April 3, 2020

3115 words 15 mins read

Paper Group ANR 69

Paper Group ANR 69

Stochastic Calibration of Radio Interferometers. Optimal least-squares solution to the hand-eye calibration problem. Mask & Focus: Conversation Modelling by Learning Concepts. Automatic Estimation of Sphere Centers from Images of Calibrated Cameras. Multi-frequency calibration for DOA estimation with distributed sensors. On the Role of Dataset Qual …

Stochastic Calibration of Radio Interferometers

Title Stochastic Calibration of Radio Interferometers
Authors Sarod Yatawatta
Abstract With ever increasing data rates produced by modern radio telescopes like LOFAR and future telescopes like the SKA, many data processing steps are overwhelmed by the amount of data that needs to be handled using limited compute resources. Calibration is one such operation that dominates the overall data processing computational cost, nonetheless, it is an essential operation to reach many science goals. Calibration algorithms do exist that scale well with the number of stations of an array and the number of directions being calibrated. However, the remaining bottleneck is the raw data volume, which scales with the number of baselines, and which is proportional to the square of the number of stations. We propose a ‘stochastic’ calibration strategy where we only read in a mini-batch of data for obtaining calibration solutions, as opposed to reading the full batch of data being calibrated. Nonetheless, we obtain solutions that are valid for the full batch of data. Normally, data need to be averaged before calibration is performed to accommodate the data in size-limited compute memory. Stochastic calibration overcomes the need for data averaging before any calibration can be performed, and offers many advantages including: enabling the mitigation of faint radio frequency interference; better removal of strong celestial sources from the data; and better detection and spatial localization of fast radio transients.
Tasks Calibration
Published 2020-03-02
URL https://arxiv.org/abs/2003.00986v2
PDF https://arxiv.org/pdf/2003.00986v2.pdf
PWC https://paperswithcode.com/paper/stochastic-calibration-of-radio
Repo
Framework

Optimal least-squares solution to the hand-eye calibration problem

Title Optimal least-squares solution to the hand-eye calibration problem
Authors Amit Dekel, Linus Härenstam-Nielsen, Sergio Caccamo
Abstract We propose a least-squares formulation to the noisy hand-eye calibration problem using dual-quaternions, and introduce efficient algorithms to find the exact optimal solution, based on analytic properties of the problem, avoiding non-linear optimization. We further present simple analytic approximate solutions which provide remarkably good estimations compared to the exact solution. In addition, we show how to generalize our solution to account for a given extrinsic prior in the cost function. To the best of our knowledge our algorithm is the most efficient approach to optimally solve the hand-eye calibration problem.
Tasks Calibration
Published 2020-02-25
URL https://arxiv.org/abs/2002.10838v1
PDF https://arxiv.org/pdf/2002.10838v1.pdf
PWC https://paperswithcode.com/paper/optimal-least-squares-solution-to-the-hand
Repo
Framework

Mask & Focus: Conversation Modelling by Learning Concepts

Title Mask & Focus: Conversation Modelling by Learning Concepts
Authors Gaurav Pandey, Dinesh Raghu, Sachindra Joshi
Abstract Sequence to sequence models attempt to capture the correlation between all the words in the input and output sequences. While this is quite useful for machine translation where the correlation among the words is indeed quite strong, it becomes problematic for conversation modelling where the correlation is often at a much abstract level. In contrast, humans tend to focus on the essential concepts discussed in the conversation context and generate responses accordingly. In this paper, we attempt to mimic this response generating mechanism by learning the essential concepts in the context and response in an unsupervised manner. The proposed model, referred to as Mask & Focus maps the input context to a sequence of concepts which are then used to generate the response concepts. Together, the context and the response concepts generate the final response. In order to learn context concepts from the training data automatically, we \emph{mask} words in the input and observe the effect of masking on response generation. We train our model to learn those response concepts that have high mutual information with respect to the context concepts, thereby guiding the model to \emph{focus} on the context concepts. Mask & Focus achieves significant improvement over the existing baselines in several established metrics for dialogues.
Tasks Machine Translation
Published 2020-02-11
URL https://arxiv.org/abs/2003.04976v1
PDF https://arxiv.org/pdf/2003.04976v1.pdf
PWC https://paperswithcode.com/paper/mask-focus-conversation-modelling-by-learning
Repo
Framework

Automatic Estimation of Sphere Centers from Images of Calibrated Cameras

Title Automatic Estimation of Sphere Centers from Images of Calibrated Cameras
Authors Levente Hajder, Tekla Tóth, Zoltán Pusztai
Abstract Calibration of devices with different modalities is a key problem in robotic vision. Regular spatial objects, such as planes, are frequently used for this task. This paper deals with the automatic detection of ellipses in camera images, as well as to estimate the 3D position of the spheres corresponding to the detected 2D ellipses. We propose two novel methods to (i) detect an ellipse in camera images and (ii) estimate the spatial location of the corresponding sphere if its size is known. The algorithms are tested both quantitatively and qualitatively. They are applied for calibrating the sensor system of autonomous cars equipped with digital cameras, depth sensors and LiDAR devices.
Tasks Calibration
Published 2020-02-24
URL https://arxiv.org/abs/2002.10217v1
PDF https://arxiv.org/pdf/2002.10217v1.pdf
PWC https://paperswithcode.com/paper/automatic-estimation-of-sphere-centers-from
Repo
Framework

Multi-frequency calibration for DOA estimation with distributed sensors

Title Multi-frequency calibration for DOA estimation with distributed sensors
Authors Martin Brossard, Virginie Ollier, Mohammed Nabil El Korso, Rémy Boyer, Pascal Larzabal
Abstract In this work, we investigate direction finding in the presence of sensor gain uncertainties and directional perturbations for sensor array processing in a multi-frequency scenario. Specifically, we adopt a distributed optimization scheme in which coherence models are incorporated and local agents exchange information only between connected nodes in the network, i.e., without a fusion center. Numerical simulations highlight the advantages of the proposed parallel iterative technique in terms of statistical and computational efficiency.
Tasks Calibration, Distributed Optimization
Published 2020-02-24
URL https://arxiv.org/abs/2002.11498v1
PDF https://arxiv.org/pdf/2002.11498v1.pdf
PWC https://paperswithcode.com/paper/multi-frequency-calibration-for-doa
Repo
Framework

On the Role of Dataset Quality and Heterogeneity in Model Confidence

Title On the Role of Dataset Quality and Heterogeneity in Model Confidence
Authors Yuan Zhao, Jiasi Chen, Samet Oymak
Abstract Safety-critical applications require machine learning models that output accurate and calibrated probabilities. While uncalibrated deep networks are known to make over-confident predictions, it is unclear how model confidence is impacted by the variations in the data, such as label noise or class size. In this paper, we investigate the role of the dataset quality by studying the impact of dataset size and the label noise on the model confidence. We theoretically explain and experimentally demonstrate that, surprisingly, label noise in the training data leads to under-confident networks, while reduced dataset size leads to over-confident models. We then study the impact of dataset heterogeneity, where data quality varies across classes, on model confidence. We demonstrate that this leads to heterogenous confidence/accuracy behavior in the test data and is poorly handled by the standard calibration algorithms. To overcome this, we propose an intuitive heterogenous calibration technique and show that the proposed approach leads to improved calibration metrics (both average and worst-case errors) on the CIFAR datasets.
Tasks Calibration
Published 2020-02-23
URL https://arxiv.org/abs/2002.09831v1
PDF https://arxiv.org/pdf/2002.09831v1.pdf
PWC https://paperswithcode.com/paper/on-the-role-of-dataset-quality-and
Repo
Framework

Learning Precise 3D Manipulation from Multiple Uncalibrated Cameras

Title Learning Precise 3D Manipulation from Multiple Uncalibrated Cameras
Authors Iretiayo Akinola, Jacob Varley, Dmitry Kalashnikov
Abstract In this work, we present an effective multi-view approach to closed-loop end-to-end learning of precise manipulation tasks that are 3D in nature. Our method learns to accomplish these tasks using multiple statically placed but uncalibrated RGB camera views without building an explicit 3D representation such as a pointcloud or voxel grid. This multi-camera approach achieves superior task performance on difficult stacking and insertion tasks compared to single-view baselines. Single view robotic agents struggle from occlusion and challenges in estimating relative poses between points of interest. While full 3D scene representations (voxels or pointclouds) are obtainable from registered output of multiple depth sensors, several challenges complicate operating off such explicit 3D representations. These challenges include imperfect camera calibration, poor depth maps due to object properties such as reflective surfaces, and slower inference speeds over 3D representations compared to 2D images. Our use of static but uncalibrated cameras does not require camera-robot or camera-camera calibration making the proposed approach easy to setup and our use of \textit{sensor dropout} during training makes it resilient to the loss of camera-views after deployment.
Tasks Calibration
Published 2020-02-21
URL https://arxiv.org/abs/2002.09107v1
PDF https://arxiv.org/pdf/2002.09107v1.pdf
PWC https://paperswithcode.com/paper/learning-precise-3d-manipulation-from
Repo
Framework

Few-Shot Graph Classification with Model Agnostic Meta-Learning

Title Few-Shot Graph Classification with Model Agnostic Meta-Learning
Authors Ning Ma, Jiajun Bu, Jieyu Yang, Zhen Zhang, Chengwei Yao, Zhi Yu
Abstract Graph classification aims to perform accurate information extraction and classification over graphstructured data. In the past few years, Graph Neural Networks (GNNs) have achieved satisfactory performance on graph classification tasks. However, most GNNs based methods focus on designing graph convolutional operations and graph pooling operations, overlooking that collecting or labeling graph-structured data is more difficult than grid-based data. We utilize meta-learning for fewshot graph classification to alleviate the scarce of labeled graph samples when training new tasks.More specifically, to boost the learning of graph classification tasks, we leverage GNNs as graph embedding backbone and meta-learning as training paradigm to capture task-specific knowledge rapidly in graph classification tasks and transfer them to new tasks. To enhance the robustness of meta-learner, we designed a novel step controller driven by Reinforcement Learning. The experiments demonstrate that our framework works well compared to baselines.
Tasks Graph Classification, Graph Embedding, Meta-Learning
Published 2020-03-18
URL https://arxiv.org/abs/2003.08246v1
PDF https://arxiv.org/pdf/2003.08246v1.pdf
PWC https://paperswithcode.com/paper/few-shot-graph-classification-with-model
Repo
Framework

The Mimicry Game: Towards Self-recognition in Chatbots

Title The Mimicry Game: Towards Self-recognition in Chatbots
Authors Yigit Oktar, Erdem Okur, Mehmet Turkan
Abstract In standard Turing test, a machine has to prove its humanness to the judges. By successfully imitating a thinking entity such as a human, this machine then proves that it can also think. However, many objections are raised against the validity of this argument. Such objections claim that Turing test is not a tool to demonstrate existence of general intelligence or thinking activity. In this light, alternatives to Turing test are to be investigated. Self-recognition tests applied on animals through mirrors appear to be a viable alternative to demonstrate the existence of a type of general intelligence. Methodology here constructs a textual version of the mirror test by placing the chatbot (in this context) as the one and only judge to figure out whether the contacted one is an other, a mimicker, or oneself in an unsupervised manner. This textual version of the mirror test is objective, self-contained, and is mostly immune to objections raised against the Turing test. Any chatbot passing this textual mirror test should have or acquire a thought mechanism that can be referred to as the inner-voice, answering the original and long lasting question of Turing “Can machines think?” in a constructive manner.
Tasks Chatbot
Published 2020-02-06
URL https://arxiv.org/abs/2002.02334v1
PDF https://arxiv.org/pdf/2002.02334v1.pdf
PWC https://paperswithcode.com/paper/the-mimicry-game-towards-self-recognition-in
Repo
Framework

LRC-Net: Learning Discriminative Features on Point Clouds by Encoding Local Region Contexts

Title LRC-Net: Learning Discriminative Features on Point Clouds by Encoding Local Region Contexts
Authors Xinhai Liu, Zhizhong Han, Fangzhou Hong, Yu-Shen Liu, Matthias Zwicker
Abstract Learning discriminative feature directly on point clouds is still challenging in the understanding of 3D shapes. Recent methods usually partition point clouds into local region sets, and then extract the local region features with fixed-size CNN or MLP, and finally aggregate all individual local features into a global feature using simple max pooling. However, due to the irregularity and sparsity in sampled point clouds, it is hard to encode the fine-grained geometry of local regions and their spatial relationships when only using the fixed-size filters and individual local feature integration, which limit the ability to learn discriminative features. To address this issue, we present a novel Local-Region-Context Network (LRC-Net), to learn discriminative features on point clouds by encoding the fine-grained contexts inside and among local regions simultaneously. LRC-Net consists of two main modules. The first module, named intra-region context encoding, is designed for capturing the geometric correlation inside each local region by novel variable-size convolution filter. The second module, named inter-region context encoding, is proposed for integrating the spatial relationships among local regions based on spatial similarity measures. Experimental results show that LRC-Net is competitive with state-of-the-art methods in shape classification and shape segmentation applications.
Tasks
Published 2020-03-18
URL https://arxiv.org/abs/2003.08240v2
PDF https://arxiv.org/pdf/2003.08240v2.pdf
PWC https://paperswithcode.com/paper/lrc-net-learning-discriminative-features-on
Repo
Framework
Title Modal Regression based Structured Low-rank Matrix Recovery for Multi-view Learning
Authors Jiamiao Xu, Fangzhao Wang, Qinmu Peng, Xinge You, Shuo Wang, Xiao-Yuan Jing, C. L. Philip Chen
Abstract Low-rank Multi-view Subspace Learning (LMvSL) has shown great potential in cross-view classification in recent years. Despite their empirical success, existing LMvSL based methods are incapable of well handling view discrepancy and discriminancy simultaneously, which thus leads to the performance degradation when there is a large discrepancy among multi-view data. To circumvent this drawback, motivated by the block-diagonal representation learning, we propose Structured Low-rank Matrix Recovery (SLMR), a unique method of effectively removing view discrepancy and improving discriminancy through the recovery of structured low-rank matrix. Furthermore, recent low-rank modeling provides a satisfactory solution to address data contaminated by predefined assumptions of noise distribution, such as Gaussian or Laplacian distribution. However, these models are not practical since complicated noise in practice may violate those assumptions and the distribution is generally unknown in advance. To alleviate such limitation, modal regression is elegantly incorporated into the framework of SLMR (term it MR-SLMR). Different from previous LMvSL based methods, our MR-SLMR can handle any zero-mode noise variable that contains a wide range of noise, such as Gaussian noise, random noise and outliers. The alternating direction method of multipliers (ADMM) framework and half-quadratic theory are used to efficiently optimize MR-SLMR. Experimental results on four public databases demonstrate the superiority of MR-SLMR and its robustness to complicated noise.
Tasks MULTI-VIEW LEARNING, Representation Learning
Published 2020-03-22
URL https://arxiv.org/abs/2003.09799v1
PDF https://arxiv.org/pdf/2003.09799v1.pdf
PWC https://paperswithcode.com/paper/modal-regression-based-structured-low-rank
Repo
Framework

Variational Inference for Deep Probabilistic Canonical Correlation Analysis

Title Variational Inference for Deep Probabilistic Canonical Correlation Analysis
Authors Mahdi Karami, Dale Schuurmans
Abstract In this paper, we propose a deep probabilistic multi-view model that is composed of a linear multi-view layer based on probabilistic canonical correlation analysis (CCA) description in the latent space together with deep generative networks as observation models. The network is designed to decompose the variations of all views into a shared latent representation and a set of view-specific components where the shared latent representation is intended to describe the common underlying sources of variation among the views. An efficient variational inference procedure is developed that approximates the posterior distributions of the latent probabilistic multi-view layer while taking into account the solution of probabilistic CCA. A generalization to models with arbitrary number of views is also proposed. The empirical studies confirm that the proposed deep generative multi-view model can successfully extend deep variational inference to multi-view learning while it efficiently integrates the relationship between multiple views to alleviate the difficulty of learning.
Tasks MULTI-VIEW LEARNING
Published 2020-03-09
URL https://arxiv.org/abs/2003.04292v1
PDF https://arxiv.org/pdf/2003.04292v1.pdf
PWC https://paperswithcode.com/paper/variational-inference-for-deep-probabilistic
Repo
Framework

Multi-View Learning for Vision-and-Language Navigation

Title Multi-View Learning for Vision-and-Language Navigation
Authors Qiaolin Xia, Xiujun Li, Chunyuan Li, Yonatan Bisk, Zhifang Sui, Jianfeng Gao, Yejin Choi, Noah A. Smith
Abstract Learning to navigate in a visual environment following natural language instructions is a challenging task because natural language instructions are highly variable, ambiguous, and under-specified. In this paper, we present a novel training paradigm, Learn from EveryOne (LEO), which leverages multiple instructions (as different views) for the same trajectory to resolve language ambiguity and improve generalization. By sharing parameters across instructions, our approach learns more effectively from limited training data and generalizes better in unseen environments. On the recent Room-to-Room (R2R) benchmark dataset, LEO achieves 16% improvement (absolute) over a greedy agent as the base agent (25.3% $\rightarrow$ 41.4%) in Success Rate weighted by Path Length (SPL). Further, LEO is complementary to most existing models for vision-and-language navigation, allowing for easy integration with the existing techniques, leading to LEO+, which creates the new state of the art, pushing the R2R benchmark to 62% (9% absolute improvement).
Tasks MULTI-VIEW LEARNING
Published 2020-03-02
URL https://arxiv.org/abs/2003.00857v3
PDF https://arxiv.org/pdf/2003.00857v3.pdf
PWC https://paperswithcode.com/paper/multi-view-learning-for-vision-and-language
Repo
Framework

A Multi-view Perspective of Self-supervised Learning

Title A Multi-view Perspective of Self-supervised Learning
Authors Chuanxing Geng, Zhenghao Tan, Songcan Chen
Abstract As a newly emerging unsupervised learning paradigm, self-supervised learning (SSL) recently gained widespread attention, which usually introduces a pretext task without manual annotation of data. With its help, SSL effectively learns the feature representation beneficial for downstream tasks. Thus the pretext task plays a key role. However, the study of its design, especially its essence currently is still open. In this paper, we borrow a multi-view perspective to decouple a class of popular pretext tasks into a combination of view data augmentation (VDA) and view label classification (VLC), where we attempt to explore the essence of such pretext task while providing some insights into its design. Specifically, a simple multi-view learning framework is specially designed (SSL-MV), which assists the feature learning of downstream tasks (original view) through the same tasks on the augmented views. SSL-MV focuses on VDA while abandons VLC, empirically uncovering that it is VDA rather than generally considered VLC that dominates the performance of such SSL. Additionally, thanks to replacing VLC with VDA tasks, SSL-MV also enables an integrated inference combining the predictions from the augmented views, further improving the performance. Experiments on several benchmark datasets demonstrate its advantages.
Tasks Data Augmentation, MULTI-VIEW LEARNING
Published 2020-02-22
URL https://arxiv.org/abs/2003.00877v1
PDF https://arxiv.org/pdf/2003.00877v1.pdf
PWC https://paperswithcode.com/paper/a-multi-view-perspective-of-self-supervised
Repo
Framework

Incremental Learning for Metric-Based Meta-Learners

Title Incremental Learning for Metric-Based Meta-Learners
Authors Qing Liu, Orchid Majumder, Avinash Ravichandran, Rahul Bhotika, Stefano Soatto
Abstract Majority of the modern meta-learning methods for few-shot classification tasks operate in two phases: a meta-training phase where the meta-learner learns a generic representation by solving multiple few-shot tasks sampled from a large dataset and a testing phase, where the meta-learner leverages its learnt internal representation for a specific few-shot task involving classes which were not seen during the meta-training phase. To the best of our knowledge, all such meta-learning methods use a single base dataset for meta-training to sample tasks from and do not adapt the algorithm after meta-training. This strategy may not scale to real-world use-cases where the meta-learner does not potentially have access to the full meta-training dataset from the very beginning and we need to update the meta-learner in an incremental fashion when additional training data becomes available. Through our experimental setup, we develop a notion of incremental learning during the meta-training phase of meta-learning and propose a method which can be used with multiple existing metric-based meta-learning algorithms. Experimental results on benchmark dataset show that our approach performs favorably at test time as compared to training a model with the full meta-training set and incurs negligible amount of catastrophic forgetting
Tasks Meta-Learning
Published 2020-02-11
URL https://arxiv.org/abs/2002.04162v1
PDF https://arxiv.org/pdf/2002.04162v1.pdf
PWC https://paperswithcode.com/paper/incremental-learning-for-metric-based-meta
Repo
Framework
comments powered by Disqus