PyTorchKR Papers

최신 논문

총 3,337편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2102.08312공식 코드 · Papers with Code

On Mathews Correlation Coefficient and Improved Distance Map Loss for Automatic Glacier Calving Front Segmentation in SAR Imagery

The vast majority of the outlet glaciers and ice streams of the polar ice sheets end in the ocean. Ice mass loss via calving of the glaciers into the ocean has increased over the last few decades. Information on the temporal variability of the calving front position provides fundamental information on the state of the glacier and ice stream, which can be exploited as calibration and validation data to enhance ice dynamics modeling. To identify the calving front position automatically, deep neural network-based semantic segmentation pipelines can be used to delineate the acquired SAR imagery. However, the extreme class imbalance is highly challenging for the accurate calving front segmentation in these images. Therefore, we propose the use of the Mathews correlation coefficient (MCC) as an early stopping criterion because of its symmetrical properties and its invariance towards class imbalance. Moreover, we propose an improvement to the distance map-based binary cross-entropy (BCE) loss function. The distance map adds context to the loss function about the important regions for segmentation and helps accounting for the imbalanced data. Using Mathews correlation coefficient as early stopping demonstrates an average 15% dice coefficient improvement compared to the commonly used BCE. The modified distance map loss further improves the segmentation performance by another 2%. These results are encouraging as they support the effectiveness of the proposed methods for segmentation problems suffering from extreme class imbalances.

arXiv:2102.07594

Fast End-to-End Speech Recognition via Non-Autoregressive Models and Cross-Modal Knowledge Transferring from BERT

Attention-based encoder-decoder (AED) models have achieved promising performance in speech recognition. However, because the decoder predicts text tokens (such as characters or words) in an autoregressive manner, it is difficult for an AED model to predict all tokens in parallel. This makes the inference speed relatively slow. We believe that because the encoder already captures the whole speech utterance, which has the token-level relationship implicitly, we can predict a token without explicitly autoregressive language modeling. When the prediction of a token does not rely on other tokens, the parallel prediction of all tokens in the sequence is realizable. Based on this idea, we propose a non-autoregressive speech recognition model called LASO (Listen Attentively, and Spell Once). The model consists of an encoder, a decoder, and a position dependent summarizer (PDS). The three modules are based on basic attention blocks. The encoder extracts high-level representations from the speech. The PDS uses positional encodings corresponding to tokens to convert the acoustic representations into token-level representations. The decoder further captures token-level relationships with the self-attention mechanism. At last, the probability distribution on the vocabulary is computed for each token position. Therefore, speech recognition is re-formulated as a position-wise classification problem. Further, we propose a cross-modal transfer learning method to refine semantics from a large-scale pre-trained language model BERT for improving the performance.

arXiv:2102.07090공식 코드 · Papers with Code

New methods for metastimuli: architecture, embeddings, and neural network optimization

Six significant new methodological developments of the previously-presented "metastimuli architecture" for human learning through machine learning of spatially correlated structural position within a user's personal information management system (PIMS), providing the basis for haptic metastimuli, are presented. These include architectural innovation, recurrent (RNN) artificial neural network (ANN) application, a variety of atom embedding techniques (including a novel technique we call "nabla" embedding inspired by linguistics), ANN hyper-parameter (one that affects the network but is not trained, e.g. the learning rate) optimization, and meta-parameter (one that determines the system performance but is not trained and not a hyper-parameter, e.g. the atom embedding technique) optimization for exploring the large design space. A technique for using the system for automatic atom categorization in a user's PIMS is outlined. ANN training and hyper- and meta-parameter optimization results are presented and discussed in service of methodological recommendations.

arXiv:2102.06150

A Geometric Nonlinear Stochastic Filter for Simultaneous Localization and Mapping

Simultaneous Localization and Mapping (SLAM) is one of the key robotics tasks as it tackles simultaneous mapping of the unknown environment defined by multiple landmark positions and localization of the unknown pose (i.e., attitude and position) of the robot in three-dimensional (3D) space. The true SLAM problem is modeled on the Lie group of $\mathbb{SLAM}_{n}\left(3\right)$, and its true dynamics rely on angular and translational velocities. This paper proposes a novel geometric nonlinear stochastic estimator algorithm for SLAM on $\mathbb{SLAM}_{n}\left(3\right)$ that precisely mimics the nonlinear motion dynamics of the true SLAM problem. Unlike existing solutions, the proposed stochastic filter takes into account unknown constant bias and noise attached to the velocity measurements. The proposed nonlinear stochastic estimator on manifold is guaranteed to produce good results provided with the measurements of angular velocities, translational velocities, landmarks, and inertial measurement unit (IMU). Simulation and experimental results reflect the ability of the proposed filter to successfully estimate the six-degrees-of-freedom (6 DoF) robot's pose and landmark positions. Keywords: Simultaneous Localization and Mapping, nonlinear stochastic observer for SLAM, stochastic differential equations, pose estimator, position, attitude, Brownian motion process, inertial measurement unit, landmarks, features, SDE, SO(3), SE(3), SLAM.

arXiv:2102.05260

SensPick: Sense Picking for Word Sense Disambiguation

Word sense disambiguation (WSD) methods identify the most suitable meaning of a word with respect to the usage of that word in a specific context. Neural network-based WSD approaches rely on a sense-annotated corpus since they do not utilize lexical resources. In this study, we utilize both context and related gloss information of a target word to model the semantic relationship between the word and the set of glosses. We propose SensPick, a type of stacked bidirectional Long Short Term Memory (LSTM) network to perform the WSD task. The experimental evaluation demonstrates that SensPick outperforms traditional and state-of-the-art models on most of the benchmark datasets with a relative improvement of 3.5% in F-1 score. While the improvement is not significant, incorporating semantic relationships brings SensPick in the leading position compared to others.

arXiv:2102.04310

The Singleton Fallacy: Why Current Critiques of Language Models Miss the Point

This paper discusses the current critique against neural network-based Natural Language Understanding (NLU) solutions known as language models. We argue that much of the current debate rests on an argumentation error that we will refer to as the singleton fallacy: the assumption that language, meaning, and understanding are single and uniform phenomena that are unobtainable by (current) language models. By contrast, we will argue that there are many different types of language use, meaning and understanding, and that (current) language models are build with the explicit purpose of acquiring and representing one type of structural understanding of language. We will argue that such structural understanding may cover several different modalities, and as such can handle several different types of meaning. Our position is that we currently see no theoretical reason why such structural knowledge would be insufficient to count as "real" understanding.

arXiv:2102.04139

APS: A Large-Scale Multi-Modal Indoor Camera Positioning System

Navigation inside a closed area with no GPS-signal accessibility is a highly challenging task. In order to tackle this problem, recently the imaging-based methods have grabbed the attention of many researchers. These methods either extract the features (e.g. using SIFT, or SOSNet) and map the descriptive ones to the camera position and rotation information, or deploy an end-to-end system that directly estimates this information out of RGB images, similar to PoseNet. While the former methods suffer from heavy computational burden during the test process, the latter suffers from lack of accuracy and robustness against environmental changes and object movements. However, end-to-end systems are quite fast during the test and inference and are pretty qualified for real-world applications, even though their training phase could be longer than the former ones. In this paper, a novel multi-modal end-to-end system for large-scale indoor positioning has been proposed, namely APS (Alpha Positioning System), which integrates a Pix2Pix GAN network to reconstruct the point cloud pair of the input query image, with a deep CNN network in order to robustly estimate the position and rotation information of the camera. For this integration, the existing datasets have the shortcoming of paired RGB/point cloud images for indoor environments. Therefore, we created a new dataset to handle this situation. By implementing the proposed APS system, we could achieve a highly accurate camera positioning with a precision level of less than a centimeter.

arXiv:2102.04024공식 코드 · Papers with Code

IDOL: Inertial Deep Orientation-Estimation and Localization

Many smartphone applications use inertial measurement units (IMUs) to sense movement, but the use of these sensors for pedestrian localization can be challenging due to their noise characteristics. Recent data-driven inertial odometry approaches have demonstrated the increasing feasibility of inertial navigation. However, they still rely upon conventional smartphone orientation estimates that they assume to be accurate, while in fact these orientation estimates can be a significant source of error. To address the problem of inaccurate orientation estimates, we present a two-stage, data-driven pipeline using a commodity smartphone that first estimates device orientations and then estimates device position. The orientation module relies on a recurrent neural network and Extended Kalman Filter to obtain orientation estimates that are used to then rotate raw IMU measurements into the appropriate reference frame. The position module then passes those measurements through another recurrent network architecture to perform localization. Our proposed method outperforms state-of-the-art methods in both orientation and position error on a large dataset we constructed that contains 20 hours of pedestrian motion across 3 buildings and 15 subjects.

arXiv:2102.02995

Application of Deep Learning in Recognizing Bates Numbers and Confidentiality Stamping from Images

In eDiscovery, it is critical to ensure that each page produced in legal proceedings conforms with the requirements of court or government agency production requests. Errors in productions could have severe consequences in a case, putting a party in an adverse position. The volume of pages produced continues to increase, and tremendous time and effort has been taken to ensure quality control of document productions. This has historically been a manual and laborious process. This paper demonstrates a novel automated production quality control application which leverages deep learning-based image recognition technology to extract Bates Number and Confidentiality Stamping from legal case production images and validate their correctness. Effectiveness of the method is verified with an experiment using a real-world production data.

arXiv:2102.02898공식 코드 · Papers with Code

Cobiveco: Consistent biventricular coordinates for precise and intuitive description of position in the heart -- with MATLAB implementation

Ventricular coordinates are widely used as a versatile tool for various applications that benefit from a description of local position within the heart. However, the practical usefulness of ventricular coordinates is determined by their ability to meet application-specific requirements. For regression-based estimation of biventricular position, for example, a symmetric definition of coordinate directions in both ventricles is important. For the transfer of data between different hearts as another use case, the consistency of coordinate values across different geometries is particularly relevant. To meet these requirements, we compare different approaches to compute coordinates and present Cobiveco, a symmetric, consistent and intuitive biventricular coordinate system that builds upon existing coordinate systems, but overcomes some of their limitations. A novel one-way transfer error is introduced to assess the consistency of the coordinates. Normalized distances along bijective trajectories between two boundaries were found to be superior to solutions of Laplace's equation for defining coordinate values, as they show better linearity in space. Evaluation of transfer and linearity errors on 36 patient geometries revealed a more than 4-fold improvement compared to a state-of-the-art method. Finally, we show two application examples underlining the relevance for cardiac data processing. Cobiveco MATLAB code is available under a permissive open-source license.

arXiv:2102.02855공식 코드 · Papers with Code

Machine Learning for Auxiliary Sources

We rewrite the numerical ansatz of the Method of Auxiliary Sources (MAS), typically used in computational electromagnetics, as a neural network, i.e. as a composed function of linear and activation layers. MAS is a numerical method for Partial Differential Equations (PDEs) that employs point sources, which are also exact solutions of the considered PDE, as radial basis functions to match a given boundary condition. In the framework of neural networks we rely on optimization algorithms such as Adam to train MAS and find both its optimal coefficients and positions of the central singularities of the sources. In this work we also show that the MAS ansatz trained as a neural network can be used, in the case of an unknown function with a central singularity, to detect the position of such singularity.

arXiv:2102.03130

Improving CSI-based Massive MIMO Indoor Positioning using Convolutional Neural Network

Multiple-input multiple-output (MIMO) is an enabling technology to meet the growing demand for faster and more reliable communications in wireless networks with a large number of terminals, but it can also be applied for position estimation of a terminal exploiting multipath propagation from multiple antennas. In this paper, we investigate new convolutional neural network (CNN) structures for exploiting MIMO-based channel state information (CSI) to improve indoor positioning. We evaluate and compare the performance of three variants of the proposed CNN structure to five NN structures proposed in the scientific literature using the same sets of training-evaluation data. The results demonstrate that the proposed residual convolutional NN structure improves the accuracy of position estimation and keeps the total number of weights lower than the published NN structures. The proposed CNN structure yields from 2cm to 10cm better position accuracy than known NN structures used as a reference.

arXiv:2011.12892공식 코드 · Papers with Code

Single point positioning using full and fractional pseudorange measurements from GPS and BDS

In conventional global navigation satellite system (GNSS) receivers, usually full pseudorange measurements are required to complete a single point position fix. However, to obtain full pseudorange measurements takes longer time than for fractional pseudorange measurements. Considering such a fact, in order to shorten the time to first fix and improve the position accuracy during cold or warm start of a dual-constellation GNSS receiver, we propose a positioning algorithm using full and fractional pseudorange measurements from the two navigational constellations. This method uses four full pseudorange measurements from one constellation along with fractional ones from either or both constellations to obtain a potentially rapid position result with an identical accuracy to that of the conventional positioning method using full measurements. Tests with simulated and real Global Positioning System (GPS) and BeiDou Navigation Satellite System (BDS) data demonstrate that the proposed method can generate correct single point position solutions and the position error is identical with the result from the conventional approach using the full pseudorange measurements.

arXiv:2101.12322

Position, Padding and Predictions: A Deeper Look at Position Information in CNNs

In contrast to fully connected networks, Convolutional Neural Networks (CNNs) achieve efficiency by learning weights associated with local filters with a finite spatial extent. An implication of this is that a filter may know what it is looking at, but not where it is positioned in the image. In this paper, we first test this hypothesis and reveal that a surprising degree of absolute position information is encoded in commonly used CNNs. We show that zero padding drives CNNs to encode position information in their internal representations, while a lack of padding precludes position encoding. This gives rise to deeper questions about the role of position information in CNNs: (i) What boundary heuristics enable optimal position encoding for downstream tasks?; (ii) Does position encoding affect the learning of semantic representations?; (iii) Does position encoding always improve performance? To provide answers, we perform the largest case study to date on the role that padding and border heuristics play in CNNs. We design novel tasks which allow us to quantify boundary effects as a function of the distance to the border. Numerous semantic objectives reveal the effect of the border on semantic representations. Finally, we demonstrate the implications of these findings on multiple real-world tasks to show that position information can both help or hurt performance.

arXiv:2101.11954

Identifying COVID-19 Fake News in Social Media

The evolution of social media platforms have empowered everyone to access information easily. Social media users can easily share information with the rest of the world. This may sometimes encourage spread of fake news, which can result in undesirable consequences. In this work, we train models which can identify health news related to COVID-19 pandemic as real or fake. Our models achieve a high F1-score of 98.64%. Our models achieve second place on the leaderboard, tailing the first position with a very narrow margin 0.05% points.

arXiv:2101.11268공식 코드 · Papers with Code

Enquire One's Parent and Child Before Decision: Fully Exploit Hierarchical Structure for Self-Supervised Taxonomy Expansion

Taxonomy is a hierarchically structured knowledge graph that plays a crucial role in machine intelligence. The taxonomy expansion task aims to find a position for a new term in an existing taxonomy to capture the emerging knowledge in the world and keep the taxonomy dynamically updated. Previous taxonomy expansion solutions neglect valuable information brought by the hierarchical structure and evaluate the correctness of merely an added edge, which downgrade the problem to node-pair scoring or mini-path classification. In this paper, we propose the Hierarchy Expansion Framework (HEF), which fully exploits the hierarchical structure's properties to maximize the coherence of expanded taxonomy. HEF makes use of taxonomy's hierarchical structure in multiple aspects: i) HEF utilizes subtrees containing most relevant nodes as self-supervision data for a complete comparison of parental and sibling relations; ii) HEF adopts a coherence modeling module to evaluate the coherence of a taxonomy's subtree by integrating hypernymy relation detection and several tree-exclusive features; iii) HEF introduces the Fitting Score for position selection, which explicitly evaluates both path and level selections and takes full advantage of parental relations to interchange information for disambiguation and self-correction. Extensive experiments show that by better exploiting the hierarchical structure and optimizing taxonomy's coherence, HEF vastly surpasses the prior state-of-the-art on three benchmark datasets by an average improvement of 46.7% in accuracy and 32.3% in mean reciprocal rank.

arXiv:2101.11179

Solar Radiation Ramping Events Modeling Using Spatio-temporal Point Processes

Modeling and predicting solar events, particularly the solar ramping event, is critical for improving situational awareness for solar power generation systems. It has been acknowledged that weather conditions such as temperature, humidity, and cloud density can significantly impact the emergence and position of solar ramping events. As a result, modeling these events with complex spatio-temporal correlations is highly challenging. To tackle the question, we adopt a novel spatio-temporal categorical point process model, which intuitively and effectively addresses correlation and interaction among ramping events. We demonstrate the interpretability and predictive power of our model on extensive real-data experiments.

arXiv:2101.10838

Visible light communication-based monitoring for indoor environments using unsupervised learning

Visible Light Communication~(VLC) systems provide not only illumination and data communication, but also indoor monitoring services if the effect that different events create on the received optical signal is properly tracked. For this purpose, the Channel State Information that a VLC receiver computes to equalize the subcarriers of the OFDM signal can be also reused to train an Unsupervised Learning classifier. This way, different clusters can be created on the collected CSI data, which could be then mapped into relevant events to-be-monitored in the indoor environments, such as the presence of a new object in a given position or the change of the position of a given object. When compared to supervised learning algorithms, the proposed approach does not need to add tags in the training data, simplifying notably the implementation of the machine learning classifier. The practical validation the monitoring approach was done with the aid of a software-defined VLC link based on OFDM, in which a copy of the intensity modulated signal coming from a Phosphor-converted LED was captured by a pair of Photodetectors~(PDs). The performance evaluation of the experimental VLC-based monitoring demo achieved a positioning accuracy in the few-centimeter-range, without the necessity of deploying a large number of sensors and/or adding a VLC-enabled sensor on the object to-be-tracked.

arXiv:2101.10655

Variational Information Bottleneck Model for Accurate Indoor Position Recognition

Recognizing user location with WiFi fingerprints is a popular approach for accurate indoor positioning problems. In this work, our goal is to interpret WiFi fingerprints into actual user locations. However, WiFi fingerprint data can be very high dimensional in some cases, we need to find a good representation of the input data for the learning task first. Otherwise, using neural networks will suffer from severe overfitting. In this work, we solve this issue by combining the Information Bottleneck method and Variational Inference. Based on these two approaches, we propose a Variational Information Bottleneck model for accurate indoor positioning. The proposed model consists of an encoder structure and a predictor structure. The encoder is to find a good representation in the input data for the learning task. The predictor is to use the latent representation to predict the final output. To enhance the generalization of our model, we also adopt the Dropout technique for each hidden layer of the decoder. We conduct the validation experiments on a real-world dataset. We also compare the proposed model to other existing methods so as to quantify the performances of our method.

arXiv:2101.10098

The Slodderwetenschap (Sloppy Science) of Stochastic Parrots -- A Plea for Science to NOT take the Route Advocated by Gebru and Bender

This article is a position paper written in reaction to the now-infamous paper titled "On the Dangers of Stochastic Parrots: Can Language Models Be Too Big?" by Timnit Gebru, Emily Bender, and others who were, as of the date of this writing, still unnamed. I find the ethics of the Parrot Paper lacking, and in that lack, I worry about the direction in which computer science, machine learning, and artificial intelligence are heading. At best, I would describe the argumentation and evidentiary practices embodied in the Parrot Paper as Slodderwetenschap (Dutch for Sloppy Science) -- a word which the academic world last widely used in conjunction with the Diederik Stapel affair in psychology [2]. What is missing in the Parrot Paper are three critical elements: 1) acknowledgment that it is a position paper/advocacy piece rather than research, 2) explicit articulation of the critical presuppositions, and 3) explicit consideration of cost/benefit trade-offs rather than a mere recitation of potential "harms" as if benefits did not matter. To leave out these three elements is not good practice for either science or research.