Paper Group ANR 1491
Character Keypoint-based Homography Estimation in Scanned Documents for Efficient Information Extraction. Inferring Occluded Geometry Improves Performance when Retrieving an Object from Dense Clutter. No Spurious Local Minima in Deep Quadratic Networks. An Image Fusion Scheme for Single-Shot High Dynamic Range Imaging with Spatially Varying Exposur …
Character Keypoint-based Homography Estimation in Scanned Documents for Efficient Information Extraction
| Title | Character Keypoint-based Homography Estimation in Scanned Documents for Efficient Information Extraction |
| Authors | Kushagra Mahajan, Monika Sharma, Lovekesh Vig |
| Abstract | Precise homography estimation between multiple images is a pre-requisite for many computer vision applications. One application that is particularly relevant in today’s digital era is the alignment of scanned or camera-captured document images such as insurance claim forms for information extraction. Traditional learning based approaches perform poorly due to the absence of an appropriate gradient. Feature based keypoint extraction techniques for homography estimation in real scene images either detect an extremely large number of inconsistent keypoints due to sharp textual edges, or produce inaccurate keypoint correspondences due to variations in illumination and viewpoint differences between document images. In this paper, we propose a novel algorithm for aligning scanned or camera-captured document images using character based keypoints and a reference template. The algorithm is both fast and accurate and utilizes a standard Optical character recognition (OCR) engine such as Tesseract to find character based unambiguous keypoints, which are utilized to identify precise keypoint correspondences between two images. Finally, the keypoints are used to compute the homography mapping between a test document and a template. We evaluated the proposed approach for information extraction on two real world anonymized datasets comprised of health insurance claim forms and the results support the viability of the proposed technique. |
| Tasks | Homography Estimation, Optical Character Recognition |
| Published | 2019-11-14 |
| URL | https://arxiv.org/abs/1911.05870v1 |
| https://arxiv.org/pdf/1911.05870v1.pdf | |
| PWC | https://paperswithcode.com/paper/character-keypoint-based-homography |
| Repo | |
| Framework | |
Inferring Occluded Geometry Improves Performance when Retrieving an Object from Dense Clutter
| Title | Inferring Occluded Geometry Improves Performance when Retrieving an Object from Dense Clutter |
| Authors | Andrew Price, Linyi Jin, Dmitry Berenson |
| Abstract | Object search – the problem of finding a target object in a cluttered scene – is essential to solve for many robotics applications in warehouse and household environments. However, cluttered environments entail that objects often occlude one another, making it difficult to segment objects and infer their shapes and properties. Instead of relying on the availability of CAD or other explicit models of scene objects, we augment a manipulation planner for cluttered environments with a state-of-the-art deep neural network for shape completion as well as a volumetric memory system, allowing the robot to reason about what may be contained in occluded areas. We test the system in a variety of tabletop manipulation scenes composed of household items, highlighting its applicability to realistic domains. Our results suggest that incorporating both components into a manipulation planning framework significantly reduces the number of actions needed to find a hidden object in dense clutter. |
| Tasks | |
| Published | 2019-07-20 |
| URL | https://arxiv.org/abs/1907.08770v2 |
| https://arxiv.org/pdf/1907.08770v2.pdf | |
| PWC | https://paperswithcode.com/paper/inferring-occluded-geometry-improves |
| Repo | |
| Framework | |
No Spurious Local Minima in Deep Quadratic Networks
| Title | No Spurious Local Minima in Deep Quadratic Networks |
| Authors | Abbas Kazemipour, Brett Larsen, Shaul Druckmann |
| Abstract | Despite their practical success, a theoretical understanding of the loss landscape of neural networks has proven challenging due to the high-dimensional, non-convex, and highly nonlinear structure of such models. In this paper, we characterize the training landscape of the quadratic loss landscape for neural networks with quadratic activation functions. We prove existence of spurious local minima and saddle points which can be escaped easily with probability one when the number of neurons is greater than or equal to the input dimension and the norm of the training samples is used as a regressor. We prove that deep overparameterized neural networks with quadratic activations benefit from similar nice landscape properties. Our theoretical results are independent of data distribution and fill the existing gap in theory for two-layer quadratic neural networks. Finally, we empirically demonstrate convergence to a global minimum for these problems. |
| Tasks | |
| Published | 2019-12-31 |
| URL | https://arxiv.org/abs/2001.00098v1 |
| https://arxiv.org/pdf/2001.00098v1.pdf | |
| PWC | https://paperswithcode.com/paper/no-spurious-local-minima-in-deep-quadratic |
| Repo | |
| Framework | |
An Image Fusion Scheme for Single-Shot High Dynamic Range Imaging with Spatially Varying Exposures
| Title | An Image Fusion Scheme for Single-Shot High Dynamic Range Imaging with Spatially Varying Exposures |
| Authors | Chihiro Go, Yuma Kinoshita, Sayaka Shiota, Hitoshi Kiya |
| Abstract | This paper proposes a novel multi-exposure image fusion (MEF) scheme for single-shot high dynamic range imaging with spatially varying exposures (SVE). Single-shot imaging with SVE enables us not only to produce images without color saturation regions from a single-shot image, but also to avoid ghost artifacts in the producing ones. However, the number of exposures is generally limited to two, and moreover it is difficult to decide the optimum exposure values before the photographing. In the proposed scheme, a scene segmentation method is applied to input multi-exposure images, and then the luminance of the input images is adjusted according to both of the number of scenes and the relationship between exposure values and pixel values. The proposed method with the luminance adjustment allows us to improve the above two issues. In this paper, we focus on dual-ISO imaging as one of single-shot imaging. In an experiment, the proposed scheme is demonstrated to be effective for single-shot high dynamic range imaging with SVE, compared with conventional MEF schemes with exposure compensation. |
| Tasks | Scene Segmentation |
| Published | 2019-08-22 |
| URL | https://arxiv.org/abs/1908.08195v1 |
| https://arxiv.org/pdf/1908.08195v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-image-fusion-scheme-for-single-shot-high |
| Repo | |
| Framework | |
Training Optimus Prime, M.D.: Generating Medical Certification Items by Fine-Tuning OpenAI’s gpt2 Transformer Model
| Title | Training Optimus Prime, M.D.: Generating Medical Certification Items by Fine-Tuning OpenAI’s gpt2 Transformer Model |
| Authors | Matthias von Davier |
| Abstract | This article describes new results of an application using transformer-based language models to automated item generation (AIG), an area of ongoing interest in the domain of certification testing as well as in educational measurement and psychological testing. OpenAI’s gpt2 pre-trained 345M parameter language model was retrained using the public domain text mining set of PubMed articles and subsequently used to generate item stems (case vignettes) as well as distractor proposals for multiple-choice items. This case study shows promise and produces draft text that can be used by human item writers as input for authoring. Future experiments with more recent transformer models (such as Grover, TransformerXL) using existing item pools are expected to improve results further and to facilitate the development of assessment materials. |
| Tasks | Language Modelling |
| Published | 2019-08-23 |
| URL | https://arxiv.org/abs/1908.08594v3 |
| https://arxiv.org/pdf/1908.08594v3.pdf | |
| PWC | https://paperswithcode.com/paper/training-optimus-prime-md-generating-medical |
| Repo | |
| Framework | |
Online Active Perception for Partially Observable Markov Decision Processes with Limited Budget
| Title | Online Active Perception for Partially Observable Markov Decision Processes with Limited Budget |
| Authors | Mahsa Ghasemi, Ufuk Topcu |
| Abstract | Active perception strategies enable an agent to selectively gather information in a way to improve its performance. In applications in which the agent does not have prior knowledge about the available information sources, it is crucial to synthesize active perception strategies at runtime. We consider a setting in which at runtime an agent is capable of gathering information under a limited budget. We pose the problem in the context of partially observable Markov decision processes. We propose a generalized greedy strategy that selects a subset of information sources with near-optimality guarantees on uncertainty reduction. Our theoretical analysis establishes that the proposed active perception strategy achieves near-optimal performance in terms of expected cumulative reward. We demonstrate the resulting strategies in simulations on a robotic navigation problem. |
| Tasks | |
| Published | 2019-10-04 |
| URL | https://arxiv.org/abs/1910.02130v1 |
| https://arxiv.org/pdf/1910.02130v1.pdf | |
| PWC | https://paperswithcode.com/paper/online-active-perception-for-partially |
| Repo | |
| Framework | |
BAYHENN: Combining Bayesian Deep Learning and Homomorphic Encryption for Secure DNN Inference
| Title | BAYHENN: Combining Bayesian Deep Learning and Homomorphic Encryption for Secure DNN Inference |
| Authors | Peichen Xie, Bingzhe Wu, Guangyu Sun |
| Abstract | Recently, deep learning as a service (DLaaS) has emerged as a promising way to facilitate the employment of deep neural networks (DNNs) for various purposes. However, using DLaaS also causes potential privacy leakage from both clients and cloud servers. This privacy issue has fueled the research interests on the privacy-preserving inference of DNN models in the cloud service. In this paper, we present a practical solution named BAYHENN for secure DNN inference. It can protect both the client’s privacy and server’s privacy at the same time. The key strategy of our solution is to combine homomorphic encryption and Bayesian neural networks. Specifically, we use homomorphic encryption to protect a client’s raw data and use Bayesian neural networks to protect the DNN weights in a cloud server. To verify the effectiveness of our solution, we conduct experiments on MNIST and a real-life clinical dataset. Our solution achieves consistent latency decreases on both tasks. In particular, our method can outperform the best existing method (GAZELLE) by about 5x, in terms of end-to-end latency. |
| Tasks | |
| Published | 2019-06-03 |
| URL | https://arxiv.org/abs/1906.00639v2 |
| https://arxiv.org/pdf/1906.00639v2.pdf | |
| PWC | https://paperswithcode.com/paper/190600639 |
| Repo | |
| Framework | |
Counterfactual Cross-Validation: Stable Model Selection Procedure for Causal Inference Models
| Title | Counterfactual Cross-Validation: Stable Model Selection Procedure for Causal Inference Models |
| Authors | Yuta Saito, Shota Yasui |
| Abstract | What is the most effective way to select the best causal model among potential candidates? In this paper, we propose a method to effectively select the best conditional average treatment effect (CATE) predictors from a set of candidates using only an observational validation set. When conducting a model selection or tuning hyperparameters, we are interested in choosing the best model or hyperparameter value. Thus, we focus on accurately preserving the rank order of the CATE prediction performance of causal model candidates. For this purpose, we propose a new model selection procedure that preserves the true ranking of the model performance and minimizes the upper bound of the finite sample uncertainty in model selection. Consistent with the theoretical properties, empirical evaluations demonstrate that our proposed method is more likely to select the best model and set of hyperparameters for both model selection and hyperparameter tuning tasks. |
| Tasks | Causal Inference, Model Selection |
| Published | 2019-09-11 |
| URL | https://arxiv.org/abs/1909.05299v3 |
| https://arxiv.org/pdf/1909.05299v3.pdf | |
| PWC | https://paperswithcode.com/paper/counterfactual-cross-validation-effective |
| Repo | |
| Framework | |
Bayesian-Deep-Learning Estimation of Earthquake Location from Single-Station Observations
| Title | Bayesian-Deep-Learning Estimation of Earthquake Location from Single-Station Observations |
| Authors | S. Mostafa Mousavi, Gregory C. Beroza |
| Abstract | We present a deep learning method for single-station earthquake location, which we approach as a regression problem using two separate Bayesian neural networks. We use a multi-task temporal-convolutional neural network to learn epicentral distance and P travel time from 1-minute seismograms. The network estimates epicentral distance and P travel time with absolute mean errors of 0.23 km and 0.03 s respectively, along with their epistemic and aleatory uncertainties. We design a separate multi-input network using standard convolutional layers to estimate the back-azimuth angle, and its epistemic uncertainty. This network estimates the direction from which seismic waves arrive to the station with a mean error of 1 degree. Using this information, we estimate the epicenter, origin time, and depth along with their confidence intervals. We use a global dataset of earthquake signals recorded within 1 degree (~112 km) from the event to build the model and to demonstrate its performance. Our model can predict epicenter, origin time, and depth with mean errors of 7.3 km, 0.4 second, and 6.7 km respectively, at different locations around the world. Our approach can be used for fast earthquake source characterization with a limited number of observations, and also for estimating location of earthquakes that are sparsely recorded – either because they are small or because stations are widely separated. |
| Tasks | |
| Published | 2019-12-03 |
| URL | https://arxiv.org/abs/1912.01144v1 |
| https://arxiv.org/pdf/1912.01144v1.pdf | |
| PWC | https://paperswithcode.com/paper/bayesian-deep-learning-estimation-of |
| Repo | |
| Framework | |
Plotting Markson’s ‘Mistress’
| Title | Plotting Markson’s ‘Mistress’ |
| Authors | Kelleher Conor, Mark T. Keane |
| Abstract | The post-modern novel ‘Wittgenstein’s Mistress’ by David Markson (1988) presents the reader with a very challenging non linear narrative, that itself appears to one of the novel’s themes. We present a distant reading of this work designed to complement a close reading of it by David Foster Wallace (1990). Using a combination of text analysis, entity recognition and networks, we plot repetitive structures in the novel’s narrative relating them to its critical analysis. |
| Tasks | |
| Published | 2019-05-17 |
| URL | https://arxiv.org/abs/1905.07185v1 |
| https://arxiv.org/pdf/1905.07185v1.pdf | |
| PWC | https://paperswithcode.com/paper/plotting-marksons-mistress-1 |
| Repo | |
| Framework | |
Small-world networks for summarization of biomedical articles
| Title | Small-world networks for summarization of biomedical articles |
| Authors | Milad Moradi |
| Abstract | In recent years, many methods have been developed to identify important portions of text documents. Summarization tools can utilize these methods to extract summaries from large volumes of textual information. However, to identify concepts representing central ideas within a text document and to extract the most informative sentences that best convey those concepts still remain two crucial tasks in summarization methods. In this paper, we introduce a graph-based method to address these two challenges in the context of biomedical text summarization. We show that how a summarizer can discover meaningful concepts within a biomedical text document using the Helmholtz principle. The summarizer considers the meaningful concepts as the main topics and constructs a graph based on the topics that the sentences share. The summarizer can produce an informative summary by extracting those sentences having higher values of the degree. We assess the performance of our method for summarization of biomedical articles using the Recall-Oriented Understudy for Gisting Evaluation (ROUGE) toolkit. The results show that the degree can be a useful centrality measure to identify important sentences in this type of graph-based modelling. Our method can improve the performance of biomedical text summarization compared to some state-of-the-art and publicly available summarizers. Combining a concept-based modelling strategy and a graph-based approach to sentence extraction, our summarizer can produce summaries with the highest scores of informativeness among the comparison methods. This research work can be regarded as a start point to the study of small-world networks in summarization of biomedical texts. |
| Tasks | Text Summarization |
| Published | 2019-03-07 |
| URL | http://arxiv.org/abs/1903.02861v1 |
| http://arxiv.org/pdf/1903.02861v1.pdf | |
| PWC | https://paperswithcode.com/paper/small-world-networks-for-summarization-of |
| Repo | |
| Framework | |
PyRobot: An Open-source Robotics Framework for Research and Benchmarking
| Title | PyRobot: An Open-source Robotics Framework for Research and Benchmarking |
| Authors | Adithyavairavan Murali, Tao Chen, Kalyan Vasudev Alwala, Dhiraj Gandhi, Lerrel Pinto, Saurabh Gupta, Abhinav Gupta |
| Abstract | This paper introduces PyRobot, an open-source robotics framework for research and benchmarking. PyRobot is a light-weight, high-level interface on top of ROS that provides a consistent set of hardware independent mid-level APIs to control different robots. PyRobot abstracts away details about low-level controllers and inter-process communication, and allows non-robotics researchers (ML, CV researchers) to focus on building high-level AI applications. PyRobot aims to provide a research ecosystem with convenient access to robotics datasets, algorithm implementations and models that can be used to quickly create a state-of-the-art baseline. We believe PyRobot, when paired up with low-cost robot platforms such as LoCoBot, will reduce the entry barrier into robotics, and democratize robotics. PyRobot is open-source, and can be accessed via https://pyrobot.org. |
| Tasks | |
| Published | 2019-06-19 |
| URL | https://arxiv.org/abs/1906.08236v1 |
| https://arxiv.org/pdf/1906.08236v1.pdf | |
| PWC | https://paperswithcode.com/paper/pyrobot-an-open-source-robotics-framework-for |
| Repo | |
| Framework | |
Cooperative Online Learning: Keeping your Neighbors Updated
| Title | Cooperative Online Learning: Keeping your Neighbors Updated |
| Authors | Nicolò Cesa-Bianchi, Tommaso R. Cesari, Claire Monteleoni |
| Abstract | We study an asynchronous online learning setting with a network of agents. At each time step, some of the agents are activated, requested to make a prediction, and pay the corresponding loss. The loss function is then revealed to these agents and also to their neighbors in the network. Our results characterize how much knowing the network structure affects the regret as a function of the model of agent activations. When activations are stochastic, the optimal regret (up to constant factors) is shown to be of order $\sqrt{\alpha T}$, where $T$ is the horizon and $\alpha$ is the independence number of the network. We prove that the upper bound is achieved even when agents have no information about the network structure. When activations are adversarial the situation changes dramatically: if agents ignore the network structure, a $\Omega(T)$ lower bound on the regret can be proven, showing that learning is impossible. However, when agents can choose to ignore some of their neighbors based on the knowledge of the network structure, we prove a $O(\sqrt{\overline{\chi} T})$ sublinear regret bound, where $\overline{\chi} \ge \alpha$ is the clique-covering number of the network. |
| Tasks | |
| Published | 2019-01-23 |
| URL | https://arxiv.org/abs/1901.08082v4 |
| https://arxiv.org/pdf/1901.08082v4.pdf | |
| PWC | https://paperswithcode.com/paper/cooperative-online-learning-keeping-your |
| Repo | |
| Framework | |
Learning Hierarchical Representations of Electronic Health Records for Clinical Outcome Prediction
| Title | Learning Hierarchical Representations of Electronic Health Records for Clinical Outcome Prediction |
| Authors | Luchen Liu, Haoran Li, Zhiting Hu, Haoran Shi, Zichang Wang, Jian Tang, Ming Zhang |
| Abstract | Clinical outcome prediction based on the Electronic Health Record (EHR) plays a crucial role in improving the quality of healthcare. Conventional deep sequential models fail to capture the rich temporal patterns encoded in the longand irregular clinical event sequences. We make the observation that clinical events at a long time scale exhibit strongtemporal patterns, while events within a short time period tend to be disordered co-occurrence. We thus propose differentiated mechanisms to model clinical events at different time scales. Our model learns hierarchical representationsof event sequences, to adaptively distinguish between short-range and long-range events, and accurately capture coretemporal dependencies. Experimental results on real clinical data show that our model greatly improves over previous state-of-the-art models, achieving AUC scores of 0.94 and 0.90 for predicting death and ICU admission respectively, Our model also successfully identifies important events for different clinical outcome prediction tasks |
| Tasks | |
| Published | 2019-03-20 |
| URL | https://arxiv.org/abs/1903.08652v2 |
| https://arxiv.org/pdf/1903.08652v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-hierarchical-representations-of |
| Repo | |
| Framework | |
Uncertainty-Aware Data Aggregation for Deep Imitation Learning
| Title | Uncertainty-Aware Data Aggregation for Deep Imitation Learning |
| Authors | Yuchen Cui, David Isele, Scott Niekum, Kikuo Fujimura |
| Abstract | Estimating statistical uncertainties allows autonomous agents to communicate their confidence during task execution and is important for applications in safety-critical domains such as autonomous driving. In this work, we present the uncertainty-aware imitation learning (UAIL) algorithm for improving end-to-end control systems via data aggregation. UAIL applies Monte Carlo Dropout to estimate uncertainty in the control output of end-to-end systems, using states where it is uncertain to selectively acquire new training data. In contrast to prior data aggregation algorithms that force human experts to visit sub-optimal states at random, UAIL can anticipate its own mistakes and switch control to the expert in order to prevent visiting a series of sub-optimal states. Our experimental results from simulated driving tasks demonstrate that our proposed uncertainty estimation method can be leveraged to reliably predict infractions. Our analysis shows that UAIL outperforms existing data aggregation algorithms on a series of benchmark tasks. |
| Tasks | Autonomous Driving, Imitation Learning |
| Published | 2019-05-07 |
| URL | https://arxiv.org/abs/1905.02780v1 |
| https://arxiv.org/pdf/1905.02780v1.pdf | |
| PWC | https://paperswithcode.com/paper/uncertainty-aware-data-aggregation-for-deep |
| Repo | |
| Framework | |
