Edwardsdean1072

By forcing the student model to mimic the predicted distributions of teacher model on both original examples and perturbed examples, the knowledge of QA-interaction can be learned by student model. We evaluate the proposed framework on the widely used BioASQ datasets, and experimental results have shown the proposed method's promising potential.Cerebellar ataxia (CA) is concerned with the incoordination of movement caused by cerebellar dysfunction. Movements of the eyes, speech, trunk, and limbs are affected. Conventional machine learning approaches utilizing centralised databases have been used to objectively diagnose and quantify the severity of CA. Although these approaches achieved high accuracy, large scale deployment will require large clinics and raises privacy concerns. In this study, we propose an image transformation-based approach to leverage the advantages of state-of-the-art deep learning with federated learning in diagnosing CA. We use motion capture sensors during the performance of a standard neurological balance test obtained from four geographically separated clinics. The recurrence plot, melspectrogram, and poincaré plot are three transformation techniques explored. Experimental results indicate that the recurrence plot yields the highest validation accuracy (86.69%) with MobileNetV2 model in diagnosing CA. The proposed scheme provides a practical solution with high diagnosis accuracy, removing the need for feature engineering and preserving data privacy for a large-scale deployment.Therapeutic hypothermia (TH) is a common and effective technique to reduce inflammation and induce neuroprotection across a variety of diseases. Focal TH of the brain can avoid the side effects of systemic cooling. The degree and extent of focal TH are a function of cooling probe design and local brain thermoregulation processes. To refine focal TH probe design, with application-specific optimization, we develop precise computational models of brain thermodynamics under intense local cooling. Here, we present a novel multiphysics in silico model that can accurately predict brain response to focal cooling. The model was parameterized from previously described values of metabolic activity, thermal conductivity, and temperature-dependent cerebral perfusion. The model was validated experimentally using data from clinical cases where local cooling was induced intracranially and brain temperatures monitored in real-time with MR thermometry. The validated model was then used to identify optimal design probe parameters to maximize volumetric TH, including considering three stratifications of cooling (mild, moderate, and profound) to produce Volume of Tissue Cooled (VOTC) maps. We report cooling radius increases in a nearly linear fashion with probe length and decreasing probe surface temperature.We present the first one-shot personalized sketch segmentation method. We aim to segment all sketches belonging to the same category provisioned with a single sketch with a given part annotation while (i) preserving the parts semantics embedded in the exemplar, and (ii) being robust to input style and abstraction. We refer to this scenario as personalized. With that, we importantly enable a much-desired personalization capability for downstream fine-grained sketch analysis tasks. To train a robust segmentation module, we deform the exemplar sketch to each of the available sketches of the same category. Our method generalizes to sketches not observed during training. Our central contribution is a sketch-specific hierarchical deformation network. Given a multi-level sketch-strokes encoding obtained via a graph convolutional network, our method estimates rigid-body transformation from the target to the exemplar, on the upper level. Finer deformation from the exemplar to the globally warped target sketch is further obtained through stroke-wise deformations, on the lower-level. Both levels of deformation are guided by mean squared distances between the keypoints learned without supervision, ensuring that the stroke semantics are preserved. We evaluate our method against the state-of-the-art segmentation and perceptual grouping baselines re-purposed for the one-shot setting and against two few-shot 3D shape segmentation methods. We show that our method outperforms all the alternatives by more than 10% on average. Ablation studies further demonstrate that our method is robust to personalization changes in input part semantics and style differences.Most reference-based image super-resolution (RefSR) methods directly leverage the raw features extracted from a pretrained VGG encoder to transfer the matched texture information from a reference image to a low-resolution image. We argue that simply operating on these raw features neglects the influence of irrelevant and redundant information and the importance of abundant high-frequency representations, leading to undesirable texture matching and transfer results. Taking the advantages of wavelet transformation, which represents the contextual and textural information of features at different scales, we propose a Wavelet-based Texture Reformation Network (WTRN) for RefSR. We first decompose the extracted texture features into low-frequency and high-frequency sub-bands and conduct feature matching on the low-frequency component. Based on the correlation map obtained from the feature matching process, we then separately swap and transfer wavelet-domain features at different stages of the network. Furthermore, a wavelet-based texture adversarial loss is proposed to make the network generate more visually plausible textures. Experiments on four benchmark datasets demonstrate that our proposed method outperforms previous RefSR methods both quantitatively and qualitatively. The source code is available at https//github.com/zskuang58/WTRN-TIP.High Dynamic Range (HDR) imaging via multi-exposure fusion is an important task for most modern imaging platforms. In spite of recent developments in both hardware and algorithm innovations, challenges remain over content association ambiguities caused by saturation, motion, and various artifacts introduced during multi-exposure fusion such as ghosting, noise, and blur. In this work, we propose an Attention-guided Progressive Neural Texture Fusion (APNT-Fusion) HDR restoration model which aims to address these issues within one framework. An efficient two-stream structure is proposed which separately focuses on texture feature transfer over saturated regions and multi-exposure tonal and texture feature fusion. A neural feature transfer mechanism is proposed which establishes spatial correspondence between different exposures based on multi-scale VGG features in the masked saturated HDR domain for discriminative contextual clues over the ambiguous image areas. A progressive texture blending module is designed to blend the encoded two-stream features in a multi-scale and progressive manner. In addition, we introduce several novel attention mechanisms, i.e., the motion attention module detects and suppresses the content discrepancies among the reference images; the saturation attention module facilitates differentiating the misalignment caused by saturation from those caused by motion; and the scale attention module ensures texture blending consistency between different coder/decoder scales. Ruxolitinib manufacturer We carry out comprehensive qualitative and quantitative evaluations and ablation studies, which validate that these novel modules work coherently under the same framework and outperform state-of-the-art methods.This work presents a prototype system based on a multichannel receiving (RX) integrated circuit (IC) for contrast-enhanced ultrasound (CEUS) imaging. The RX IC is implemented in a 40-nm low-voltage CMOS technology and is designed to interface to a capacitive micromachined ultrasonic transducer array. To enable a direct connection of the RX electronics to the transducer, an analog multiplexer with on-chip protection circuitry is developed. Stress tests confirm the reliability of this arrangement when combined with a high-voltage pulser. The RX IC is equipped with a highly programmable bandpass filter to capture harmonic signals from ultrasound contrast agents (UCAs) while suppressing fundamental components. In order to examine the impact of analog front-end (AFE) bandpass filtering, in vitro acoustic experiments are performed with UCAs. A spatial resolution analysis suggests that the AFE bandpass filtering combined with a pulse inversion (PI) technique can improve the lateral resolution by 38% or 9% compared to the original full-bandwidth approach or a stand-alone PI approach, respectively, while the impact on axial resolution is negligible. A phantom study shows that compared to digital bandpass filtering, the AFE bandpass filtering enables better use of the dynamic range of the RX electronics, resulting in better generalized contrast-to-noise ratio from 0.44/0.53 to 0.57/0.68 without or with PI.Deep learning approaches process data in a layer-by-layer way with intermediate (or latent) features. We aim at designing a general solution to optimize the latent manifolds to improve the performance on classification, segmentation, completion and/or reconstruction through probabilistic models. This paper proposes a variational inference model which leads to a clustered embedding. We introduce additional variables in the latent space, called \emphnebula anchors, that guide the latent variables to form clusters during training. To prevent the anchors from clustering among themselves, we employ the variational constraint that enforces the latent features within an anchor to form a Gaussian distribution, resulting in a generative model we refer as Nebula Variational Coding (NVC). Since each latent feature can be labeled with the closest anchor, we also propose to apply metric learning in a self-supervised way to make the separation between clusters more explicit. Consequently, the latent variables of our variational coder form clusters which adapt to the generated semantic of the training data, \eg the categorical labels of each sample. We demonstrate experimentally that it can be used within different architectures designed to solve different problems including text sequence, images, 3D point clouds and volumetric data, validating the advantage of our method.Physics perception very often faces the problem that only limited data or partial measurements on the scene are available. In this work, we propose a strategy to learn the full state of sloshing liquids from measurements of the free surface. Our approach is based on recurrent neural networks (RNN) that project the limited information available to a reduced-order manifold so as to not only reconstruct the unknown information, but also to be capable of performing fluid reasoning about future scenarios in real time. To obtain physically consistent predictions, we train deep neural networks on the reduced-order manifold that, through the employ of inductive biases, ensure the fulfillment of the principles of thermodynamics. RNNs learn from history the required hidden information to correlate the limited information with the latent space where the simulation occurs. Finally, a decoder returns data back to the high-dimensional manifold, so as to provide the user with insightful information in the form of augmented reality.