arXiv subjects

Boris N. Oreshkin

Publications and source records attributed to Boris N. Oreshkin.

34 records · Page 2Linked to original sources

arXiv2020

Adaptive filters for the moving target indicator system

Adaptive algorithms belong to an important class of algorithms used in radar target detection to overcome prior uncertainty of interference covariance. The contamination of the empirical covariance matrix by the useful signal leads to significant degradation of performance of this class of adaptive algorithms. Regularization, also known in radar literature as sample covariance loading, can be used to combat both ill conditioning of the original problem and contamination of the empirical covariance by the desired signal for the adaptive algorithms based on sample covariance matrix inversion. However, the optimum value of loading factor cannot be derived unless strong assumptions are made regarding the structure of covariance matrix and useful signal penetration model. Similarly, least mean square algorithm with linear constraint or without constraint, is also sensitive to the contamination of the learning sample with the target signal. We synthesize two approaches to improve the convergence of adaptive algorithms and protect them from the contamination of the learning sample with the signal from the target. The proposed approach is based on the maximization of empirical signal to interference plus noise ratio (SINR). Its effectiveness is demonstrated using simulated data.

eess.SP↗

arXiv2020

Meta-learning framework with applications to zero-shot time-series forecasting

Can meta-learning discover generic ways of processing time series (TS) from a diverse dataset so as to greatly improve generalization on new TS coming from different datasets? This work provides positive evidence to this using a broad meta-learning framework which we show subsumes many existing meta-learning algorithms. Our theoretical analysis suggests that residual connections act as a meta-learning adaptation mechanism, generating a subset of task-specific parameters based on a given TS input, thus gradually expanding the expressive power of the architecture on-the-fly. The same mechanism is shown via linearization analysis to have the interpretation of a sequential update of the final linear layer. Our empirical results on a wide range of data emphasize the importance of the identified meta-learning mechanisms for successful zero-shot univariate forecasting, suggesting that it is viable to train a neural network on a source TS dataset and deploy it on a different target TS dataset without retraining, resulting in performance that is at least as good as that of state-of-practice univariate forecasting models.

cs.LG↗

arXiv2020

FC-GAGA: Fully Connected Gated Graph Architecture for Spatio-Temporal Traffic Forecasting

Forecasting of multivariate time-series is an important problem that has applications in traffic management, cellular network configuration, and quantitative finance. A special case of the problem arises when there is a graph available that captures the relationships between the time-series. In this paper we propose a novel learning architecture that achieves performance competitive with or better than the best existing algorithms, without requiring knowledge of the graph. The key element of our proposed architecture is the learnable fully connected hard graph gating mechanism that enables the use of the state-of-the-art and highly computationally efficient fully connected time-series forecasting architecture in traffic forecasting applications. Experimental results for two public traffic network datasets illustrate the value of our approach, and ablation studies confirm the importance of each element of the architecture. The code is available here: https://github.com/boreshkinai/fc-gaga.

cs.LG↗

arXiv2020

Optimization of loading factor preventing target cancellation

Adaptive algorithms based on sample matrix inversion belong to an important class of algorithms used in radar target detection to overcome prior uncertainty of interference covariance. Sample matrix inversion problem is generally ill conditioned. Moreover, the contamination of the empirical covariance matrix by the useful signal leads to significant degradation of performance of this class of adaptive algorithms. Regularization, also known in radar literature as sample covariance loading, can be used to combat both ill conditioning of the original problem and contamination of the empirical covariance by the desired signal. However, the optimum value of loading factor cannot be derived unless strong assumptions are made regarding the structure of covariance matrix and useful signal penetration model. In this paper an iterative algorithm for loading factor optimization based on the maximization of empirical signal to interference plus noise ratio (SINR) is proposed. The proposed solution does not rely on any assumptions regarding the structure of empirical covariance matrix and signal penetration model. The paper also presents simulation examples showing the effectiveness of the proposed solution.

eess.SP↗

arXiv2020

Optimization over Random and Gradient Probabilistic Pixel Sampling for Fast, Robust Multi-Resolution Image Registration

This paper presents an approach to fast image registration through probabilistic pixel sampling. We propose a practical scheme to leverage the benefits of two state-of-the-art pixel sampling approaches: gradient magnitude based pixel sampling and uniformly random sampling. Our framework involves learning the optimal balance between the two sampling schemes off-line during training, based on a small training dataset, using particle swarm optimization. We then test the proposed sampling approach on 3D rigid registration against two state-of-the-art approaches based on the popular, publicly available, Vanderbilt RIRE dataset. Our results indicate that the proposed sampling approach yields much faster, accurate and robust registration results when compared against the state-of-the-art.

cs.CV↗

arXiv2020

Uncertainty driven probabilistic voxel selection for image registration

This paper presents a novel probabilistic voxel selection strategy for medical image registration in time-sensitive contexts, where the goal is aggressive voxel sampling (e.g. using less than 1% of the total number) while maintaining registration accuracy and low failure rate. We develop a Bayesian framework whereby, first, a voxel sampling probability field (VSPF) is built based on the uncertainty on the transformation parameters. We then describe a practical, multi-scale registration algorithm, where, at each optimization iteration, different voxel subsets are sampled based on the VSPF. The approach maximizes accuracy without committing to a particular fixed subset of voxels. The probabilistic sampling scheme developed is shown to manage the tradeoff between the robustness of traditional random voxel selection (by permitting more exploration) and the accuracy of fixed voxel selection (by permitting a greater proportion of informative voxels).

cs.CV↗

arXiv2020

Weakly Supervised Few-shot Object Segmentation using Co-Attention with Visual and Semantic Embeddings

Significant progress has been made recently in developing few-shot object segmentation methods. Learning is shown to be successful in few-shot segmentation settings, using pixel-level, scribbles and bounding box supervision. This paper takes another approach, i.e., only requiring image-level label for few-shot object segmentation. We propose a novel multi-modal interaction module for few-shot object segmentation that utilizes a co-attention mechanism using both visual and word embedding. Our model using image-level labels achieves 4.8% improvement over previously proposed image-level few-shot object segmentation. It also outperforms state-of-the-art methods that use weak bounding box supervision on PASCAL-5i. Our results show that few-shot segmentation benefits from utilizing word embeddings, and that we are able to perform few-shot segmentation using stacked joint visual semantic processing with weak image-level labels. We further propose a novel setup, Temporal Object Segmentation for Few-shot Learning (TOSFL) for videos. TOSFL can be used on a variety of public video data such as Youtube-VOS, as demonstrated in both instance-level and category-level TOSFL experiments.

cs.CV↗

arXiv2020

CLAREL: Classification via retrieval loss for zero-shot learning

We address the problem of learning fine-grained cross-modal representations. We propose an instance-based deep metric learning approach in joint visual and textual space. The key novelty of this paper is that it shows that using per-image semantic supervision leads to substantial improvement in zero-shot performance over using class-only supervision. On top of that, we provide a probabilistic justification for a metric rescaling approach that solves a very common problem in the generalized zero-shot learning setting, i.e., classifying test images from unseen classes as one of the classes seen during training. We evaluate our approach on two fine-grained zero-shot learning datasets: CUB and FLOWERS. We find that on the generalized zero-shot classification task CLAREL consistently outperforms the existing approaches on both datasets.

cs.CV↗

arXiv2020

N-BEATS: Neural basis expansion analysis for interpretable time series forecasting

We focus on solving the univariate times series point forecasting problem using deep learning. We propose a deep neural architecture based on backward and forward residual links and a very deep stack of fully-connected layers. The architecture has a number of desirable properties, being interpretable, applicable without modification to a wide array of target domains, and fast to train. We test the proposed architecture on several well-known datasets, including M3, M4 and TOURISM competition datasets containing time series from diverse domains. We demonstrate state-of-the-art performance for two configurations of N-BEATS for all the datasets, improving forecast accuracy by 11% over a statistical benchmark and by 3% over last year's winner of the M4 competition, a domain-adjusted hand-crafted hybrid between neural network and statistical time series models. The first configuration of our model does not employ any time-series-specific components and its performance on heterogeneous datasets strongly suggests that, contrarily to received wisdom, deep learning primitives such as residual blocks are by themselves sufficient to solve a wide range of forecasting problems. Finally, we demonstrate how the proposed architecture can be augmented to provide outputs that are interpretable without considerable loss in accuracy.

cs.LG↗

arXiv2020

Adaptive Cross-Modal Few-Shot Learning

Metric-based meta-learning techniques have successfully been applied to few-shot classification problems. In this paper, we propose to leverage cross-modal information to enhance metric-based few-shot learning methods. Visual and semantic feature spaces have different structures by definition. For certain concepts, visual features might be richer and more discriminative than text ones. While for others, the inverse might be true. Moreover, when the support from visual information is limited in image classification, semantic representations (learned from unsupervised text corpora) can provide strong prior knowledge and context to help learning. Based on these two intuitions, we propose a mechanism that can adaptively combine information from both modalities according to new image categories to be learned. Through a series of experiments, we show that by this adaptive combination of the two modalities, our model outperforms current uni-modality few-shot learning methods and modality-alignment methods by a large margin on all benchmarks and few-shot scenarios tested. Experiments also show that our model can effectively adjust its focus on the two modalities. The improvement in performance is particularly large when the number of shots is very small.

cs.LG↗

arXiv2019

One-Shot Weakly Supervised Video Object Segmentation

Conventional few-shot object segmentation methods learn object segmentation from a few labelled support images with strongly labelled segmentation masks. Recent work has shown to perform on par with weaker levels of supervision in terms of scribbles and bounding boxes. However, there has been limited attention given to the problem of few-shot object segmentation with image-level supervision. We propose a novel multi-modal interaction module for few-shot object segmentation that utilizes a co-attention mechanism using both visual and word embeddings. It enables our model to achieve 5.1% improvement over previously proposed image-level few-shot object segmentation. Our method compares relatively close to the state of the art methods that use strong supervision, while ours use the least possible supervision. We further propose a novel setup for few-shot weakly supervised video object segmentation(VOS) that relies on image-level labels for the first frame. The proposed setup uses weak annotation unlike semi-supervised VOS setting that utilizes strongly labelled segmentation masks. The setup evaluates the effectiveness of generalizing to novel classes in the VOS setting. The setup splits the VOS data into multiple folds with different categories per fold. It provides a potential setup to evaluate how few-shot object segmentation methods can benefit from additional object poses, or object interactions that is not available in static frames as in PASCAL-5i benchmark.

cs.CV↗

arXiv2019

TADAM: Task dependent adaptive metric for improved few-shot learning

Few-shot learning has become essential for producing models that generalize from few examples. In this work, we identify that metric scaling and metric task conditioning are important to improve the performance of few-shot algorithms. Our analysis reveals that simple metric scaling completely changes the nature of few-shot algorithm parameter updates. Metric scaling provides improvements up to 14% in accuracy for certain metrics on the mini-Imagenet 5-way 5-shot classification task. We further propose a simple and effective way of conditioning a learner on the task sample set, resulting in learning a task-dependent metric space. Moreover, we propose and empirically test a practical end-to-end optimization procedure based on auxiliary task co-training to learn a task-dependent metric space. The resulting few-shot learning model based on the task-dependent scaled metric achieves state of the art on mini-Imagenet. We confirm these results on another few-shot dataset that we introduce in this paper based on CIFAR100. Our code is publicly available at https://github.com/ElementAI/TADAM.

cs.LG↗

arXiv2013

Sensor fusion for bimodal generalized likelihood ratio test with unknown noise variances

In this paper we address the problem of sensor fusion. We formulate the joint detection problem using a general linear observation model and inter-modality independence assumption for noises. We derive the fusion architecture based on the generalized likelihood ratio principle and calculate the expressions for the distributions of the test statistic under the signal present and the null hypotheses. To obtain these results we develop a methodology for the joint detection algorithm analysis based on the theory of the Meijer G-function.

math.ST↗

arXiv2012

Analysis of error propagation in particle filters with approximation

This paper examines the impact of approximation steps that become necessary when particle filters are implemented on resource-constrained platforms. We consider particle filters that perform intermittent approximation, either by subsampling the particles or by generating a parametric approximation. For such algorithms, we derive time-uniform bounds on the weak-sense $L_p$ error and present associated exponential inequalities. We motivate the theoretical analysis by considering the leader node particle filter and present numerical experiments exploring its performance and the relationship to the error bounds.

math.PR↗

arXiv2010

Efficient delay-tolerant particle filtering

This paper proposes a novel framework for delay-tolerant particle filtering that is computationally efficient and has limited memory requirements. Within this framework the informativeness of a delayed (out-of-sequence) measurement (OOSM) is estimated using a lightweight procedure and uninformative measurements are immediately discarded. The framework requires the identification of a threshold that separates informative from uninformative; this threshold selection task is formulated as a constrained optimization problem, where the goal is to minimize tracking error whilst controlling the computational requirements. We develop an algorithm that provides an approximate solution for the optimization problem. Simulation experiments provide an example where the proposed framework processes less than 40% of all OOSMs with only a small reduction in tracking accuracy.

stat.AP↗

arXiv2010

Optimization and Analysis of Distributed Averaging with Short Node Memory

In this paper, we demonstrate, both theoretically and by numerical examples, that adding a local prediction component to the update rule can significantly improve the convergence rate of distributed averaging algorithms. We focus on the case where the local predictor is a linear combination of the node's two previous values (i.e., two memory taps), and our update rule computes a combination of the predictor and the usual weighted linear combination of values received from neighbouring nodes. We derive the optimal mixing parameter for combining the predictor with the neighbors' values, and carry out a theoretical analysis of the improvement in convergence rate that can be obtained using this acceleration methodology. For a chain topology on n nodes, this leads to a factor of n improvement over the one-step algorithm, and for a two-dimensional grid, our approach achieves a factor of n^1/2 improvement, in terms of the number of iterations required to reach a prescribed level of accuracy.

cs.DC↗