January 25, 2020

2924 words 14 mins read

Paper Group ANR 1744

Multi-View Matching Network for 6D Pose Estimation. DeepHealth: Deep Learning for Health Informatics. Building Change Detection for Remote Sensing Images Using a Dual Task Constrained Deep Siamese Convolutional Network Model. ACM-DE: Adaptive p-best Cauchy Mutation with linear failure threshold reduction for Differential Evolution in numerical opti …

Multi-View Matching Network for 6D Pose Estimation


Title	Multi-View Matching Network for 6D Pose Estimation
Authors	Daniel Mas Montserrat, Jianhang Chen, Qian Lin, Jan P. Allebach, Edward J. Delp
Abstract	Applications that interact with the real world such as augmented reality or robot manipulation require a good understanding of the location and pose of the surrounding objects. In this paper, we present a new approach to estimate the 6 Degree of Freedom (DoF) or 6D pose of objects from a single RGB image. Our approach can be paired with an object detection and segmentation method to estimate, refine and track the pose of the objects by matching the input image with rendered images.
Tasks	6D Pose Estimation, Object Detection, Pose Estimation
Published	2019-11-27
URL	https://arxiv.org/abs/1911.12330v1
PDF	https://arxiv.org/pdf/1911.12330v1.pdf
PWC	https://paperswithcode.com/paper/multi-view-matching-network-for-6d-pose
Repo
Framework

DeepHealth: Deep Learning for Health Informatics


Title	DeepHealth: Deep Learning for Health Informatics
Authors	Gloria Hyun-Jung Kwak, Pan Hui
Abstract	Machine learning and deep learning have provided us with an exploration of a whole new research era. As more data and better computational power become available, they have been implemented in various fields. The demand for artificial intelligence in the field of health informatics is also increasing and we can expect to see the potential benefits of artificial intelligence applications in healthcare. Deep learning can help clinicians diagnose disease, identify cancer sites, identify drug effects for each patient, understand the relationship between genotypes and phenotypes, explore new phenotypes, and predict infectious disease outbreaks with high accuracy. In contrast to traditional models, its approach does not require domain-specific data pre-process, and it is expected that it will ultimately change human life a lot in the future. Despite its notable advantages, there are some challenges on data (high dimensionality, heterogeneity, time dependency, sparsity, irregularity, lack of label) and model (reliability, interpretability, feasibility, security, scalability) for practical use. This article presents a comprehensive review of research applying deep learning in health informatics with a focus on the last five years in the fields of medical imaging, electronic health records, genomics, sensing, and online communication health, as well as challenges and promising directions for future research. We highlight ongoing popular approaches’ research and identify several challenges in building deep learning models.
Tasks
Published	2019-09-01
URL	https://arxiv.org/abs/1909.00384v1
PDF	https://arxiv.org/pdf/1909.00384v1.pdf
PWC	https://paperswithcode.com/paper/deephealth-deep-learning-for-health
Repo
Framework

Building Change Detection for Remote Sensing Images Using a Dual Task Constrained Deep Siamese Convolutional Network Model


Title	Building Change Detection for Remote Sensing Images Using a Dual Task Constrained Deep Siamese Convolutional Network Model
Authors	Yi Liu, Chao Pang, Zongqian Zhan, Xiaomeng Zhang, Xue Yang
Abstract	In recent years, building change detection methods have made great progress by introducing deep learning, but they still suffer from the problem of the extracted features not being discriminative enough, resulting in incomplete regions and irregular boundaries. To tackle this problem, we propose a dual task constrained deep Siamese convolutional network (DTCDSCN) model, which contains three sub-networks: a change detection network and two semantic segmentation networks. DTCDSCN can accomplish both change detection and semantic segmentation at the same time, which can help to learn more discriminative object-level features and obtain a complete change detection map. Furthermore, we introduce a dual attention module (DAM) to exploit the interdependencies between channels and spatial positions, which improves the feature representation. We also improve the focal loss function to suppress the sample imbalance problem. The experimental results obtained with the WHU building dataset show that the proposed method is effective for building change detection and achieves a state-of-the-art performance in terms of four metrics: precision, recall, F1-score, and intersection over union.
Tasks	Semantic Segmentation
Published	2019-09-17
URL	https://arxiv.org/abs/1909.07726v1
PDF	https://arxiv.org/pdf/1909.07726v1.pdf
PWC	https://paperswithcode.com/paper/building-change-detection-for-remote-sensing
Repo
Framework

ACM-DE: Adaptive p-best Cauchy Mutation with linear failure threshold reduction for Differential Evolution in numerical optimization


Title	ACM-DE: Adaptive p-best Cauchy Mutation with linear failure threshold reduction for Differential Evolution in numerical optimization
Authors	Tae Jong Choi, Julian Togelius, Yun-Gyung Cheong
Abstract	A new Cauchy mutation for improving the convergence of differential evolution (DE) is proposed in this paper. DE is an efficient evolutionary algorithm for optimizing multidimensional real-valued functions, which has been successfully applied to various real-world problems. To improve convergence a Cauchy mutation-based DE variant called modified DE was proposed, but it has serious limitations of 1) controlling the balance between exploration and exploitation; 2) adjusting the algorithm to a given problem; 3) having less reliable performance on multimodal problems. In this paper, we propose a new adaptive Cauchy mutation-based DE variant called ACM-DE (Adaptive Cauchy Mutation Differential Evolution), which removes all of these limitations. Specifically, two popular parameter controls are employed for the exploration and exploitation scheme and robust performance. Also, a less greedy approach is employed, which uses any of the top p% individuals in the phase of the Cauchy mutation. Experimental results on a set of 58 benchmark problems show that ACM-DE is capable of finding more accurate solutions than modified DE, especially for multimodal problems. In addition, we applied ACM to two state-of-the-art DE variants, and similar to the previous results, ACM based variants exhibit significantly improved performance.
Tasks
Published	2019-07-01
URL	https://arxiv.org/abs/1907.01095v2
PDF	https://arxiv.org/pdf/1907.01095v2.pdf
PWC	https://paperswithcode.com/paper/acm-de-adaptive-p-best-cauchy-mutation-with
Repo
Framework

Shallow Self-Learning for Reject Inference in Credit Scoring


Title	Shallow Self-Learning for Reject Inference in Credit Scoring
Authors	Nikita Kozodoi, Panagiotis Katsas, Stefan Lessmann, Luis Moreira-Matias, Konstantinos Papakonstantinou
Abstract	Credit scoring models support loan approval decisions in the financial services industry. Lenders train these models on data from previously granted credit applications, where the borrowers’ repayment behavior has been observed. This approach creates sample bias. The scoring model (i.e., classifier) is trained on accepted cases only. Applying the resulting model to screen credit applications from the population of all borrowers degrades model performance. Reject inference comprises techniques to overcome sampling bias through assigning labels to rejected cases. The paper makes two contributions. First, we propose a self-learning framework for reject inference. The framework is geared toward real-world credit scoring requirements through considering distinct training regimes for iterative labeling and model training. Second, we introduce a new measure to assess the effectiveness of reject inference strategies. Our measure leverages domain knowledge to avoid artificial labeling of rejected cases during strategy evaluation. We demonstrate this approach to offer a robust and operational assessment of reject inference strategies. Experiments on a real-world credit scoring data set confirm the superiority of the adjusted self-learning framework over regular self-learning and previous reject inference strategies. We also find strong evidence in favor of the proposed evaluation measure assessing reject inference strategies more reliably, raising the performance of the eventual credit scoring model.
Tasks
Published	2019-09-13
URL	https://arxiv.org/abs/1909.06108v1
PDF	https://arxiv.org/pdf/1909.06108v1.pdf
PWC	https://paperswithcode.com/paper/shallow-self-learning-for-reject-inference-in
Repo
Framework

Geometric Matrix Completion with Deep Conditional Random Fields


Title	Geometric Matrix Completion with Deep Conditional Random Fields
Authors	Duc Minh Nguyen, Robert Calderbank, Nikos Deligiannis
Abstract	The problem of completing high-dimensional matrices from a limited set of observations arises in many big data applications, especially, recommender systems. Existing matrix completion models generally follow either a memory- or a model-based approach, whereas, geometric matrix completion models combine the best from both approaches. Existing deep-learning-based geometric models yield good performance, but, in order to operate, they require a fixed structure graph capturing the relationships among the users and items. This graph is typically constructed by evaluating a pre-defined similarity metric on the available observations or by using side information, e.g., user profiles. In contrast, Markov-random-fields-based models do not require a fixed structure graph but rely on handcrafted features to make predictions. When no side information is available and the number of available observations becomes very low, existing solutions are pushed to their limits. In this paper, we propose a geometric matrix completion approach that addresses these challenges. We consider matrix completion as a structured prediction problem in a conditional random field (CRF), which is characterized by a maximum a posterior (MAP) inference, and we propose a deep model that predicts the missing entries by solving the MAP inference problem. The proposed model simultaneously learns the similarities among matrix entries, computes the CRF potentials, and solves the inference problem. Its training is performed in an end-to-end manner, with a method to supervise the learning of entry similarities. Comprehensive experiments demonstrate the superior performance of the proposed model compared to various state-of-the-art models on popular benchmark datasets and underline its superior capacity to deal with highly incomplete matrices.
Tasks	Matrix Completion, Recommendation Systems, Structured Prediction
Published	2019-01-29
URL	https://arxiv.org/abs/1901.10429v2
PDF	https://arxiv.org/pdf/1901.10429v2.pdf
PWC	https://paperswithcode.com/paper/geometric-matrix-completion-with-deep
Repo
Framework

Theory of Optimal Bayesian Feature Filtering


Title	Theory of Optimal Bayesian Feature Filtering
Authors	Ali Foroughi pour, Lori A. Dalton
Abstract	Optimal Bayesian feature filtering (OBF) is a supervised screening method designed for biomarker discovery. In this article, we prove two major theoretical properties of OBF. First, optimal Bayesian feature selection under a general family of Bayesian models reduces to filtering if and only if the underlying Bayesian model assumes all features are mutually independent. Therefore, OBF is optimal if and only if one assumes all features are mutually independent, and OBF is the only filter method that is optimal under at least one model in the general Bayesian framework. Second, OBF under independent Gaussian models is consistent under very mild conditions, including cases where the data is non-Gaussian with correlated features. This result provides conditions where OBF is guaranteed to identify the correct feature set given enough data, and it justifies the use of OBF in non-design settings where its assumptions are invalid.
Tasks	Feature Selection
Published	2019-09-09
URL	https://arxiv.org/abs/1909.03637v1
PDF	https://arxiv.org/pdf/1909.03637v1.pdf
PWC	https://paperswithcode.com/paper/theory-of-optimal-bayesian-feature-filtering
Repo
Framework

Computing large market equilibria using abstractions


Title	Computing large market equilibria using abstractions
Authors	Christian Kroer, Alexander Peysakhovich, Eric Sodomka, Nicolas E. Stier-Moses
Abstract	Computing market equilibria is an important practical problem for market design (e.g. fair division, item allocation). However, computing equilibria requires large amounts of information (e.g. all valuations for all buyers for all items) and compute power. We consider ameliorating these issues by applying a method used for solving complex games: constructing a coarsened abstraction of a given market, solving for the equilibrium in the abstraction, and lifting the prices and allocations back to the original market. We show how to bound important quantities such as regret, envy, Nash social welfare, Pareto optimality, and maximin share when the abstracted prices and allocations are used in place of the real equilibrium. We then study two abstraction methods of interest for practitioners: 1) filling in unknown valuations using techniques from matrix completion, 2) reducing the problem size by aggregating groups of buyers/items into smaller numbers of representative buyers/items and solving for equilibrium in this coarsened market. We find that in real data allocations/prices that are relatively close to equilibria can be computed from even very coarse abstractions.
Tasks	Matrix Completion
Published	2019-01-18
URL	http://arxiv.org/abs/1901.06230v1
PDF	http://arxiv.org/pdf/1901.06230v1.pdf
PWC	https://paperswithcode.com/paper/computing-large-market-equilibria-using
Repo
Framework

Human Gist Processing Augments Deep Learning Breast Cancer Risk Assessment


Title	Human Gist Processing Augments Deep Learning Breast Cancer Risk Assessment
Authors	Skylar W. Wurster, Arkadiusz Sitek, Jian Chen, Karla Evans, Gaeun Kim, Jeremy M. Wolfe
Abstract	Radiologists can classify a mammogram as normal or abnormal at better than chance levels after less than a second’s exposure to the images. In this work, we combine these radiologists’ gist inputs into pre-trained machine learning models to validate that integrating gist with a CNN model can achieve an AUC (area under the curve) statistically significantly higher than either the gist perception of radiologists or the model without gist input.
Tasks
Published	2019-11-28
URL	https://arxiv.org/abs/1912.05470v1
PDF	https://arxiv.org/pdf/1912.05470v1.pdf
PWC	https://paperswithcode.com/paper/human-gist-processing-augments-deep-learning
Repo
Framework

Nonconvex Rectangular Matrix Completion via Gradient Descent without $\ell_{2,\infty}$ Regularization


Title	Nonconvex Rectangular Matrix Completion via Gradient Descent without $\ell_{2,\infty}$ Regularization
Authors	Ji Chen, Dekai Liu, Xiaodong Li
Abstract	The analysis of nonconvex matrix completion has recently attracted much attention in the community of machine learning thanks to its computational convenience. Existing analysis on this problem, however, usually relies on $\ell_{2,\infty}$ projection or regularization that involves unknown model parameters, although they are observed to be unnecessary in numerical simulations, see, e.g., Zheng and Lafferty [2016]. In this paper, we extend the analysis of the vanilla gradient descent for positive semidefinite matrix completion proposed in Ma et al. [2017] to the rectangular case, and more significantly, improve the required sampling rate from $O(\operatorname{poly}(\kappa)\mu^3 r^3 \log^3 n/n )$ to $O(\mu^2 r^2 \kappa^{14} \log n/n )$. Our technical ideas and contributions are potentially useful in improving the leave-one-out analysis in other related problems.
Tasks	Matrix Completion
Published	2019-01-18
URL	http://arxiv.org/abs/1901.06116v2
PDF	http://arxiv.org/pdf/1901.06116v2.pdf
PWC	https://paperswithcode.com/paper/nonconvex-rectangular-matrix-completion-via
Repo
Framework

Collaborative Multi-agent Learning for MR Knee Articular Cartilage Segmentation


Title	Collaborative Multi-agent Learning for MR Knee Articular Cartilage Segmentation
Authors	Chaowei Tan, Zhennan Yan, Shaoting Zhang, Kang Li, Dimitris N. Metaxas
Abstract	The 3D morphology and quantitative assessment of knee articular cartilages (i.e., femoral, tibial, and patellar cartilage) in magnetic resonance (MR) imaging is of great importance for knee radiographic osteoarthritis (OA) diagnostic decision making. However, effective and efficient delineation of all the knee articular cartilages in large-sized and high-resolution 3D MR knee data is still an open challenge. In this paper, we propose a novel framework to solve the MR knee cartilage segmentation task. The key contribution is the adversarial learning based collaborative multi-agent segmentation network. In the proposed network, we use three parallel segmentation agents to label cartilages in their respective region of interest (ROI), and then fuse the three cartilages by a novel ROI-fusion layer. The collaborative learning is driven by an adversarial sub-network. The ROI-fusion layer not only fuses the individual cartilages from multiple agents, but also backpropagates the training loss from the adversarial sub-network to each agent to enable joint learning of shape and spatial constraints. Extensive evaluations are conducted on a dataset including hundreds of MR knee volumes with diverse populations, and the proposed method shows superior performance.
Tasks	Decision Making
Published	2019-08-13
URL	https://arxiv.org/abs/1908.04469v1
PDF	https://arxiv.org/pdf/1908.04469v1.pdf
PWC	https://paperswithcode.com/paper/collaborative-multi-agent-learning-for-mr
Repo
Framework

To Follow or not to Follow: Selective Imitation Learning from Observations


Title	To Follow or not to Follow: Selective Imitation Learning from Observations
Authors	Youngwoon Lee, Edward S. Hu, Zhengyu Yang, Joseph J. Lim
Abstract	Learning from demonstrations is a useful way to transfer a skill from one agent to another. While most imitation learning methods aim to mimic an expert skill by following the demonstration step-by-step, imitating every step in the demonstration often becomes infeasible when the learner and its environment are different from the demonstration. In this paper, we propose a method that can imitate a demonstration composed solely of observations, which may not be reproducible with the current agent. Our method, dubbed selective imitation learning from observations (SILO), selects reachable states in the demonstration and learns how to reach the selected states. Our experiments on both simulated and real robot environments show that our method reliably performs a new task by following a demonstration. Videos and code are available at https://clvrai.com/silo .
Tasks	Imitation Learning
Published	2019-12-16
URL	https://arxiv.org/abs/1912.07670v1
PDF	https://arxiv.org/pdf/1912.07670v1.pdf
PWC	https://paperswithcode.com/paper/to-follow-or-not-to-follow-selective
Repo
Framework

Machine-learning a virus assembly fitness landscape


Title	Machine-learning a virus assembly fitness landscape
Authors	Pierre-Philippe Dechant, Yang-Hui He
Abstract	Realistic evolutionary fitness landscapes are notoriously difficult to construct. A recent cutting-edge model of virus assembly consists of a dodecahedral capsid with $12$ corresponding packaging signals in three affinity bands. This whole genome/phenotype space consisting of $3^{12}$ genomes has been explored via computationally expensive stochastic assembly models, giving a fitness landscape in terms of the assembly efficiency. Using latest machine-learning techniques by establishing a neural network, we show that the intensive computation can be short-circuited in a matter of minutes to astounding accuracy.
Tasks
Published	2019-01-13
URL	http://arxiv.org/abs/1901.05051v1
PDF	http://arxiv.org/pdf/1901.05051v1.pdf
PWC	https://paperswithcode.com/paper/machine-learning-a-virus-assembly-fitness
Repo
Framework

Designing a Multi-Objective Reward Function for Creating Teams of Robotic Bodyguards Using Deep Reinforcement Learning


Title	Designing a Multi-Objective Reward Function for Creating Teams of Robotic Bodyguards Using Deep Reinforcement Learning
Authors	Hassam Ullah Sheikh, Ladislau Bölöni
Abstract	We are considering a scenario where a team of bodyguard robots provides physical protection to a VIP in a crowded public space. We use deep reinforcement learning to learn the policy to be followed by the robots. As the robot bodyguards need to follow several difficult-to-reconcile goals, we study several primitive and composite reward functions and their impact on the overall behavior of the robotic bodyguards.
Tasks
Published	2019-01-28
URL	http://arxiv.org/abs/1901.09837v1
PDF	http://arxiv.org/pdf/1901.09837v1.pdf
PWC	https://paperswithcode.com/paper/designing-a-multi-objective-reward-function
Repo
Framework

6-DOF Grasping for Target-driven Object Manipulation in Clutter


Title	6-DOF Grasping for Target-driven Object Manipulation in Clutter
Authors	Adithyavairavan Murali, Arsalan Mousavian, Clemens Eppner, Chris Paxton, Dieter Fox
Abstract	Grasping in cluttered environments is a fundamental but challenging robotic skill. It requires both reasoning about unseen object parts and potential collisions with the manipulator. Most existing data-driven approaches avoid this problem by limiting themselves to top-down planar grasps which is insufficient for many real-world scenarios and greatly limits possible grasps. We present a method that plans 6-DOF grasps for any desired object in a cluttered scene from partial point cloud observations. Our method achieves a grasp success of 80.3%, outperforming baseline approaches by 17.6% and clearing 9 cluttered table scenes (which contain 23 unknown objects and 51 picks in total) on a real robotic platform. By using our learned collision checking module, we can even reason about effective grasp sequences to retrieve objects that are not immediately accessible. Supplementary video can be found at https://youtu.be/w0B5S-gCsJk.
Tasks
Published	2019-12-08
URL	https://arxiv.org/abs/1912.03628v1
PDF	https://arxiv.org/pdf/1912.03628v1.pdf
PWC	https://paperswithcode.com/paper/6-dof-grasping-for-target-driven-object
Repo
Framework