We propose a new Bayesian strategy for adaptation to smoothness in nonparametric models based on heavy tailed series priors. We illustrate it in a variety of settings, showing in particular that the corresponding Bayesian posterior distributions achieve adaptive rates of contraction in the minimax sense (up to logarithmic factors) without the need to sample hyperparameters. Unlike many existing procedures, where a form of direct model (or estimator) selection is performed, the method can be seen as performing a soft selection through the prior tail. In Gaussian regression, such heavy tailed priors are shown to lead to (near-)optimal simultaneous adaptation both in the $L^2$- and $L^\infty$-sense. Results are also derived for linear inverse problems, for anisotropic Besov classes, and for certain losses in more general models through the use of tempered posterior distributions. We present numerical simulations corroborating the theory.
相關內容
ACM/IEEE第23屆模型驅動工程語言和系統國際會議，是模型驅動軟件和系統工程的首要會議系列，由ACM-SIGSOFT和IEEE-TCSE支持組織。自1998年以來，模型涵蓋了建模的各個方面，從語言和方法到工具和應用程序。模特的參加者來自不同的背景，包括研究人員、學者、工程師和工業專業人士。MODELS 2019是一個論壇，參與者可以圍繞建模和模型驅動的軟件和系統交流前沿研究成果和創新實踐經驗。今年的版本將為建模社區提供進一步推進建模基礎的機會，并在網絡物理系統、嵌入式系統、社會技術系統、云計算、大數據、機器學習、安全、開源等新興領域提出建模的創新應用以及可持續性。
官網鏈接： ·
Extensibility
·
PSENet
·
PANet
·
未標記
·
Existing scene text detection methods typically rely on extensive real data for training. Due to the lack of annotated real images, recent works have attempted to exploit large-scale labeled synthetic data (LSD) for pre-training text detectors. However, a synth-to-real domain gap emerges, further limiting the performance of text detectors. Differently, in this work, we propose FreeReal, a real-domain-aligned pre-training paradigm that enables the complementary strengths of both LSD and unlabeled real data (URD). Specifically, to bridge real and synthetic worlds for pre-training, a glyph-based mixing mechanism (GlyphMix) is tailored for text images.GlyphMix delineates the character structures of synthetic images and embeds them as graffiti-like units onto real images. Without introducing real domain drift, GlyphMix freely yields real-world images with annotations derived from synthetic labels. Furthermore, when given free fine-grained synthetic labels, GlyphMix can effectively bridge the linguistic domain gap stemming from English-dominated LSD to URD in various languages. Without bells and whistles, FreeReal achieves average gains of 1.97%, 3.90%, 3.85%, and 4.56% in improving the performance of FCENet, PSENet, PANet, and DBNet methods, respectively, consistently outperforming previous pre-training methods by a substantial margin across four public datasets. Code is available at //github.com/SJTU-DeepVisionLab/FreeReal.
Supervised models for speech enhancement are trained using artificially generated mixtures of clean speech and noise signals. However, the synthetic training conditions may not accurately reflect real-world conditions encountered during testing. This discrepancy can result in poor performance when the test domain significantly differs from the synthetic training domain. To tackle this issue, the UDASE task of the 7th CHiME challenge aimed to leverage real-world noisy speech recordings from the test domain for unsupervised domain adaptation of speech enhancement models. Specifically, this test domain corresponds to the CHiME-5 dataset, characterized by real multi-speaker and conversational speech recordings made in noisy and reverberant domestic environments, for which ground-truth clean speech signals are not available. In this paper, we present the objective and subjective evaluations of the systems that were submitted to the CHiME-7 UDASE task, and we provide an analysis of the results. This analysis reveals a limited correlation between subjective ratings and several supervised nonintrusive performance metrics recently proposed for speech enhancement. Conversely, the results suggest that more traditional intrusive objective metrics can be used for in-domain performance evaluation using the reverberant LibriCHiME-5 dataset developed for the challenge. The subjective evaluation indicates that all systems successfully reduced the background noise, but always at the expense of increased distortion. Out of the four speech enhancement methods evaluated subjectively, only one demonstrated an improvement in overall quality compared to the unprocessed noisy speech, highlighting the difficulty of the task. The tools and audio material created for the CHiME-7 UDASE task are shared with the community.
The trustworthiness of Machine Learning (ML) models can be difficult to assess, but is critical in high-risk or ethically sensitive applications. Many models are treated as a `black-box' where the reasoning or criteria for a final decision is opaque to the user. To address this, some existing Explainable AI (XAI) approaches approximate model behaviour using perturbed data. However, such methods have been criticised for ignoring feature dependencies, with explanations being based on potentially unrealistic data. We propose a novel framework, CHILLI, for incorporating data context into XAI by generating contextually aware perturbations, which are faithful to the training data of the base model being explained. This is shown to improve both the soundness and accuracy of the explanations.
We present a new approach for nonlocal image denoising, based around the application of an unnormalized extended Gaussian ANOVA kernel within a bilevel optimization algorithm. A critical bottleneck when solving such problems for finely-resolved images is the solution of huge-scale, dense linear systems arising from the minimization of an energy term. We tackle this using a Krylov subspace approach, with a Nonequispaced Fast Fourier Transform utilized to approximate matrix-vector products in a matrix-free manner. We accelerate the algorithm using a novel change of basis approach to account for the (known) smallest eigenvalue-eigenvector pair of the matrices involved, coupled with a simple but frequently very effective diagonal preconditioning approach. We present a number of theoretical results concerning the eigenvalues and predicted convergence behavior, and a range of numerical experiments which validate our solvers and use them to tackle parameter learning problems. These demonstrate that very large problems may be effectively and rapidly denoised with very low storage requirements on a computer.
We propose a novel approach for modeling semantic contextual relationships in videos. This graph-based model enables the learning and propagation of higher-level spatial-temporal contexts to facilitate the semantic labeling of local regions. We introduce an exemplar-based nonparametric view of contextual cues, where the inherent relationships implied by object hypotheses are encoded on a similarity graph of regions. Contextual relationships learning and propagation are performed to estimate the pairwise contexts between all pairs of unlabeled local regions. Our algorithm integrates the learned contexts into a Conditional Random Field (CRF) in the form of pairwise potentials and infers the per-region semantic labels. We evaluate our approach on the challenging YouTube-Objects dataset which shows that the proposed contextual relationship model outperforms the state-of-the-art methods.
We consider a covariate-assisted ranking model grounded in the Plackett--Luce framework. Unlike existing works focusing on pure covariates or individual effects with fixed covariates, our approach integrates individual effects with dynamic covariates. This added flexibility enhances realistic ranking yet poses significant challenges for analyzing the associated estimation procedures. This paper makes an initial attempt to address these challenges. We begin by discussing the sufficient and necessary condition for the model's identifiability. We then introduce an efficient alternating maximization algorithm to compute the maximum likelihood estimator (MLE). Under suitable assumptions on the topology of comparison graphs and dynamic covariates, we establish a quantitative uniform consistency result for the MLE with convergence rates characterized by the asymptotic graph connectivity. The proposed graph topology assumption holds for several popular random graph models under optimal leading-order sparsity conditions. A comprehensive numerical study is conducted to corroborate our theoretical findings and demonstrate the application of the proposed model to real-world datasets, including horse racing and tennis competitions.
Keyword spotting (KWS) is one of the speech recognition tasks most sensitive to the quality of the feature representation. However, the research on KWS has traditionally focused on new model topologies, putting little emphasis on other aspects like feature extraction. This paper investigates the use of the multitaper technique to create improved features for KWS. The experimental study is carried out for different test scenarios, windows and parameters, datasets, and neural networks commonly used in embedded KWS applications. Experiment results confirm the advantages of using the proposed improved features.
This work presents the development and validation of a digital twin for a semi-autogenous grinding (SAG) mill controlled by an expert control system. The digital twin consists of three interconnected modules that emulate the behavior of a closed-loop system: (1) fuzzy logic for the expert control system, (2) a state-space model for the regulatory control, and (3) a recurrent neural network (RNN) for the SAG mill process. The model was trained with data corresponding to 68 hours of operation and validated with 8 hours of test data. The digital twin predicts the dynamic behavior of the mill's bearing pressure, motor power, tonnage, solids percentage, and rotational speed within a 2.5-minute horizon with a 30-second sampling time. The RNN comprises two serial modules for detection and training. The disturbance detection evaluates the need for training by comparing the recent prediction error with the expected error using hypothesis tests for mean, variance, and probability distribution. If the detection module is activated, the parameters of the neural model are re-estimated with recent data. The detection module was configured with test data to eliminate false positives. Results indicate that the digital twin can satisfactorily supervise the SAG mill, which is operated with the expert control system. Future work will focus on integrating this digital twin into real-time optimization strategies with industrial validation.
The automated finite element analysis of complex CAD models using boundary-fitted meshes is rife with difficulties. Immersed finite element methods are intrinsically more robust but usually less accurate. In this work, we introduce an efficient, robust, high-order immersed finite element method for complex CAD models. Our approach relies on three adaptive structured grids: a geometry grid for representing the implicit geometry, a finite element grid for discretising physical fields and a quadrature grid for evaluating the finite element integrals. The geometry grid is a sparse VDB (Volumetric Dynamic B+ tree) grid that is highly refined close to physical domain boundaries. The finite element grid consists of a forest of octree grids distributed over several processors, and the quadrature grid in each finite element cell is an octree grid constructed in a bottom-up fashion. We discretise physical fields on the finite element grid using high-order Lagrange basis functions. The resolution of the quadrature grid ensures that finite element integrals are evaluated with sufficient accuracy and that any sub-grid geometric features, like small holes or corners, are resolved up to a desired resolution. The conceptual simplicity and modularity of our approach make it possible to reuse open-source libraries, i.e. openVDB and p4est for implementing the geometry and finite element grids, respectively, and BDDCML for iteratively solving the discrete systems of equations in parallel using domain decomposition. We demonstrate the efficiency and robustness of the proposed approach by solving the Poisson equation on domains given by complex CAD models and discretised with tens of millions of degrees of freedom.
The major challenge when designing multipliers for FPGAs is to address several trade-offs: On the one hand at the performance level and on the other hand at the resource level utilizing DSP blocks or look-up tables (LUTs). With DSPs being a relatively limited resource, the problem of under- or over-utilization of DSPs has previously been addressed by the concept of multiplier tiling, by assembling multipliers from DSPs and small supplemental LUT multipliers. But there had always been an efficiency gap between tiling-based multipliers and radix-4 Booth-Arrays. While the monolithic Booth-Array was shown to be considerably more efficient in terms of LUT-resources on many modern FPGA-architectures, it typically possess a significantly higher critically path delay (or latency when pipelined) compared to multipliers designed by tiling. This work proposes and analyzes the use of smaller Booth-Arrays as sub-multipliers that are integrated into existing tiling-based methods, such that better trade-off points between area and delay can be reached while utilizing a user-specified number of DSP blocks. It is shown by synthesis experiments, that the critical path delay compared to large Booth-Arrays can be reduced, while achieving significant reductions in LUT-resources compared to previous tiling.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191