomy and related diseases. MRA acquisitions are typically ordered for vascular interventions, whereas in typical scenarios, MRA sequences can be absent in the patient scans. This motivates the need for a technique that generates inexistent MRA from existing MR multi-contrast, which could be a valuable tool in retrospective subject evaluations and imaging studies. In this paper, we present a generative adversarial network (GAN) based technique to generate MRA from T1-weighted and T2-weighted MRI images, for the first time to our knowledge. To better model the representation of vessels which the MRA inherently highlights, we design a loss term dedicated to a faithful reproduction of vascularities. To that end, we incorporate steerable filter responses of the generated and reference images inside a Huber function loss term. Extending the well- established generator-discriminator architecture based on the recent PatchGAN model with the addition of steerable filter loss, the proposed steerable GAN (sGAN) method is evaluated on the large public database IXI. Experimental results show that the sGAN outperforms the baseline GAN method in terms of an overlap score with similar PSNR values, while it leads to improved visual perceptual quality. |
| Tasks | Image Generation |
| Published | 2018-04-12 |
| URL | http://arxiv.org/abs/1804.04366v1 |
| http://arxiv.org/pdf/1804.04366v1.pdf | |
| PWC | https://paperswithcode.com/paper/generative-adversarial-training-for-mra-image |
| Repo | |
| Framework | |
Global and local evaluation of link prediction tasks with neural embeddings
| Title | Global and local evaluation of link prediction tasks with neural embeddings |
| Authors | Asan Agibetov, Matthias Samwald |
| Abstract | We focus our attention on the link prediction problem for knowledge graphs, which is treated herein as a binary classification task on neural embeddings of the entities. By comparing, combining and extending different methodologies for link prediction on graph-based data coming from different domains, we formalize a unified methodology for the quality evaluation benchmark of neural embeddings for knowledge graphs. This benchmark is then used to empirically investigate the potential of training neural embeddings globally for the entire graph, as opposed to the usual way of training embeddings locally for a specific relation. This new way of testing the quality of the embeddings evaluates the performance of binary classifiers for scalable link prediction with limited data. Our evaluation pipeline is made open source, and with this we aim to draw more attention of the community towards an important issue of transparency and reproducibility of the neural embeddings evaluations. |
| Tasks | Knowledge Graphs, Link Prediction |
| Published | 2018-07-27 |
| URL | http://arxiv.org/abs/1807.10511v1 |
| http://arxiv.org/pdf/1807.10511v1.pdf | |
| PWC | https://paperswithcode.com/paper/global-and-local-evaluation-of-link |
| Repo | |
| Framework | |
Mo2Cap2: Real-time Mobile 3D Motion Capture with a Cap-mounted Fisheye Camera
| Title | Mo2Cap2: Real-time Mobile 3D Motion Capture with a Cap-mounted Fisheye Camera |
| Authors | Weipeng Xu, Avishek Chatterjee, Michael Zollhoefer, Helge Rhodin, Pascal Fua, Hans-Peter Seidel, Christian Theobalt |
| Abstract | We propose the first real-time approach for the egocentric estimation of 3D human body pose in a wide range of unconstrained everyday activities. This setting has a unique set of challenges, such as mobility of the hardware setup, and robustness to long capture sessions with fast recovery from tracking failures. We tackle these challenges based on a novel lightweight setup that converts a standard baseball cap to a device for high-quality pose estimation based on a single cap-mounted fisheye camera. From the captured egocentric live stream, our CNN based 3D pose estimation approach runs at 60Hz on a consumer-level GPU. In addition to the novel hardware setup, our other main contributions are: 1) a large ground truth training corpus of top-down fisheye images and 2) a novel disentangled 3D pose estimation approach that takes the unique properties of the egocentric viewpoint into account. As shown by our evaluation, we achieve lower 3D joint error as well as better 2D overlay than the existing baselines. |
| Tasks | 3D Pose Estimation, Motion Capture, Pose Estimation |
| Published | 2018-03-15 |
| URL | http://arxiv.org/abs/1803.05959v2 |
| http://arxiv.org/pdf/1803.05959v2.pdf | |
| PWC | https://paperswithcode.com/paper/mo2cap2-real-time-mobile-3d-motion-capture |
| Repo | |
| Framework | |
Safe exploration of nonlinear dynamical systems: A predictive safety filter for reinforcement learning
| Title | Safe exploration of nonlinear dynamical systems: A predictive safety filter for reinforcement learning |
| Authors | Kim P. Wabersich, Melanie N. Zeilinger |
| Abstract | The transfer of reinforcement learning (RL) techniques into real-world applications is challenged by safety requirements in the presence of physical limitations. Most RL methods, in particular the most popular algorithms, do not support explicit consideration of state and input constraints. In this paper, we address this problem for nonlinear systems with continuous state and input spaces by introducing a predictive safety filter, which is able to turn a constrained dynamical system into an unconstrained safe system, to which any RL algorithm can be applied `out-of-the-box’. The predictive safety filter receives the proposed learning input and decides, based on the current system state, if it can be safely applied to the real system, or if it has to be modified otherwise. Safety is thereby established by a continuously updated safety policy, which is based on a model predictive control formulation using a data-driven system model and considering state and input dependent uncertainties. | |
| Tasks | Safe Exploration |
| Published | 2018-12-13 |
| URL | http://arxiv.org/abs/1812.05506v2 |
| http://arxiv.org/pdf/1812.05506v2.pdf | |
| PWC | https://paperswithcode.com/paper/safe-exploration-of-nonlinear-dynamical |
| Repo | |
| Framework | |
Feature Selection Based on Unique Relevant Information for Health Data
| Title | Feature Selection Based on Unique Relevant Information for Health Data |
| Authors | Shiyu Liu, Mehul Motani |
| Abstract | Feature selection, which searches for the most representative features in observed data, is critical for health data analysis. Unlike feature extraction, such as PCA and autoencoder based methods, feature selection preserves interpretability, meaning that the selected features provide direct information about certain health conditions (i.e., the label). Thus, feature selection allows domain experts, such as clinicians, to understand the predictions made by machine learning based systems, as well as improve their own diagnostic skills. Mutual information is often used as a basis for feature selection since it measures dependencies between features and labels. In this paper, we introduce a novel mutual information based feature selection (MIBFS) method called SURI, which boosts features with high unique relevant information. We compare SURI to existing MIBFS methods using 3 different classifiers on 6 publicly available healthcare data sets. The results indicate that, in addition to preserving interpretability, SURI selects more relevant feature subsets which lead to higher classification performance. More importantly, we explore the dynamics of mutual information on a public low-dimensional health data set via exhaustive search. The results suggest the important role of unique relevant information in feature selection and verify the principles behind SURI. |
| Tasks | Feature Selection |
| Published | 2018-12-02 |
| URL | http://arxiv.org/abs/1812.00415v1 |
| http://arxiv.org/pdf/1812.00415v1.pdf | |
| PWC | https://paperswithcode.com/paper/feature-selection-based-on-unique-relevant |
| Repo | |
| Framework | |
Deformable Part Networks
| Title | Deformable Part Networks |
| Authors | Ziming Zhang, Rongmei Lin, Alan Sullivan |
| Abstract | In this paper we propose novel Deformable Part Networks (DPNs) to learn {\em pose-invariant} representations for 2D object recognition. In contrast to the state-of-the-art pose-aware networks such as CapsNet \cite{sabour2017dynamic} and STN \cite{jaderberg2015spatial}, DPNs can be naturally {\em interpreted} as an efficient solver for a challenging detection problem, namely Localized Deformable Part Models (LDPMs) where localization is introduced to DPMs as another latent variable for searching for the best poses of objects over all pixels and (predefined) scales. In particular we construct DPNs as sequences of such LDPM units to model the semantic and spatial relations among the deformable parts as hierarchical composition and spatial parsing trees. Empirically our 17-layer DPN can outperform both CapsNets and STNs significantly on affNIST \cite{sabour2017dynamic}, for instance, by 19.19% and 12.75%, respectively, with better generalization and better tolerance to affine transformations. |
| Tasks | Object Recognition |
| Published | 2018-05-22 |
| URL | http://arxiv.org/abs/1805.08808v1 |
| http://arxiv.org/pdf/1805.08808v1.pdf | |
| PWC | https://paperswithcode.com/paper/deformable-part-networks |
| Repo | |
| Framework | |
Automated soft tissue lesion detection and segmentation in digital mammography using a u-net deep learning network
| Title | Automated soft tissue lesion detection and segmentation in digital mammography using a u-net deep learning network |
| Authors | Timothy de Moor, Alejandro Rodriguez-Ruiz, Albert Gubern Mérida, Ritse Mann, Jonas Teuwen |
| Abstract | Computer-aided detection or decision support systems aim to improve breast cancer screening programs by helping radiologists to evaluate digital mammography (DM) exams. Commonly such methods proceed in two steps: selection of candidate regions for malignancy, and later classification as either malignant or not. In this study, we present a candidate detection method based on deep learning to automatically detect and additionally segment soft tissue lesions in DM. A database of DM exams (mostly bilateral and two views) was collected from our institutional archive. In total, 7196 DM exams (28294 DM images) acquired with systems from three different vendors (General Electric, Siemens, Hologic) were collected, of which 2883 contained malignant lesions verified with histopathology. Data was randomly split on an exam level into training (50%), validation (10%) and testing (40%) of deep neural network with u-net architecture. The u-net classifies the image but also provides lesion segmentation. Free receiver operating characteristic (FROC) analysis was used to evaluate the model, on an image and on an exam level. On an image level, a maximum sensitivity of 0.94 at 7.93 false positives (FP) per image was achieved. Similarly, per exam a maximum sensitivity of 0.98 at 7.81 FP per image was achieved. In conclusion, the method could be used as a candidate selection model with high accuracy and with the additional information of lesion segmentation. |
| Tasks | Lesion Segmentation |
| Published | 2018-02-19 |
| URL | http://arxiv.org/abs/1802.06865v2 |
| http://arxiv.org/pdf/1802.06865v2.pdf | |
| PWC | https://paperswithcode.com/paper/automated-soft-tissue-lesion-detection-and |
| Repo | |
| Framework | |
On the Implicit Assumptions of GANs
| Title | On the Implicit Assumptions of GANs |
| Authors | Ke Li, Jitendra Malik |
| Abstract | Generative adversarial nets (GANs) have generated a lot of excitement. Despite their popularity, they exhibit a number of well-documented issues in practice, which apparently contradict theoretical guarantees. A number of enlightening papers have pointed out that these issues arise from unjustified assumptions that are commonly made, but the message seems to have been lost amid the optimism of recent years. We believe the identified problems deserve more attention, and highlight the implications on both the properties of GANs and the trajectory of research on probabilistic models. We recently proposed an alternative method that sidesteps these problems. |
| Tasks | |
| Published | 2018-11-29 |
| URL | http://arxiv.org/abs/1811.12402v1 |
| http://arxiv.org/pdf/1811.12402v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-implicit-assumptions-of-gans |
| Repo | |
| Framework | |
Coordination-driven learning in multi-agent problem spaces
| Title | Coordination-driven learning in multi-agent problem spaces |
| Authors | Sean L. Barton, Nicholas R. Waytowich, Derrik E. Asher |
| Abstract | We discuss the role of coordination as a direct learning objective in multi-agent reinforcement learning (MARL) domains. To this end, we present a novel means of quantifying coordination in multi-agent systems, and discuss the implications of using such a measure to optimize coordinated agent policies. This concept has important implications for adversary-aware RL, which we take to be a sub-domain of multi-agent learning. |
| Tasks | Multi-agent Reinforcement Learning |
| Published | 2018-09-13 |
| URL | http://arxiv.org/abs/1809.04918v1 |
| http://arxiv.org/pdf/1809.04918v1.pdf | |
| PWC | https://paperswithcode.com/paper/coordination-driven-learning-in-multi-agent |
| Repo | |
| Framework | |
