PyTorchKR Papers

최신 논문

총 3,337편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2110.02771

DNN-assisted Particle-based Bayesian Joint Synchronization and Localization

In this work, we propose a Deep neural network-assisted Particle Filter-based (DePF) approach to address the Mobile User (MU) joint synchronization and localization (sync\&loc) problem in ultra dense networks. In particular, DePF deploys an asymmetric time-stamp exchange mechanism between the MUs and the Access Points (APs), which, traditionally, provides us with information about the MUs' clock offset and skew. However, information about the distance between an AP and an MU is also intrinsic to the propagation delay experienced by exchanged time-stamps. In addition, to estimate the angle of arrival of the received synchronization packet, DePF draws on the multiple signal classification algorithm that is fed by Channel Impulse Response (CIR) experienced by the sync packets. The CIR is also leveraged on to determine the link condition, i.e. Line-of-Sight (LoS) or Non-LoS. Finally, to perform joint sync\&loc, DePF capitalizes on particle Gaussian mixtures that allow for a hybrid particle-based and parametric Bayesian Recursive Filtering (BRF) fusion of the aforementioned pieces of information and thus jointly estimate the position and clock parameters of the MUs. The simulation results verifies the superiority of the proposed algorithm over the state-of-the-art schemes, especially that of Extended Kalman filter- and linearized BRF-based joint sync\&loc. In particular, only drawing on the synchronization time-stamp exchange and CIRs, for 90$\%$of the cases, the absolute position and clock offset estimation error remain below 1 meter and 2 nanoseconds, respectively.

arXiv:2110.01345

A new iterative algorithm for generating gradient directions to detect white matter fibers in brain from MRI data

This paper proposes an iterative algorithm for choosing gradient directions use to reconstruct white matter fibers in the brain. The present study is not focusing on data acquisition where scanning is performed. The Adaptive Gradient Directions (AGD) approach is extended to refine the position and area of the grid, resulting in an admissible reduction in angular error. We begin with the gradient directions distributed uniformly inside a grid of bigger size and with larger spacing between the points. Both (size of the grid and spacing between the points) reduce iteratively. The proposed algorithm ensures that the actual position of fiber comes inside the grid at each iteration, unlike as in the AGD approach. As a result, the solution tends to actual orientation in each iteration followed by better estimation of fibers. The proposed algorithm is validated by associating it with mixture of Gaussian diffusion and mixture of non-central Wishart distribution models. The proposed approach significantly reduce the angular error for multiple computer-generated experiments on synthetic simulations and real data. Moreover, we have also performed simulations with fibers not residing in the XY-plane. For this set-up also, the proposed work outperforms, giving lesser angular error with both the models. Synthetic simulations have been performed with Rician distributed (R-D) noise of standard deviation ranging from 0.02-0.1. This work helps in better understanding of the anatomy of the brain using the MRI signal data.

arXiv:2110.00811

Multiversal Simulacra: Understanding Hypotheticals and Possible Worlds Through Simulation

Recommender systems research is concerned with many aspects of recommender system behavior and effects than simply its effectiveness, and simulation can be a powerful tool for uncovering these effects. In this brief position paper, I identify specific types of research that simulation is uniquely well-suited to address along with a hierarchy of simulation types.

arXiv:2110.00876공식 코드 · Papers with Code

Incremental Non-Gaussian Inference for SLAM Using Normalizing Flows

This paper presents normalizing flows for incremental smoothing and mapping (NF-iSAM), a novel algorithm for inferring the full posterior distribution in SLAM problems with nonlinear measurement models and non-Gaussian factors. NF-iSAM exploits the expressive power of neural networks, and trains normalizing flows to model and sample the full posterior. By leveraging the Bayes tree, NF-iSAM enables efficient incremental updates similar to iSAM2, albeit in the more challenging non-Gaussian setting. We demonstrate the advantages of NF-iSAM over state-of-the-art point and distribution estimation algorithms using range-only SLAM problems with data association ambiguity. NF-iSAM presents superior accuracy in describing the posterior beliefs of continuous variables (e.g., position) and discrete variables (e.g., data association).

arXiv:2110.00335공식 코드 · Papers with Code

Geometry Attention Transformer with Position-aware LSTMs for Image Captioning

In recent years, transformer structures have been widely applied in image captioning with impressive performance. For good captioning results, the geometry and position relations of different visual objects are often thought of as crucial information. Aiming to further promote image captioning by transformers, this paper proposes an improved Geometry Attention Transformer (GAT) model. In order to further leverage geometric information, two novel geometry-aware architectures are designed respectively for the encoder and decoder in our GAT. Besides, this model includes the two work modules: 1) a geometry gate-controlled self-attention refiner, for explicitly incorporating relative spatial information into image region representations in encoding steps, and 2) a group of position-LSTMs, for precisely informing the decoder of relative word position in generating caption texts. The experiment comparisons on the datasets MS COCO and Flickr30K show that our GAT is efficient, and it could often outperform current state-of-the-art image captioning models.

arXiv:2110.00513

Belief propagation for permutations, rankings, and partial orders

Many datasets give partial information about an ordering or ranking by indicating which team won a game, which item a user prefers, or who infected whom. We define a continuous spin system whose Gibbs distribution is the posterior distribution on permutations, given a probabilistic model of these interactions. Using the cavity method we derive a belief propagation algorithm that computes the marginal distribution of each node's position. In addition, the Bethe free energy lets us approximate the number of linear extensions of a partial order and perform model selection between competing probabilistic models, such as the Bradley-Terry-Luce model of noisy comparisons and its cousins.

arXiv:2109.15308공식 코드 · Papers with Code

MOLUCINATE: A Generative Model for Molecules in 3D Space

Recent advances in machine learning have enabled generative models for both optimization and de novo generation of drug candidates with desired properties. Previous generative models have focused on producing SMILES strings or 2D molecular graphs, while attempts at producing molecules in 3D have focused on reinforcement learning (RL), distance matrices, and pure atom density grids. Here we present MOLUCINATE (MOLecUlar ConvolutIoNal generATive modEl), a novel architecture that simultaneously generates topological and 3D atom position information. We demonstrate the utility of this method by using it to optimize molecules for desired radius of gyration. In the future, this model can be used for more useful optimization such as binding affinity for a protein target.

arXiv:2109.15159

Focused Contrastive Training for Test-based Constituency Analysis

We propose a scheme for self-training of grammaticality models for constituency analysis based on linguistic tests. A pre-trained language model is fine-tuned by contrastive estimation of grammatical sentences from a corpus, and ungrammatical sentences that were perturbed by a syntactic test, a transformation that is motivated by constituency theory. We show that consistent gains can be achieved if only certain positive instances are chosen for training, depending on whether they could be the result of a test transformation. This way, the positives, and negatives exhibit similar characteristics, which makes the objective more challenging for the language model, and also allows for additional markup that indicates the position of the test application within the sentence.

arXiv:2109.12982

Sustainable Urban Mobility in the Post-Pandemic Era (position paper)

COVID-19 is the first pandemic of the modern world causing significant changes to the everyday life of billions of people in all continents. To reduce its expansion, most governments decided to mitigate a great percentage of daily movements of their citizens. For instance, they enforced strict controls (in space, time, etc.) on urban movement whereas they selectively prohibited international air and ground connections. In this short study, we briefly discuss some lessons learned out of this process based on recorded mobility figures, and we raise challenges that are emerging in the post-pandemic era, in the intersection of the sustainable urban mobility and movement data science fields.

arXiv:2109.12788

Multiplicative Position-aware Transformer Models for Language Understanding

Transformer models, which leverage architectural improvements like self-attention, perform remarkably well on Natural Language Processing (NLP) tasks. The self-attention mechanism is position agnostic. In order to capture positional ordering information, various flavors of absolute and relative position embeddings have been proposed. However, there is no systematic analysis on their contributions and a comprehensive comparison of these methods is missing in the literature. In this paper, we review major existing position embedding methods and compare their accuracy on downstream NLP tasks, using our own implementations. We also propose a novel multiplicative embedding method which leads to superior accuracy when compared to existing methods. Finally, we show that our proposed embedding method, served as a drop-in replacement of the default absolute position embedding, can improve the RoBERTa-base and RoBERTa-large models on SQuAD1.1 and SQuAD2.0 datasets.

arXiv:2109.12935

Time Series Model Attribution Visualizations as Explanations

Attributions are a common local explanation technique for deep learning models on single samples as they are easily extractable and demonstrate the relevance of input values. In many cases, heatmaps visualize such attributions for samples, for instance, on images. However, heatmaps are not always the ideal visualization to explain certain model decisions for other data types. In this review, we focus on attribution visualizations for time series. We collect attribution heatmap visualizations and some alternatives, discuss the advantages as well as disadvantages and give a short position towards future opportunities for attributions and explanations for time series.

arXiv:2109.12027

Sequential TOA-Based Moving Target Localization in Multi-Agent Networks

Localizing moving targets in unknown harsh environments has always been a severe challenge. This letter investigates a novel localization system based on multi-agent networks, where multiple agents serve as mobile anchors broadcasting their time-space information to the targets. We study how the moving target can localize itself using the sequential time of arrival (TOA) of the one-way broadcast signals. An extended two-step weighted least squares (TSWLS) method is proposed to jointly estimate the position and velocity of the target in the presence of agent information uncertainties. We also address the large target clock offset (LTCO) problem for numerical stability. Analytical results reveal that our method reaches the Cramer-Rao lower bound (CRLB) under small noises. Numerical results show that the proposed method performs better than the existing algorithms.

arXiv:2109.11749공식 코드 · Papers with Code

Fine-Grained Image Generation from Bangla Text Description using Attentional Generative Adversarial Network

Generating fine-grained, realistic images from text has many applications in the visual and semantic realm. Considering that, we propose Bangla Attentional Generative Adversarial Network (AttnGAN) that allows intensified, multi-stage processing for high-resolution Bangla text-to-image generation. Our model can integrate the most specific details at different sub-regions of the image. We distinctively concentrate on the relevant words in the natural language description. This framework has achieved a better inception score on the CUB dataset. For the first time, a fine-grained image is generated from Bangla text using attentional GAN. Bangla has achieved 7th position among 100 most spoken languages. This inspires us to explicitly focus on this language, which will ensure the inevitable need of many people. Moreover, Bangla has a more complex syntactic structure and less natural language processing resource that validates our work more.

arXiv:2109.11173

Pairwise Distance and Position Estimators From Differences in UWB Channels to Observers

We consider the problem of obtaining relative location information between two wireless nodes from the differences in their ultra-wideband (UWB) channels to observer nodes. Our approach focuses on the delays of multipath components (MPCs) extracted from the observed channels. For the two different cases of known and unknown MPC association between these channels, we present estimators for the distance and for the relative position vector between the two nodes. The position estimators require both MPC directions and MPC delays as input. All presented estimators exhibit very desirable technological properties: they do not require line-of-sight conditions, precise synchronization, or knowledge about the observer locations or about the environment. These advantages could enable low-cost wireless network localization in dynamic multipath environments. The exposition is complemented by a numerical evaluation of the estimation accuracy using random sampling, where especially the position estimators show the potential for great accuracy.

arXiv:2109.10765

An artificial neural network approach to bifurcating phenomena in computational fluid dynamics

This work deals with the investigation of bifurcating fluid phenomena using a reduced order modelling setting aided by artificial neural networks. We discuss the POD-NN approach dealing with non-smooth solutions set of nonlinear parametrized PDEs. Thus, we study the Navier-Stokes equations describing: (i) the Coanda effect in a channel, and (ii) the lid driven triangular cavity flow, in a physical/geometrical multi-parametrized setting, considering the effects of the domain's configuration on the position of the bifurcation points. Finally, we propose a reduced manifold-based bifurcation diagram for a non-intrusive recovery of the critical points evolution. Exploiting such detection tool, we are able to efficiently obtain information about the pattern flow behaviour, from symmetry breaking profiles to attaching/spreading vortices, even at high Reynolds numbers.

arXiv:2109.10473공식 코드 · Papers with Code

MVM3Det: A Novel Method for Multi-view Monocular 3D Detection

Monocular 3D object detection encounters occlusion problems in many application scenarios, such as traffic monitoring, pedestrian monitoring, etc., which leads to serious false negative. Multi-view object detection effectively solves this problem by combining data from different perspectives. However, due to label confusion and feature confusion, the orientation estimation of multi-view 3D object detection is intractable, which is important for object tracking and intention prediction. In this paper, we propose a novel multi-view 3D object detection method named MVM3Det which simultaneously estimates the 3D position and orientation of the object according to the multi-view monocular information. The method consists of two parts: 1) Position proposal network, which integrates the features from different perspectives into consistent global features through feature orthogonal transformation to estimate the position. 2) Multi-branch orientation estimation network, which introduces feature perspective pooling to overcome the two confusion problems during the orientation estimation. In addition, we present a first dataset for multi-view 3D object detection named MVM3D. Comparing with State-Of-The-Art (SOTA) methods on our dataset and public dataset WildTrack, our method achieves very competitive results.

arXiv:2109.09920

Survey: Transformer based Video-Language Pre-training

Inspired by the success of transformer-based pre-training methods on natural language tasks and further computer vision tasks, researchers have begun to apply transformer to video processing. This survey aims to give a comprehensive overview on transformer-based pre-training methods for Video-Language learning. We first briefly introduce the transformer tructure as the background knowledge, including attention mechanism, position encoding etc. We then describe the typical paradigm of pre-training & fine-tuning on Video-Language processing in terms of proxy tasks, downstream tasks and commonly used video datasets. Next, we categorize transformer models into Single-Stream and Multi-Stream structures, highlight their innovations and compare their performances. Finally, we analyze and discuss the current challenges and possible future research directions for Video-Language pre-training.

arXiv:2109.09975공식 코드 · Papers with Code

Fast nonlinear risk assessment for autonomous vehicles using learned conditional probabilistic models of agent futures

This paper presents fast non-sampling based methods to assess the risk for trajectories of autonomous vehicles when probabilistic predictions of other agents' futures are generated by deep neural networks (DNNs). The presented methods address a wide range of representations for uncertain predictions including both Gaussian and non-Gaussian mixture models to predict both agent positions and control inputs conditioned on the scene contexts. We show that the problem of risk assessment when Gaussian mixture models (GMMs) of agent positions are learned can be solved rapidly to arbitrary levels of accuracy with existing numerical methods. To address the problem of risk assessment for non-Gaussian mixture models of agent position, we propose finding upper bounds on risk using nonlinear Chebyshev's Inequality and sums-of-squares (SOS) programming; they are both of interest as the former is much faster while the latter can be arbitrarily tight. These approaches only require higher order statistical moments of agent positions to determine upper bounds on risk. To perform risk assessment when models are learned for agent control inputs as opposed to positions, we propagate the moments of uncertain control inputs through the nonlinear motion dynamics to obtain the exact moments of uncertain position over the planning horizon. To this end, we construct deterministic linear dynamical systems that govern the exact time evolution of the moments of uncertain position in the presence of uncertain control inputs. The presented methods are demonstrated on realistic predictions from DNNs trained on the Argoverse and CARLA datasets and are shown to be effective for rapidly assessing the probability of low probability events.

arXiv:2109.09533공식 코드 · Papers with Code

Modeling Annotation Uncertainty with Gaussian Heatmaps in Landmark Localization

In landmark localization, due to ambiguities in defining their exact position, landmark annotations may suffer from large observer variabilities, which result in uncertain annotations. To model the annotation ambiguities of the training dataset, we propose to learn anisotropic Gaussian parameters modeling the shape of the target heatmap during optimization. Furthermore, our method models the prediction uncertainty of individual samples by fitting anisotropic Gaussian functions to the predicted heatmaps during inference. Besides state-of-the-art results, our experiments on datasets of hand radiographs and lateral cephalograms also show that Gaussian functions are correlated with both localization accuracy and observer variability. As a final experiment, we show the importance of integrating the uncertainty into decision making by measuring the influence of the predicted location uncertainty on the classification of anatomical abnormalities in lateral cephalograms.

arXiv:2109.09077

DECORAS: detection and characterization of radio-astronomical sources using deep learning

We present DECORAS, a deep learning based approach to detect both point and extended sources from Very Long Baseline Interferometry (VLBI) observations. Our approach is based on an encoder-decoder neural network architecture that uses a low number of convolutional layers to provide a scalable solution for source detection. In addition, DECORAS performs source characterization in terms of the position, effective radius and peak brightness of the detected sources. We have trained and tested the network with images that are based on realistic Very Long Baseline Array (VLBA) observations at 20 cm. Also, these images have not gone through any prior de-convolution step and are directly related to the visibility data via a Fourier transform. We find that the source catalog generated by DECORAS has a better overall completeness and purity, when compared to a traditional source detection algorithm. DECORAS is complete at the 7.5$\sigma$ level, and has an almost factor of two improvement in reliability at 5.5$\sigma$. We find that DECORAS can recover the position of the detected sources to within 0.61 $\pm$ 0.69 mas, and the effective radius and peak surface brightness are recovered to within 20 per cent for 98 and 94 per cent of the sources, respectively. Overall, we find that DECORAS provides a reliable source detection and characterization solution for future wide-field VLBI surveys.