Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

"Topic": models, code, and papers

Sparsity assisted solution to the twin image problem in phase retrieval

Jul 13, 2015
Charu Gaur, Baranidharan Mohan, Kedar Khare

The iterative phase retrieval problem for complex-valued objects from Fourier transform magnitude data is known to suffer from the twin image problem. In particular, when the object support is centro-symmetric, the iterative solution often stagnates such that the resultant complex image contains the features of both the desired solution and its inverted and complex-conjugated replica. The conventional approach to address the twin image problem is to modify the object support during initial iterations which can possibly lead to elimination of one of the twin images. However, at present there seems to be no deterministic procedure to make sure that the twin image will always be very weak or absent. In this work we make an important observation that the ideal solution without the twin image is typically more sparse (in some suitable transform domain) as compared to the stagnated solution containing the twin image. We further show that introducing a sparsity enhancing step in the iterative algorithm can address the twin image problem without the need to change the object support throughout the iterative process even when the object support is centro-symmetric. In a simulation study, we use binary and gray-scale pure phase objects and illustrate the effectiveness of the sparsity assisted phase recovery in the context of the twin image problem. The results have important implications for a wide range of topics in Physics where the phase retrieval problem plays a central role.


  Access Paper or Ask Questions

Image Super-Resolution via Sparse Bayesian Modeling of Natural Images

Sep 19, 2012
Haichao Zhang, David Wipf, Yanning Zhang

Image super-resolution (SR) is one of the long-standing and active topics in image processing community. A large body of works for image super resolution formulate the problem with Bayesian modeling techniques and then obtain its Maximum-A-Posteriori (MAP) solution, which actually boils down to a regularized regression task over separable regularization term. Although straightforward, this approach cannot exploit the full potential offered by the probabilistic modeling, as only the posterior mode is sought. Also, the separable property of the regularization term can not capture any correlations between the sparse coefficients, which sacrifices much on its modeling accuracy. We propose a Bayesian image SR algorithm via sparse modeling of natural images. The sparsity property of the latent high resolution image is exploited by introducing latent variables into the high-order Markov Random Field (MRF) which capture the content adaptive variance by pixel-wise adaptation. The high-resolution image is estimated via Empirical Bayesian estimation scheme, which is substantially faster than our previous approach based on Markov Chain Monte Carlo sampling [1]. It is shown that the actual cost function for the proposed approach actually incorporates a non-factorial regularization term over the sparse coefficients. Experimental results indicate that the proposed method can generate competitive or better results than \emph{state-of-the-art} SR algorithms.

* 8 figures, 29 pages 

  Access Paper or Ask Questions

A review of path following control strategies for autonomous robotic vehicles: theory, simulations, and experiments

Apr 15, 2022
Nguyen Hung, Francisco Rego, Joao Quintas, Joao Cruz, Marcelo Jacinto, David Souto, Andre Potes, Luis Sebastiao, Antonio Pascoal

This article presents an in-depth review of the topic of path following for autonomous robotic vehicles, with a specific focus on vehicle motion in two dimensional space (2D). From a control system standpoint, path following can be formulated as the problem of stabilizing a path following error system that describes the dynamics of position and possibly orientation errors of a vehicle with respect to a path, with the errors defined in an appropriate reference frame. In spite of the large variety of path following methods described in the literature we show that, in principle, most of them can be categorized in two groups: stabilization of the path following error system expressed either in the vehicle's body frame or in a frame attached to a "reference point" moving along the path, such as a Frenet-Serret (F-S) frame or a Parallel Transport (P-T) frame. With this observation, we provide a unified formulation that is simple but general enough to cover many methods available in the literature. We then discuss the advantages and disadvantages of each method, comparing them from the design and implementation standpoint. We further show experimental results of the path following methods obtained from field trials testing with under-actuated and fully-actuated autonomous marine vehicles. In addition, we introduce open-source Matlab and Gazebo/ROS simulation toolboxes that are helpful in testing path following methods prior to their integration in the combined guidance, navigation, and control systems of autonomous vehicles.


  Access Paper or Ask Questions

Steady-State Error Compensation in Reference Tracking and Disturbance Rejection Problems for Reinforcement Learning-Based Control

Jan 31, 2022
Daniel Weber, Maximilian Schenke, Oliver Wallscheid

Reinforcement learning (RL) is a promising, upcoming topic in automatic control applications. Where classical control approaches require a priori system knowledge, data-driven control approaches like RL allow a model-free controller design procedure, rendering them emergent techniques for systems with changing plant structures and varying parameters. While it was already shown in various applications that the transient control behavior for complex systems can be sufficiently handled by RL, the challenge of non-vanishing steady-state control errors remains, which arises from the usage of control policy approximations and finite training times. To overcome this issue, an integral action state augmentation (IASA) for actor-critic-based RL controllers is introduced that mimics an integrating feedback, which is inspired by the delta-input formulation within model predictive control. This augmentation does not require any expert knowledge, leaving the approach model free. As a result, the RL controller learns how to suppress steady-state control deviations much more effectively. Two exemplary applications from the domain of electrical energy engineering validate the benefit of the developed method both for reference tracking and disturbance rejection. In comparison to a standard deep deterministic policy gradient (DDPG) setup, the suggested IASA extension allows to reduce the steady-state error by up to 52 $\%$ within the considered validation scenarios.


  Access Paper or Ask Questions

Zero-Shot Cross-Lingual Transfer in Legal Domain Using Transformer Models

Dec 11, 2021
Zein Shaheen, Gerhard Wohlgenannt, Dmitry Mouromtsev

Zero-shot cross-lingual transfer is an important feature in modern NLP models and architectures to support low-resource languages. In this work, We study zero-shot cross-lingual transfer from English to French and German under Multi-Label Text Classification, where we train a classifier using English training set, and we test using French and German test sets. We extend EURLEX57K dataset, the English dataset for topic classification of legal documents, with French and German official translation. We investigate the effect of using some training techniques, namely Gradual Unfreezing and Language Model finetuning, on the quality of zero-shot cross-lingual transfer. We find that Language model finetuning of multi-lingual pre-trained model (M-DistilBERT, M-BERT) leads to 32.0-34.94%, 76.15-87.54% relative improvement on French and German test sets correspondingly. Also, Gradual unfreezing of pre-trained model's layers during training results in relative improvement of 38-45% for French and 58-70% for German. Compared to training a model in Joint Training scheme using English, French and German training sets, zero-shot BERT-based classification model reaches 86% of the performance achieved by jointly-trained BERT-based classification model.

* Accepted in CSCI2021 conference 

  Access Paper or Ask Questions

Zero-Shot Cross-Lingual Transfer in Legal Domain Using Transformer models

Nov 28, 2021
Zein Shaheen, Gerhard Wohlgenannt, Dmitry Muromtsev

Zero-shot cross-lingual transfer is an important feature in modern NLP models and architectures to support low-resource languages. In this work, We study zero-shot cross-lingual transfer from English to French and German under Multi-Label Text Classification, where we train a classifier using English training set, and we test using French and German test sets. We extend EURLEX57K dataset, the English dataset for topic classification of legal documents, with French and German official translation. We investigate the effect of using some training techniques, namely Gradual Unfreezing and Language Model finetuning, on the quality of zero-shot cross-lingual transfer. We find that Language model finetuning of multi-lingual pre-trained model (M-DistilBERT, M-BERT) leads to 32.0-34.94%, 76.15-87.54\% relative improvement on French and German test sets correspondingly. Also, Gradual unfreezing of pre-trained model's layers during training results in relative improvement of 38-45% for French and 58-70% for German. Compared to training a model in Joint Training scheme using English, French and German training sets, zero-shot BERT-based classification model reaches 86% of the performance achieved by jointly-trained BERT-based classification model.

* Submitted to CSCI2021 conference 

  Access Paper or Ask Questions

LassoBench: A High-Dimensional Hyperparameter Optimization Benchmark Suite for Lasso

Nov 04, 2021
Kenan Šehić, Alexandre Gramfort, Joseph Salmon, Luigi Nardi

Even though Weighted Lasso regression has appealing statistical guarantees, it is typically avoided due to its complex search space described with thousands of hyperparameters. On the other hand, the latest progress with high-dimensional HPO methods for black-box functions demonstrates that high-dimensional applications can indeed be efficiently optimized. Despite this initial success, the high-dimensional HPO approaches are typically applied to synthetic problems with a moderate number of dimensions which limits its impact in scientific and engineering applications. To address this limitation, we propose LassoBench, a new benchmark suite tailored for an important open research topic in the Lasso community that is Weighted Lasso regression. LassoBench consists of benchmarks on both well-controlled synthetic setups (number of samples, SNR, ambient and effective dimensionalities, and multiple fidelities) and real-world datasets, which enable the use of many flavors of HPO algorithms to be improved and extended to the high-dimensional setting. We evaluate 5 state-of-the-art HPO methods and 3 baselines, and demonstrate that Bayesian optimization, in particular, can improve over the methods commonly used for sparse regression while highlighting limitations of these frameworks in very high-dimensions. Remarkably, Bayesian optimization improve the Lasso baselines on 60, 100, 300, and 1000 dimensional problems by 45.7%, 19.2%, 19.7% and 15.5%, respectively.

* 10 pages, 10 figures 

  Access Paper or Ask Questions

Text is Text, No Matter What: Unifying Text Recognition using Knowledge Distillation

Jul 27, 2021
Ayan Kumar Bhunia, Aneeshan Sain, Pinaki Nath Chowdhury, Yi-Zhe Song

Text recognition remains a fundamental and extensively researched topic in computer vision, largely owing to its wide array of commercial applications. The challenging nature of the very problem however dictated a fragmentation of research efforts: Scene Text Recognition (STR) that deals with text in everyday scenes, and Handwriting Text Recognition (HTR) that tackles hand-written text. In this paper, for the first time, we argue for their unification -- we aim for a single model that can compete favourably with two separate state-of-the-art STR and HTR models. We first show that cross-utilisation of STR and HTR models trigger significant performance drops due to differences in their inherent challenges. We then tackle their union by introducing a knowledge distillation (KD) based framework. This is however non-trivial, largely due to the variable-length and sequential nature of text sequences, which renders off-the-shelf KD techniques that mostly works with global fixed-length data inadequate. For that, we propose three distillation losses all of which are specifically designed to cope with the aforementioned unique characteristics of text recognition. Empirical evidence suggests that our proposed unified model performs on par with individual models, even surpassing them in certain cases. Ablative studies demonstrate that naive baselines such as a two-stage framework, and domain adaption/generalisation alternatives do not work as well, further verifying the appropriateness of our design.

* IEEE International Conference on Computer Vision (ICCV), 2021 

  Access Paper or Ask Questions

Non-parametric Active Learning and Rate Reduction in Many-body Hilbert Space with Rescaled Logarithmic Fidelity

Jul 01, 2021
Wei-Ming Li, Shi-Ju Ran

In quantum and quantum-inspired machine learning, the very first step is to embed the data in quantum space known as Hilbert space. Developing quantum kernel function (QKF), which defines the distances among the samples in the Hilbert space, belongs to the fundamental topics for machine learning. In this work, we propose the rescaled logarithmic fidelity (RLF) and a non-parametric active learning in the quantum space, which we name as RLF-NAL. The rescaling takes advantage of the non-linearity of the kernel to tune the mutual distances of samples in the Hilbert space, and meanwhile avoids the exponentially-small fidelities between quantum many-qubit states. We compare RLF-NAL with several well-known non-parametric algorithms including naive Bayes classifiers, $k$-nearest neighbors, and spectral clustering. Our method exhibits excellent accuracy particularly for the unsupervised case with no labeled samples and the few-shot cases with small numbers of labeled samples. With the visualizations by t-SNE, our results imply that the machine learning in the Hilbert space complies with the principles of maximal coding rate reduction, where the low-dimensional data exhibit within-class compressibility, between-class discrimination, and overall diversity. Our proposals can be applied to other quantum and quantum-inspired machine learning, including the methods using the parametric models such as tensor networks, quantum circuits, and quantum neural networks.

* 7 pages, 4 figures 

  Access Paper or Ask Questions

Feature-based Style Randomization for Domain Generalization

Jun 06, 2021
Yue Wang, Lei Qi, Yinghuan Shi, Yang Gao

As a recent noticeable topic, domain generalization (DG) aims to first learn a generic model on multiple source domains and then directly generalize to an arbitrary unseen target domain without any additional adaption. In previous DG models, by generating virtual data to supplement observed source domains, the data augmentation based methods have shown its effectiveness. To simulate the possible unseen domains, most of them enrich the diversity of original data via image-level style transformation. However, we argue that the potential styles are hard to be exhaustively illustrated and fully augmented due to the limited referred styles, leading the diversity could not be always guaranteed. Unlike image-level augmentation, we in this paper develop a simple yet effective feature-based style randomization module to achieve feature-level augmentation, which can produce random styles via integrating random noise into the original style. Compared with existing image-level augmentation, our feature-level augmentation favors a more goal-oriented and sample-diverse way. Furthermore, to sufficiently explore the efficacy of the proposed module, we design a novel progressive training strategy to enable all parameters of the network to be fully trained. Extensive experiments on three standard benchmark datasets, i.e., PACS, VLCS and Office-Home, highlight the superiority of our method compared to the state-of-the-art methods.


  Access Paper or Ask Questions

<<
541
542
543
544
545
546
547
548
549
550
551
552
553
>>