The ability of deep learning (DL) approaches to learn generalised signal and noise models, coupled with their fast inference on GPUs, holds great promise for enhancing gravitational-wave (GW) searches in terms of spee...
详细信息
The ability of deep learning (DL) approaches to learn generalised signal and noise models, coupled with their fast inference on GPUs, holds great promise for enhancing gravitational-wave (GW) searches in terms of speed, parameter space coverage, and search sensitivity. However, the opaque nature of DL models severely harms their reliability. In this work, we meticulously develop a DL model stage-wise and work towards improving its robustness and reliability. First, we address the problems in maintaining the purity of training data by deriving a new metric that better reflects the visual strength of the 'chirp' signal features in the data. Using a reduced, smooth representation obtained through a variational auto-encoder (VAE), we build a classifier to search for compact binary coalescence (CBC) signals. Our tests on real LIGO data show an impressive performance of the model. However, upon probing the robustness of the model through adversarial attacks, its simple failure modes were identified, underlining how such models can still be highly fragile. As a first step towards bringing robustness, we retrain the model in a novel framework involving a generative adversarial network (GAN). Over the course of training, the model learns to eliminate the primary modes of failure identified by the adversaries. Although absolute robustness is practically impossible to achieve, we demonstrate some fundamental improvements earned through such training, like sparseness and reduced degeneracy in the extracted features at different layers inside the model. We show that these gains are achieved at practically zero loss in terms of model performance on real LIGO data before and after GAN training. Through a direct search on similar to 8.8 days of LIGO data, we recover two significant CBC events from GWTC-2.1 (Abbott et al 2022 2108.01045 [gr-qc]), GW190519_153544 and GW190521_074359. We also report the search sensitivity obtained from an injection study.
Herein, a highly productive and defect-free 3D-printing system enforced by deep-learning (DL)-based anomaly detection and reinforcement-learning (RL)-based optimization processes is developed. Unpredictable defect fac...
详细信息
Herein, a highly productive and defect-free 3D-printing system enforced by deep-learning (DL)-based anomaly detection and reinforcement-learning (RL)-based optimization processes is developed. Unpredictable defect factors, such as machine setting errors or unexpected material flow, are analyzed by image-based anomaly detection implemented using a variational autoencoder DL model. Real-time detection and in situ correction of defects are implemented by an autocalibration algorithm in conjunction with the DL system. In view of productivity enhancement, the optimized set of diversified printing speeds can be generated from virtual simulation of RL, which is established using a physics-based engineering model. The RL-simulated parameter set maximizes printing speed and minimizes deflection-related failures throughout the 3D-printing process. With the synergistic assistance of DL and RL techniques, the developed system can overcome the inherent challenging intractability of 3D printing in terms of material property and geometry, achieving high process productivity.
variational autoencoders (VAEs) and Generative Adversarial Networks (GANs) have been widely used in hyperspectral image classification (HSIC) tasks. However, the generated HSI virtual samples by VAEs are often ambiguo...
详细信息
variational autoencoders (VAEs) and Generative Adversarial Networks (GANs) have been widely used in hyperspectral image classification (HSIC) tasks. However, the generated HSI virtual samples by VAEs are often ambiguous, and GANs are prone to the mode collapse, which lead the poor generalization abilities ultimately. Moreover, most of these models only consider the extraction of spectral or spatial features. They fail to combine the two branches interactively and ignore the correlation between them. Consequently, the variational generative adversarial network with crossed spatial and spectral interactions (CSSVGAN) was proposed in this paper, which includes a dual-branch variational Encoder to map spectral and spatial information to different latent spaces, a crossed interactive Generator to improve the quality of generated virtual samples, and a Discriminator stuck with a classifier to enhance the classification performance. Combining these three subnetworks, the proposed CSSVGAN achieves excellent classification by ensuring the diversity and interacting spectral and spatial features in a crossed manner. The superior experimental results on three datasets verify the effectiveness of this method.
In hyperspectral unmixing (HU), spectral variability in hyperspectral images (HSIs) is a major challenge which has received a lot of attention over the last few years. Here, we propose a method utilizing a generative ...
详细信息
In hyperspectral unmixing (HU), spectral variability in hyperspectral images (HSIs) is a major challenge which has received a lot of attention over the last few years. Here, we propose a method utilizing a generative adversarial network (GAN) for creating synthetic HSIs having a controllable degree of realistic spectral variability from existing HSIs with established ground truth abundance maps. Such synthetic images can be a valuable tool when developing HU methods that can deal with spectral variability. We use a variational autoencoder (VAE) to investigate how the variability in the synthesized images differs from the original images and perform blind unmixing experiments on the generated images to illustrate the effect of increasing the variability.
Deep learning is usually applied to static datasets. If used for classification based on data streams, it is not easy to take into account a non-stationarity. This thesis presents work in progress on a new method for ...
详细信息
Deep learning is usually applied to static datasets. If used for classification based on data streams, it is not easy to take into account a non-stationarity. This thesis presents work in progress on a new method for online deep classifi- cation learning in data streams with slow or moderate drift, highly relevant for the application domain of malware detection. The method uses a combination of multilayer perceptron and variational autoencoder to achieve constant mem- ory consumption by encoding past data to a generative model. This can make online learning of neural networks more accessible for independent adaptive sys- tems with limited memory. First results for real-world malware stream data are presented, and they look promising. 1
The current image generative models have achieved a remarkably realistic image quality, offering numerous academic and industrial applications. However, to ensure these models are used for benign purposes, it is essen...
详细信息
The current image generative models have achieved a remarkably realistic image quality, offering numerous academic and industrial applications. However, to ensure these models are used for benign purposes, it is essential to develop tools that definitively detect whether an image has been synthetically generated. Consequently, several detectors with excellent performance in computer vision applications have been developed. However, these detectors cannot be directly applied as they areto multi-spectral satellite images, necessitating the training of new models. While two-class classifiers generally achieve high detection accuracies, they struggle to generalize to image domains and generative architectures different from those encountered during training. In this paper, we propose a one-class classifier based on Vector Quantized variational autoencoder 2 (VQ-VAE 2) features to overcome the limitations of two-class classifiers. We start by highlighting the generalization problem faced by binary classifiers. This was demonstrated by training and testing an EfficientNet-B4 architecture on multiple multi-spectral datasets. We then illustrate that the VQ-VAE 2-based classifier, which was trained exclusively on pristine images, could detect images from different domains and generated by architectures not encountered during training. Finally, we conducted a head-to-head comparison between the two classifiers on the same generated datasets, emphasizing the superior generalization capabilities of the VQ-VAE 2-based detector, wherewe obtained a probability of detection at a 0.05 false alarm rate of 1 for the blue and red channels when using the VQ-VAE 2-based detector, and 0.72 when we used the EfficientNet-B4 classifier.
We give an asymptotic expansion of the relative entropy between the heat kernel q(Z)(t, z, w) of a compact Riemannian manifold Z and the normalized Riemannian volume for small values of t and for a fixed element z is ...
详细信息
We give an asymptotic expansion of the relative entropy between the heat kernel q(Z)(t, z, w) of a compact Riemannian manifold Z and the normalized Riemannian volume for small values of t and for a fixed element z is an element of Z. We prove that coefficients in the expansion can be expressed as universal polynomials in the components of the curvature tensor and its covariant derivatives at z, when they are expressed in terms of normal coordinates. We describe a method to compute the coefficients, and we use the method to compute the first three coefficients. The asymptotic expansion is necessary for an unsupervised machine-learning algorithm called the Diffusion variational autoencoder.
Map matching has been widely used in various indoor localization technologies. However, conventional map matching technologies based on probabilistic models, such as particle filter (PF), still have a series of limita...
详细信息
Map matching has been widely used in various indoor localization technologies. However, conventional map matching technologies based on probabilistic models, such as particle filter (PF), still have a series of limitations, such as underutilization of map information, poor generalization, and relatively low precision. To improve the performance of PF-based map matching technique, this paper proposes MapDem, a novel map matching model fusing dynamic word embeddings and variational autoencoder (VAE) to improve matching performance significantly. The key to our approach is to extract map information using dynamic word embeddings to represent each reachable point on the map as word vectors with allowable oriented trajectory information. The same point has different representations on different trajectories so that MapDem can adaptively learn the contextual information of map for position estimation. Unlike traditional particle filters, MapDem focuses on the learning of particle sets distribution by a statistical model, variational autoencoder (VAE), followed by estimating position with combined current and previous sequence information. Extensive experiments have been conducted with 610 trajectories in three real-world scenarios. Numerical results demonstrate the adaptability of MapDem which works equally well in all three different scenarios, outperforming traditional particle filters by 18% on average.
Deep learning-based methods have recently demonstrated outstanding performance on general image classification tasks. As optimization of these methods is dependent on a large amount of labeled data, their application ...
详细信息
Deep learning-based methods have recently demonstrated outstanding performance on general image classification tasks. As optimization of these methods is dependent on a large amount of labeled data, their application in medical image classification is limited. To address this issue, we propose PFEMed, a novel few-shot classification method for medical images. To extract general and specific features from medical images, this method employs a dual-encoder structure, that is, one encoder with fixed weights pre-trained on public image classification datasets and another encoder trained on the target medical dataset. In addition, we introduce a novel prior-guided variational autoencoder (VAE) module to enhance the robustness of the target feature, which is the concatenation of the general and specific features. Then, we match the target features extracted from both the support and query medical image samples and pre-dict the category attribution of the query examples. Extensive experiments on several publicly available medical image datasets show that our method outperforms current state-of-the-art few-shot methods by a wide margin, particularly outperforming MetaMed on the Pap smear dataset by over 2.63%.(c) 2022 Elsevier Ltd. All rights reserved.
The estimation of patient-specific tissue properties in the form of model parameters is important for personalized physiological models. Because tissue properties are spatially varying across the underlying geometrica...
详细信息
The estimation of patient-specific tissue properties in the form of model parameters is important for personalized physiological models. Because tissue properties are spatially varying across the underlying geometrical model, it presents a significant challenge of high-dimensional (HD) optimization at the presence of limited measurement data. A common solution to reduce the dimension of the parameter space is to explicitly partition the geometrical mesh. In this paper, we present a novel concept that uses a generative variational auto-encoder (VAE) to embed HD Bayesian optimization into a low-dimensional (LD) latent space that represents the generative code of HD parameters. We further utilize VAE-encoded knowledge about the generative code to guide the exploration of the search space. The presented method is applied to estimating tissue excitability in a cardiac electrophysiological model in a range of synthetic and real-data experiments, through which we demonstrate its improved accuracy and substantially reduced computational cost in comparison to existing methods that rely on geometry-based reduction of the HD parameter space. (C) 2020 Elsevier B.V. All rights reserved.
暂无评论