April 2, 2020

3264 words 16 mins read

Paper Group ANR 277

Paper Group ANR 277

Joint Unsupervised Learning for the Vertebra Segmentation, Artifact Reduction and Modality Translation of CBCT Images. Dynamic Radar Network of UAVs: A Joint Navigation and Tracking Approach. Mapping Motor Cortex Stimulation to Muscle Responses: A Deep Neural Network Modeling Approach. Top-K Training of GANs: Improving Generators by Making Critics …

Joint Unsupervised Learning for the Vertebra Segmentation, Artifact Reduction and Modality Translation of CBCT Images

Title Joint Unsupervised Learning for the Vertebra Segmentation, Artifact Reduction and Modality Translation of CBCT Images
Authors Yuanyuan Lyu, Haofu Liao, Heqin Zhu, S. Kevin Zhou
Abstract We investigate the unsupervised learning of the vertebra segmentation, artifact reduction and modality translation of CBCT images. To this end, we formulate this problem under a unified framework that jointly addresses these three tasks and intensively leverages the knowledge sharing. The unsupervised learning of this framework is enabled by 1) a novel shape-aware artifact disentanglement network that supports different forms of image synthesis and vertebra segmentation and 2) a deliberate fusion of knowledge from an independent CT dataset. Specifically, the proposed framework takes a random pair of CBCT and CT images as the input, and manipulates the synthesis and segmentation via different combinations of the decodings of the disentangled latent codes. Then, by discovering various forms of consistencies between the synthesized images and segmented , the learning is achieved via self-learning from the given CBCT and CT images obviating the need for the paired (i.e., anatomically identical) groundtruth data. Extensive experiments on clinical CBCT and CT datasets show that the proposed approach performs significantly better than other state-of-the-art unsupervised methods trained independently for each task and, remarkably, the proposed approach achieves a dice coefficient of 0.879 for unsupervised CBCT vertebra segmentation.
Tasks Image Generation
Published 2020-01-02
URL https://arxiv.org/abs/2001.00339v2
PDF https://arxiv.org/pdf/2001.00339v2.pdf
PWC https://paperswithcode.com/paper/joint-unsupervised-learning-for-the-vertebra
Repo
Framework

Dynamic Radar Network of UAVs: A Joint Navigation and Tracking Approach

Title Dynamic Radar Network of UAVs: A Joint Navigation and Tracking Approach
Authors Anna Guerra, Davide Dardari, Petar M. Djuric
Abstract Nowadays there is a growing research interest on the possibility of enriching small flying robots with autonomous sensing and online navigation capabilities. This will enable a large number of applications spanning from remote surveillance to logistics, smarter cities and emergency aid in hazardous environments. In this context, an emerging problem is to track unauthorized small unmanned aerial vehicles (UAVs) hiding behind buildings or concealing in large UAV networks. In contrast with current solutions mainly based on static and on-ground radars, this paper proposes the idea of a dynamic radar network of UAVs for real-time and high-accuracy tracking of malicious targets. To this end, we describe a solution for real-time navigation of UAVs to track a dynamic target using heterogeneously sensed information. Such information is shared by the UAVs with their neighbors via multi-hops, allowing tracking the target by a local Bayesian estimator running at each agent. Since not all the paths are equal in terms of information gathering point-of-view, the UAVs plan their own trajectory by minimizing the posterior covariance matrix of the target state under UAV kinematic and anti-collision constraints. Our results show how a dynamic network of radars attains better localization results compared to a fixed configuration and how the on-board sensor technology impacts the accuracy in tracking a target with different radar cross sections, especially in non line-of-sight (NLOS) situations.
Tasks
Published 2020-01-13
URL https://arxiv.org/abs/2001.04560v1
PDF https://arxiv.org/pdf/2001.04560v1.pdf
PWC https://paperswithcode.com/paper/dynamic-radar-network-of-uavs-a-joint
Repo
Framework

Mapping Motor Cortex Stimulation to Muscle Responses: A Deep Neural Network Modeling Approach

Title Mapping Motor Cortex Stimulation to Muscle Responses: A Deep Neural Network Modeling Approach
Authors Md Navid Akbar, Mathew Yarossi, Marc Martinez-Gost, Marc A. Sommer, Moritz Dannhauer, Sumientra Rampersad, Dana Brooks, Eugene Tunik, Deniz Erdoğmuş
Abstract A deep neural network (DNN) that can reliably model muscle responses from corresponding brain stimulation has the potential to increase knowledge of coordinated motor control for numerous basic science and applied use cases. Such cases include the understanding of abnormal movement patterns due to neurological injury from stroke, and stimulation based interventions for neurological recovery such as paired associative stimulation. In this work, potential DNN models are explored and the one with the minimum squared errors is recommended for the optimal performance of the M2M-Net, a network that maps transcranial magnetic stimulation of the motor cortex to corresponding muscle responses, using: a finite element simulation, an empirical neural response profile, a convolutional autoencoder, a separate deep network mapper, and recordings of multi-muscle activation. We discuss the rationale behind the different modeling approaches and architectures, and contrast their results. Additionally, to obtain a comparative insight of the trade-off between complexity and performance analysis, we explore different techniques, including the extension of two classical information criteria for M2M-Net. Finally, we find that the model analogous to mapping the motor cortex stimulation to a combination of direct and synergistic connection to the muscles performs the best, when the neural response profile is used at the input.
Tasks
Published 2020-02-14
URL https://arxiv.org/abs/2002.06250v1
PDF https://arxiv.org/pdf/2002.06250v1.pdf
PWC https://paperswithcode.com/paper/mapping-motor-cortex-stimulation-to-muscle
Repo
Framework

Top-K Training of GANs: Improving Generators by Making Critics Less Critical

Title Top-K Training of GANs: Improving Generators by Making Critics Less Critical
Authors Samarth Sinha, Anirudh Goyal, Colin Raffel, Augustus Odena
Abstract We introduce a simple (one line of code) modification to the Generative Adversarial Network (GAN) training algorithm that materially improves results with no increase in computational cost: When updating the generator parameters, we simply zero out the gradient contributions from the elements of the batch that the critic scores as least realistic'. Through experiments on many different GAN variants, we show that this top-k update’ procedure is a generally applicable improvement. In order to understand the nature of the improvement, we conduct extensive analysis on a simple mixture-of-Gaussians dataset and discover several interesting phenomena. Among these is that, when gradient updates are computed using the worst-scoring batch elements, samples can actually be pushed further away from the their nearest mode.
Tasks
Published 2020-02-14
URL https://arxiv.org/abs/2002.06224v1
PDF https://arxiv.org/pdf/2002.06224v1.pdf
PWC https://paperswithcode.com/paper/top-k-training-of-gans-improving-generators
Repo
Framework

Developing Multi-Task Recommendations with Long-Term Rewards via Policy Distilled Reinforcement Learning

Title Developing Multi-Task Recommendations with Long-Term Rewards via Policy Distilled Reinforcement Learning
Authors Xi Liu, Li Li, Ping-Chun Hsieh, Muhe Xie, Yong Ge, Rui Chen
Abstract With the explosive growth of online products and content, recommendation techniques have been considered as an effective tool to overcome information overload, improve user experience, and boost business revenue. In recent years, we have observed a new desideratum of considering long-term rewards of multiple related recommendation tasks simultaneously. The consideration of long-term rewards is strongly tied to business revenue and growth. Learning multiple tasks simultaneously could generally improve the performance of individual task due to knowledge sharing in multi-task learning. While a few existing works have studied long-term rewards in recommendations, they mainly focus on a single recommendation task. In this paper, we propose {\it PoDiRe}: a \underline{po}licy \underline{di}stilled \underline{re}commender that can address long-term rewards of recommendations and simultaneously handle multiple recommendation tasks. This novel recommendation solution is based on a marriage of deep reinforcement learning and knowledge distillation techniques, which is able to establish knowledge sharing among different tasks and reduce the size of a learning model. The resulting model is expected to attain better performance and lower response latency for real-time recommendation services. In collaboration with Samsung Game Launcher, one of the world’s largest commercial mobile game platforms, we conduct a comprehensive experimental study on large-scale real data with hundreds of millions of events and show that our solution outperforms many state-of-the-art methods in terms of several standard evaluation metrics.
Tasks Multi-Task Learning
Published 2020-01-27
URL https://arxiv.org/abs/2001.09595v1
PDF https://arxiv.org/pdf/2001.09595v1.pdf
PWC https://paperswithcode.com/paper/developing-multi-task-recommendations-with
Repo
Framework
Title Network Representation Learning for Link Prediction: Are we improving upon simple heuristics?
Authors Alexandru Mara, Jefrey Lijffijt, Tijl De Bie
Abstract Network representation learning has become an active research area in recent years with many new methods showcasing their performance on downstream prediction tasks such as Link Prediction. Despite the efforts of the community to ensure reproducibility of research by providing method implementations, important issues remain. The complexity of the evaluation pipelines and abundance of design choices have led to difficulties in quantifying the progress in the field and identifying the state-of-the-art. In this work, we analyse 17 network embedding methods on 7 real-world datasets and find, using a consistent evaluation pipeline, only thin progress over the recent years. Also, many embedding methods are outperformed by simple heuristics. Finally, we discuss how standardized evaluation tools can repair this situation and boost progress in this field.
Tasks Link Prediction, Network Embedding, Representation Learning
Published 2020-02-25
URL https://arxiv.org/abs/2002.11522v3
PDF https://arxiv.org/pdf/2002.11522v3.pdf
PWC https://paperswithcode.com/paper/network-representation-learning-for-link
Repo
Framework

Multi-Task Learning Enhanced Single Image De-Raining

Title Multi-Task Learning Enhanced Single Image De-Raining
Authors YuLong Fan, Rong Chen, Bo Li
Abstract Rain removal in images is an important task in computer vision filed and attracting attentions of more and more people. In this paper, we address a non-trivial issue of removing visual effect of rain streak from a single image. Differing from existing work, our method combines various semantic constraint task in a proposed multi-task regression model for rain removal. These tasks reinforce the model’s capabilities from the content, edge-aware, and local texture similarity respectively. To further improve the performance of multi-task learning, we also present two simple but powerful dynamic weighting algorithms. The proposed multi-task enhanced network (MENET) is a powerful convolutional neural network based on U-Net for rain removal research, with a specific focus on utilize multiple tasks constraints and exploit the synergy among them to facilitate the model’s rain removal capacity. It is noteworthy that the adaptive weighting scheme has further resulted in improved network capability. We conduct several experiments on synthetic and real rain images, and achieve superior rain removal performance over several selected state-of-the-art (SOTA) approaches. The overall effect of our method is impressive, even in the decomposition of heavy rain and rain streak accumulation.The source code and some results can be found at:https://github.com/SumiHui/MENET.
Tasks Multi-Task Learning, Rain Removal
Published 2020-03-21
URL https://arxiv.org/abs/2003.09689v1
PDF https://arxiv.org/pdf/2003.09689v1.pdf
PWC https://paperswithcode.com/paper/multi-task-learning-enhanced-single-image-de
Repo
Framework

Multi-source Deep Gaussian Process Kernel Learning

Title Multi-source Deep Gaussian Process Kernel Learning
Authors Chi-Ken Lu, Patrick Shafto
Abstract For many problems, relevant data are plentiful but explicit knowledge is not. Predictions about target variables may be informed by data sources that are noisy but plentiful, or data which the target variable is merely some function of. Intrepretable and flexible machine learning methods capable of fusing data across sources are lacking. We generalize the Deep Gaussian Processes so that GPs in intermediate layers can represent the posterior distribution summarizing the data from a related source. We model the prior-posterior stacking DGP with a single GP. The exact second moment of DGP is calculated analytically, and is taken as the kernel function for GP. The result is a kernel that captures effective correlation through function composition, reflects the structure of the observations from other data sources, and can be used to inform prediction based on limited direct observations. Therefore, the approximation of prior-posterior DGP can be considered a novel kernel composition which blends the kernels in different layers and have explicit dependence on the data. We consider two synthetic multi-source prediction problems: a) predicting a target variable that is merely a function of the source data and b) predicting noise-free data using a kernel trained on noisy data. Our method produces better prediction and tighter uncertainty on the synthetic data when comparing with standard GP and other DGP method, suggesting that our data-informed approximate DGPs are a powerful tool for integrating data across sources.
Tasks Gaussian Processes
Published 2020-02-07
URL https://arxiv.org/abs/2002.02826v1
PDF https://arxiv.org/pdf/2002.02826v1.pdf
PWC https://paperswithcode.com/paper/multi-source-deep-gaussian-process-kernel
Repo
Framework

Fast inference of Boosted Decision Trees in FPGAs for particle physics

Title Fast inference of Boosted Decision Trees in FPGAs for particle physics
Authors Sioni Summers, Giuseppe Di Guglielmo, Javier Duarte, Philip Harris, Duc Hoang, Sergo Jindariani, Edward Kreinar, Vladimir Loncar, Jennifer Ngadiuba, Maurizio Pierini, Dylan Rankin, Nhan Tran, Zhenbin Wu
Abstract We describe the implementation of Boosted Decision Trees in the hls4ml library, which allows the translation of a trained model into FPGA firmware through an automated conversion process. Thanks to its fully on-chip implementation, hls4ml performs inference of Boosted Decision Tree models with extremely low latency. With a typical latency less than 100 ns, this solution is suitable for FPGA-based real-time processing, such as in the Level-1 Trigger system of a collider experiment. These developments open up prospects for physicists to deploy BDTs in FPGAs for identifying the origin of jets, better reconstructing the energies of muons, and enabling better selection of rare signal processes.
Tasks
Published 2020-02-05
URL https://arxiv.org/abs/2002.02534v2
PDF https://arxiv.org/pdf/2002.02534v2.pdf
PWC https://paperswithcode.com/paper/fast-inference-of-boosted-decision-trees-in
Repo
Framework

Gun Source and Muzzle Head Detection

Title Gun Source and Muzzle Head Detection
Authors Zhong Zhou, Isak Czeresnia Etinger, Florian Metze, Alexander Hauptmann, Alexander Waibel
Abstract There is a surging need across the world for protection against gun violence. There are three main areas that we have identified as challenging in research that tries to curb gun violence: temporal location of gunshots, gun type prediction and gun source (shooter) detection. Our task is gun source detection and muzzle head detection, where the muzzle head is the round opening of the firing end of the gun. We would like to locate the muzzle head of the gun in the video visually, and identify who has fired the shot. In our formulation, we turn the problem of muzzle head detection into two sub-problems of human object detection and gun smoke detection. Our assumption is that the muzzle head typically lies between the gun smoke caused by the shot and the shooter. We have interesting results both in bounding the shooter as well as detecting the gun smoke. In our experiments, we are successful in detecting the muzzle head by detecting the gun smoke and the shooter.
Tasks Head Detection, Object Detection
Published 2020-01-29
URL https://arxiv.org/abs/2001.11120v1
PDF https://arxiv.org/pdf/2001.11120v1.pdf
PWC https://paperswithcode.com/paper/gun-source-and-muzzle-head-detection
Repo
Framework

Variational Bayesian Methods for Stochastically Constrained System Design Problems

Title Variational Bayesian Methods for Stochastically Constrained System Design Problems
Authors Prateek Jaiswal, Harsha Honnappa, Vinayak A. Rao
Abstract We study system design problems stated as parameterized stochastic programs with a chance-constraint set. We adopt a Bayesian approach that requires the computation of a posterior predictive integral which is usually intractable. In addition, for the problem to be a well-defined convex program, we must retain the convexity of the feasible set. Consequently, we propose a variational Bayes-based method to approximately compute the posterior predictive integral that ensures tractability and retains the convexity of the feasible set. Under certain regularity conditions, we also show that the solution set obtained using variational Bayes converges to the true solution set as the number of observations tends to infinity. We also provide bounds on the probability of qualifying a true infeasible point (with respect to the true constraints) as feasible under the VB approximation for a given number of samples.
Tasks
Published 2020-01-06
URL https://arxiv.org/abs/2001.01404v1
PDF https://arxiv.org/pdf/2001.01404v1.pdf
PWC https://paperswithcode.com/paper/variational-bayesian-methods-for
Repo
Framework

Target driven visual navigation exploiting object relationships

Title Target driven visual navigation exploiting object relationships
Authors Yiding Qiu, Anwesan Pal, Henrik I. Christensen
Abstract Recently target driven visual navigation strategies have gained a lot of popularity in the computer vision and reinforcement learning community. Unfortunately, most of the current research tends to incorporate sensory input into a reward-based learning approach, with the hope that a robot can implicitly learn its optimal actions through recursive trials. These methods seldom generalize across domains as they fail to exploit natural environment object relationships. We present Memory-utilized Joint hierarchical Object Learning for Navigation in Indoor Rooms (MJOLNIR), a target-driven visual navigation algorithm, which considers the inherent relationship between “target” objects, along with the more salient “parent” objects occurring in its surrounding. Extensive experiments conducted across multiple environment settings show $\approx \textbf{30 %}$ improvement over the existing state-of-the-art navigation methods in terms of the success rate. We also show that our model learns to converge much faster than other algorithms. We will make our code publicly available for use in the scientific community.
Tasks Visual Navigation
Published 2020-03-15
URL https://arxiv.org/abs/2003.06749v1
PDF https://arxiv.org/pdf/2003.06749v1.pdf
PWC https://paperswithcode.com/paper/target-driven-visual-navigation-exploiting
Repo
Framework

Consistent Batch Normalization for Weighted Loss in Imbalanced-Data Environment

Title Consistent Batch Normalization for Weighted Loss in Imbalanced-Data Environment
Authors Muneki Yasuda, Yeo Xian En, Seishirou Ueno
Abstract In this study, we consider classification problems based on neural networks in a data-imbalanced environment. Learning from an imbalanced dataset is one of the most important and practical problems in the field of machine learning. A weighted loss function (WLF) based on a cost-sensitive approach is a well-known and effective method for imbalanced datasets. We consider a combination of WLF and batch normalization (BN) in this study. BN is considered as a powerful standard technique in the recent developments in deep learning. A simple combination of both methods leads to a size-inconsistency problem due to a mismatch between the interpretations of the effective size of the dataset in both methods. We propose a simple modification to BN, called weighted batch normalization (WBN), to correct the size-mismatch. The idea of WBN is simple and natural. Using numerical experiments, we demonstrate that our method is effective in a data-imbalanced environment.
Tasks
Published 2020-01-06
URL https://arxiv.org/abs/2001.01433v2
PDF https://arxiv.org/pdf/2001.01433v2.pdf
PWC https://paperswithcode.com/paper/consistent-batch-normalization-for-weighted
Repo
Framework

Exploring Structural Inductive Biases in Emergent Communication

Title Exploring Structural Inductive Biases in Emergent Communication
Authors Agnieszka Słowik, Abhinav Gupta, William L. Hamilton, Mateja Jamnik, Sean B. Holden, Christopher Pal
Abstract Human language and thought are characterized by the ability to systematically generate a potentially infinite number of complex structures (e.g., sentences) from a finite set of familiar components (e.g., words). Recent works in emergent communication have discussed the propensity of artificial agents to develop a systematically compositional language through playing co-operative referential games. The degree of structure in the input data was found to affect the compositionality of the emerged communication protocols. Thus, we explore various structural priors in multi-agent communication and propose a novel graph referential game. We compare the effect of structural inductive bias (bag-of-words, sequences and graphs) on the emergence of compositional understanding of the input concepts measured by topographic similarity and generalization to unseen combinations of familiar properties. We empirically show that graph neural networks induce a better compositional language prior and a stronger generalization to out-of-domain data. We further perform ablation studies that show the robustness of the emerged protocol in graph referential games.
Tasks
Published 2020-02-04
URL https://arxiv.org/abs/2002.01335v1
PDF https://arxiv.org/pdf/2002.01335v1.pdf
PWC https://paperswithcode.com/paper/exploring-structural-inductive-biases-in
Repo
Framework

Deep Learning Approach for Intelligent Named Entity Recognition of Cyber Security

Title Deep Learning Approach for Intelligent Named Entity Recognition of Cyber Security
Authors Simran K, Sriram S, Vinayakumar R, Soman KP
Abstract In recent years, the amount of Cyber Security data generated in the form of unstructured texts, for example, social media resources, blogs, articles, and so on has exceptionally increased. Named Entity Recognition (NER) is an initial step towards converting this unstructured data into structured data which can be used by a lot of applications. The existing methods on NER for Cyber Security data are based on rules and linguistic characteristics. A Deep Learning (DL) based approach embedded with Conditional Random Fields (CRFs) is proposed in this paper. Several DL architectures are evaluated to find the most optimal architecture. The combination of Bidirectional Gated Recurrent Unit (Bi-GRU), Convolutional Neural Network (CNN), and CRF performed better compared to various other DL frameworks on a publicly available benchmark dataset. This may be due to the reason that the bidirectional structures preserve the features related to the future and previous words in a sequence.
Tasks Named Entity Recognition
Published 2020-03-31
URL https://arxiv.org/abs/2004.00502v1
PDF https://arxiv.org/pdf/2004.00502v1.pdf
PWC https://paperswithcode.com/paper/deep-learning-approach-for-intelligent-named
Repo
Framework
comments powered by Disqus