PyTorchKR Papers

최신 논문

총 3,383편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1911.03594

Robo-PlaNet: Learning to Poke in a Day

Recently, the Deep Planning Network (PlaNet) approach was introduced as a model-based reinforcement learning method that learns environment dynamics directly from pixel observations. This architecture is useful for learning tasks in which either the agent does not have access to meaningful states (like position/velocity of robotic joints) or where the observed states significantly deviate from the physical state of the agent (which is commonly the case in low-cost robots in the form of backlash or noisy joint readings). PlaNet, by design, interleaves phases of training the dynamics model with phases of collecting more data on the target environment, leading to long training times. In this work, we introduce Robo-PlaNet, an asynchronous version of PlaNet. This algorithm consistently reaches higher performance in the same amount of time, which we demonstrate in both a simulated and a real robotic experiment.

arXiv:1911.02391

Towards Human Centered AutoML

Building models from data is an integral part of the majority of data science workflows. While data scientists are often forced to spend the majority of the time available for a given project on data cleaning and exploratory analysis, the time available to practitioners to build actual models from data is often rather short due to time constraints for a given project. AutoML systems are currently rising in popularity, as they can build powerful models without human oversight. In this position paper, we aim to discuss the impact of the rising popularity of such systems and how a user-centered interface for such systems could look like. More importantly, we also want to point out features that are currently missing in those systems and start to explore better usability of such systems from a data-scientists perspective.

arXiv:1911.02254

Secure Federated Submodel Learning

Federated learning was proposed with an intriguing vision of achieving collaborative machine learning among numerous clients without uploading their private data to a cloud server. However, the conventional framework requires each client to leverage the full model for learning, which can be prohibitively inefficient for resource-constrained clients and large-scale deep learning tasks. We thus propose a new framework, called federated submodel learning, where clients download only the needed parts of the full model, namely submodels, and then upload the submodel updates. Nevertheless, the "position" of a client's truly required submodel corresponds to her private data, and its disclosure to the cloud server during interactions inevitably breaks the tenet of federated learning. To integrate efficiency and privacy, we have designed a secure federated submodel learning scheme coupled with a private set union protocol as a cornerstone. Our secure scheme features the properties of randomized response, secure aggregation, and Bloom filter, and endows each client with a customized plausible deniability, in terms of local differential privacy, against the position of her desired submodel, thus protecting her private data. We further instantiated our scheme with the e-commerce recommendation scenario in Alibaba, implemented a prototype system, and extensively evaluated its performance over 30-day Taobao user data. The analysis and evaluation results demonstrate the feasibility and scalability of our scheme from model accuracy and convergency, practical communication, computation, and storage overheads, as well as manifest its remarkable advantages over the conventional federated learning framework.

arXiv:1910.13934공식 코드 · Papers with Code

SMS-WSJ: Database, performance measures, and baseline recipe for multi-channel source separation and recognition

We present a multi-channel database of overlapping speech for training, evaluation, and detailed analysis of source separation and extraction algorithms: SMS-WSJ -- Spatialized Multi-Speaker Wall Street Journal. It consists of artificially mixed speech taken from the WSJ database, but unlike earlier databases we consider all WSJ0+1 utterances and take care of strictly separating the speaker sets present in the training, validation and test sets. When spatializing the data we ensure a high degree of randomness w.r.t. room size, array center and rotation, as well as speaker position. Furthermore, this paper offers a critical assessment of recently proposed measures of source separation performance. Alongside the code to generate the database we provide a source separation baseline and a Kaldi recipe with competitive word error rates to provide common ground for evaluation.

arXiv:1910.12122

Estimation of Pelvic Sagittal Inclination from Anteroposterior Radiograph Using Convolutional Neural Networks: Proof-of-Concept Study

Alignment of the bones in standing position provides useful information in surgical planning. In total hip arthroplasty (THA), pelvic sagittal inclination (PSI) angle in the standing position is an important factor in planning of cup alignment and has been estimated mainly from radiographs. Previous methods for PSI estimation used a patient-specific CT to create digitally reconstructed radiographs (DRRs) and compare them with the radiograph to estimate relative position between the pelvis and the x-ray detector. In this study, we developed a method that estimates PSI angle from a single anteroposterior radiograph using two convolutional neural networks (CNNs) without requiring the patient-specific CT, which reduces radiation exposure of the patient and opens up the possibility of application in a larger number of hospitals where CT is not acquired in a routine protocol.

arXiv:1910.12020

D-Point Trigonometric Path Planning based on Q-Learning in Uncertain Environments

Finding the optimum path for a robot for moving from start to the goal position through obstacles is still a challenging issue. This paper presents a novel path planning method, named D-point trigonometric, based on Q-learning algorithm for dynamic and uncertain environments, in which all the obstacles and the target are moving. We define a new state, action and reward functions for the Q-learning by which the agent can find the best action in every state to reach the goal in the most appropriate path. The D-point approach minimizes the possible number of states. Moreover, the experiments in Unity3D confirmed the high convergence speed, the high hit rate, as well as the low dependency on environmental parameters of the proposed method compared with an opponent approach.

arXiv:1910.11147

DCT Maps: Compact Differentiable Lidar Maps Based on the Cosine Transform

Most robot mapping techniques for lidar sensors tessellate the environment into pixels or voxels and assume uniformity of the environment within them. Although intuitive, this representation entails disadvantages: The resulting grid maps exhibit aliasing effects and are not differentiable. In the present paper, we address these drawbacks by introducing a novel mapping technique that does neither rely on tessellation nor on the assumption of piecewise uniformity of the space, without increasing memory requirements. Instead of representing the map in the position domain, we store the map parameters in the discrete frequency domain and leverage the continuous extension of the inverse discrete cosine transform to convert them to a continuously differentiable scalar field in the position domain, which we call DCT map. A DCT map assigns to each point in space a lidar decay rate, which models the local permeability of the space for laser rays. In this way, the map can describe objects of different laser permeabilities, from completely opaque to completely transparent. DCT maps represent lidar measurements significantly more accurate than grid maps, Gaussian process occupancy maps, and Hilbert maps, all with the same memory requirements, as demonstrated in our real-world experiments.

arXiv:1910.10037

One-Shot Template Matching for Automatic Document Data Capture

In this paper, we propose a novel one-shot template-matching algorithm to automatically capture data from business documents with an aim to minimize manual data entry. Given one annotated document, our algorithm can automatically extract similar data from other documents having the same format. Based on a set of engineered visual and textual features, our method is invariant to changes in position and value. Experiments on a dataset of 595 real invoices demonstrate 86.4% accuracy.

arXiv:1910.09441

DeepMNavigate: Deep Reinforced Multi-Robot Navigation Unifying Local & Global Collision Avoidance

We present a novel algorithm (DeepMNavigate) for global multi-agent navigation in dense scenarios using deep reinforcement learning (DRL). Our approach uses local and global information for each robot from motion information maps. We use a three-layer CNN that takes these maps as input to generate a suitable action to drive each robot to its goal position. Our approach is general, learns an optimal policy using a multi-scenario, multi-state training algorithm, and can directly handle raw sensor measurements for local observations. We demonstrate the performance on dense, complex benchmarks with narrow passages and environments with tens of agents. We highlight the algorithm's benefits over prior learning methods and geometric decentralized algorithms in complex scenarios.

arXiv:1910.07254공식 코드 · Papers with Code

Audio-Conditioned U-Net for Position Estimation in Full Sheet Images

The goal of score following is to track a musical performance, usually in the form of audio, in a corresponding score representation. Established methods mainly rely on computer-readable scores in the form of MIDI or MusicXML and achieve robust and reliable tracking results. Recently, multimodal deep learning methods have been used to follow along musical performances in raw sheet images. Among the current limits of these systems is that they require a non trivial amount of preprocessing steps that unravel the raw sheet image into a single long system of staves. The current work is an attempt at removing this particular limitation. We propose an architecture capable of estimating matching score positions directly within entire unprocessed sheet images. We argue that this is a necessary first step towards a fully integrated score following system that does not rely on any preprocessing steps such as optical music recognition.

arXiv:1910.06425

Real-time Data Driven Precision Estimator for RAVEN-II Surgical Robot End Effector Position

Surgical robots have been introduced to operating rooms over the past few decades due to their high sensitivity, small size, and remote controllability. The cable-driven nature of many surgical robots allows the systems to be dexterous and lightweight, with diameters as low as 5mm. However, due to the slack and stretch of the cables and the backlash of the gears, inevitable uncertainties are brought into the kinematics calculation. Since the reported end effector position of surgical robots like RAVEN-II is directly calculated using the motor encoder measurements and forward kinematics, it may contain relatively large error up to 10mm, whereas semi-autonomous functions being introduced into abdominal surgeries require position inaccuracy of at most 1mm. To resolve the problem, a cost-effective, real-time and data-driven pipeline for robot end effector position precision estimation is proposed and tested on RAVEN-II. Analysis shows an improved end effector position error of around 1mm RMS traversing through the entire robot workspace without high-resolution motion tracker.

arXiv:1910.06621

A Method to Generate Synthetically Warped Document Image

The digital camera captured document images may often be warped and distorted due to different camera angles or document surfaces. A robust technique is needed to solve this kind of distortion. The research on dewarping of the document suffers due to the limited availability of benchmark public dataset. In recent times, deep learning based approaches are used to solve the problems accurately. To train most of the deep neural networks a large number of document images is required and generating such a large volume of document images manually is difficult. In this paper, we propose a technique to generate a synthetic warped image from a flat-bedded scanned document image. It is done by calculating warping factors for each pixel position using two warping position parameters (WPP) and eight warping control parameters (WCP). These parameters can be specified as needed depending upon the desired warping. The results are compared with similar real captured images both qualitative and quantitative way.

arXiv:1910.05901

Multi-Stage HRNet: Multiple Stage High-Resolution Network for Human Pose Estimation

Human pose estimation are of importance for visual understanding tasks such as action recognition and human-computer interaction. In this work, we present a Multiple Stage High-Resolution Network (Multi-Stage HRNet) to tackling the problem of multi-person pose estimation in images. Specifically, we follow the top-down pipelines and high-resolution representations are maintained during single-person pose estimation. In addition, multiple stage network and cross stage feature aggregation are adopted to further refine the keypoint position. The resulting approach achieves promising results in COCO datasets. Our single-model-single-scale test configuration obtains 77.1 AP score in test-dev using publicly available training data.

arXiv:1910.06219

ICPS-net: An End-to-End RGB-based Indoor Camera Positioning System using deep convolutional neural networks

Indoor positioning and navigation inside an area with no GPS-data availability is a challenging problem. There are applications such as augmented reality, autonomous driving, navigation of drones inside tunnels, in which indoor positioning gets crucial. In this paper, a tandem architecture of deep network-based systems, for the first time to our knowledge, is developed to address this problem. This structure is trained on the scene images being obtained through scanning of the desired area segments using photogrammetry. A CNN structure based on EfficientNet is trained as a classifier of the scenes, followed by a MobileNet CNN structure which is trained to perform as a regressor. The proposed system achieves amazingly fine precisions for both Cartesian position and Quaternion information of the camera.

arXiv:1910.06205

Variational Tracking and Prediction with Generative Disentangled State-Space Models

We address tracking and prediction of multiple moving objects in visual data streams as inference and sampling in a disentangled latent state-space model. By encoding objects separately and including explicit position information in the latent state space, we perform tracking via amortized variational Bayesian inference of the respective latent positions. Inference is implemented in a modular neural framework tailored towards our disentangled latent space. Generative and inference model are jointly learned from observations only. Comparing to related prior work, we empirically show that our Markovian state-space assumption enables faithful and much improved long-term prediction well beyond the training horizon. Further, our inference model correctly decomposes frames into objects, even in the presence of occlusions. Tracking performance is increased significantly over prior art.

arXiv:1910.03650

Multi-Head Attention for Multi-Modal Joint Vehicle Motion Forecasting

This paper presents a novel vehicle motion forecasting method based on multi-head attention. It produces joint forecasts for all vehicles on a road scene as sequences of multi-modal probability density functions of their positions. Its architecture uses multi-head attention to account for complete interactions between all vehicles, and long short-term memory layers for encoding and forecasting. It relies solely on vehicle position tracks, does not need maneuver definitions, and does not represent the scene with a spatial grid. This allows it to be more versatile than similar model while combining any forecasting capabilities, namely joint forecast with interactions, uncertainty estimation, and multi-modality. The resulting prediction likelihood outperforms state-of-the-art models on the same dataset.

arXiv:1910.01728

Machine learning strategies for path-planning microswimmers in turbulent flows

We develop an adversarial-reinforcement learning scheme for microswimmers in statistically homogeneous and isotropic turbulent fluid flows, in both two (2D) and three dimensions (3D). We show that this scheme allows microswimmers to find non-trivial paths, which enable them to reach a target on average in less time than a naive microswimmer, which tries, at any instant of time and at a given position in space, to swim in the direction of the target. We use pseudospectral direct numerical simulations (DNSs) of the 2D and 3D (incompressible) Navier-Stokes equations to obtain the turbulent flows. We then introduce passive microswimmers that try to swim along a given direction in these flows; the microswimmers do not affect the flow, but they are advected by it.

arXiv:1910.00127

A Mobile Manipulation System for One-Shot Teaching of Complex Tasks in Homes

We describe a mobile manipulation hardware and software system capable of autonomously performing complex human-level tasks in real homes, after being taught the task with a single demonstration from a person in virtual reality. This is enabled by a highly capable mobile manipulation robot, whole-body task space hybrid position/force control, teaching of parameterized primitives linked to a robust learned dense visual embeddings representation of the scene, and a task graph of the taught behaviors. We demonstrate the robustness of the approach by presenting results for performing a variety of tasks, under different environmental conditions, in multiple real homes. Our approach achieves 85% overall success rate on three tasks that consist of an average of 45 behaviors each.

arXiv:1909.12642공식 코드 · Papers with Code

HateMonitors: Language Agnostic Abuse Detection in Social Media

Reducing hateful and offensive content in online social media pose a dual problem for the moderators. On the one hand, rigid censorship on social media cannot be imposed. On the other, the free flow of such content cannot be allowed. Hence, we require efficient abusive language detection system to detect such harmful content in social media. In this paper, we present our machine learning model, HateMonitor, developed for Hate Speech and Offensive Content Identification in Indo-European Languages (HASOC), a shared task at FIRE 2019. We have used a Gradient Boosting model, along with BERT and LASER embeddings, to make the system language agnostic. Our model came at First position for the German sub-task A. We have also made our model public at https://github.com/punyajoy/HateMonitors-HASOC .

arXiv:1909.11313

Determining offshore wind installation times using machine learning and open data

The installation process of offshore wind turbines requires the use of expensive jack-up vessels. These vessels regularly report their position via the Automatic Identification System (AIS). This paper introduces a novel approach of applying machine learning to AIS data from jack-up vessels. We apply the new method to 13 offshore wind farms in Danish, German and British waters. For each of the wind farms we identify individual turbine locations, individual installation times, time in transit and time in harbor for the respective vessel. This is done in an automated way exclusively using AIS data with no prior knowledge of turbine locations, thus enabling a detailed description of the entire installation process.