During the titanium alloy milling process, high temperatures in the tool-chip contact area will affect the tool life and precision of titanium alloy machining. Therefore, it is essential to measure ...the temperature of the tool-chip contact area continuously. In this paper, a finite element simulation model of the milling process was established using ABAQUS2020 to obtain the highest temperature location in the tool-chip contact area when milling titanium alloy. The integration of the wire with the alumina ceramic substrate formed an integrated wire substrate. Furthermore, NiCr, NiSi, and SiO2 films were deposited on the substrate sequentially using the DC pulsed magnetron sputtering technique. Finally, its microscopic morphology and static and dynamic performance were tested. The results show that the developed thin-film thermocouple temperature sensor has a Seebeck coefficient of 40.72 μV/°C and a dynamic response time of 0.703 ms. The application of the sensor to our titanium alloy milling experiments showed that the sensor can monitor the transient temperature in the tool-chip contact area, and its temperature measurement performance showed no detrimental effect from wearing. The effect of each milling parameter on the milling temperature was analyzed using ANOVA, and a regression model with an R-sq of 96.76% was obtained for the milling temperature.
A hybrid mesoporous photonic crystal vapor sensing chip was developed by introducing fluorescent dyes into mesoporous colloidal crystals. The sensing chip was capable of discriminating various kinds ...of vapors, as well as their concentrations, according to their fluorescence and reflective responses to vapor analytes.
CariGANs Cao, Kaidi; Liao, Jing; Yuan, Lu
ACM transactions on graphics,
12/2018, Letnik:
37, Številka:
6
Journal Article
Recenzirano
Facial caricature is an art form of drawing faces in an exaggerated way to convey humor or sarcasm. In this paper, we propose the first Generative Adversarial Network (GAN) for unpaired ...photo-to-caricature translation, which we call "CariGANs". It explicitly models geometric exaggeration and appearance stylization using two components:
CariGeoGAN
, which only models the geometry-to-geometry transformation from face photos to caricatures, and
CariStyGAN
, which transfers the style appearance from caricatures to face photos without any geometry deformation. In this way, a difficult cross-domain translation problem is decoupled into two easier tasks. The perceptual study shows that caricatures generated by our
CariGANs
are closer to the hand-drawn ones, and at the same time better persevere the identity, compared to state-of-the-art methods. Moreover, our
CariGANs
allow users to control the shape exaggeration degree and change the color/texture style by tuning the parameters or giving an example caricature.
Autism spectrum disorder (ASD) is a highly heterogeneous disorder that affects nearly 1 in 189 females and 1 in 42 males. However, the neurobiological basis of gender differences in ASD is poorly ...understood, as most studies have neglected females and used methods ill-suited to capture such differences.
To identify robust functional brain organisation markers that distinguish between females and males with ASD and predict symptom severity.
We leveraged multiple neuroimaging cohorts (ASD n = 773) and developed a novel spatiotemporal deep neural network (stDNN), which uses spatiotemporal convolution on functional magnetic resonance imaging data to distinguish between groups.
stDNN achieved consistently high classification accuracy in distinguishing between females and males with ASD. Notably, stDNN trained to distinguish between females and males with ASD could not distinguish between neurotypical females and males, suggesting that there are gender differences in the functional brain organisation in ASD that differ from normative gender differences. Brain features associated with motor, language and visuospatial attentional systems reliably distinguished between females and males with ASD. Crucially, these results were observed in a large multisite cohort and replicated in a fully independent cohort. Furthermore, brain features associated with the motor network's primary motor cortex node predicted the severity of restricted/repetitive behaviours in females but not in males with ASD.
Our replicable findings reveal that the brains of females and males with ASD are functionally organised differently, contributing to their clinical symptoms in distinct ways. They inform the development of gender-specific diagnoses and treatment strategies for ASD, and ultimately advance precision psychiatry.
Face recognition achieves exceptional success thanks to the emergence of deep learning. However, many contemporary face recognition models still perform relatively poor in processing profile faces ...compared to frontal faces. A key reason is that the number of frontal and profile training faces are highly imbalanced - there are extensively more frontal training samples compared to profile ones. In addition, it is intrinsically hard to learn a deep representation that is geometrically invariant to large pose variations. In this study, we hypothesize that there is an inherent mapping between frontal and profile faces, and consequently, their discrepancy in the deep representation space can be bridged by an equivariant mapping. To exploit this mapping, we formulate a novel Deep Residual EquivAriant Mapping (DREAM) block, which is capable of adaptively adding residuals to the input deep representation to transform a profile face representation to a canonical pose that simplifies recognition. The DREAM block consistently enhances the performance of profile face recognition for many strong deep networks, including ResNet models, without deliberately augmenting training data of profile faces. The block is easy to use, light-weight, and can be implemented with a negligible computational overhead1.
Supervised deep learning techniques have made a tremendous and unprecedented impact in all segments of our lives, including finance, healthcare, social networks, and more. However, the progress is ...hindered by a substantial challenge: the dependence on large, high-quality labeled datasets. This issue is particularly acute in areas such as biomedicine, where the procurement and annotation of data are not only costly but also intricate. In response to these challenges, this thesis introduces innovative machine learning strategies that are data-efficient, aiming to reduce the dependence on extensive labeled datasets while either preserving or improving the efficacy of deep learning models. The thesis is systematically divided into two primary sections, each targeting key aspects of data-efficient machine learning. Part I is dedicated to the development of advanced algorithms optimized for existing datasets, particularly under the constraint of limited labeling. This section introduces a novel machine learning setting for enhancing generalization and robustness in low-label scenarios, proposes an innovative open-world semi-supervised learning framework, and adapts this framework to real-world applications. Part II focuses on augmenting training resources by incorporating supplementary knowledge. It explores the integration of auxiliary tasks to enhance training, examines the use of historical data to improve AutoML search efficiency, and introduces methods for including large datasets that were previously unmanageable due to memory constraints.
Unsupervised image-to-image translation aims at learning a mapping between two visual domains. However, learning a translation across large geometry variations al- ways ends up with failure. In this ...work, we present a novel disentangle-and-translate framework to tackle the complex objects image-to-image translation task. Instead of learning the mapping on the image space directly, we disentangle image space into a Cartesian product of the appearance and the geometry latent spaces. Specifically, we first in- troduce a geometry prior loss and a conditional VAE loss to encourage the network to learn independent but com- plementary representations. The translation is then built on appearance and geometry space separately. Extensive experiments demonstrate the superior performance of our method to other state-of-the-art approaches, especially in the challenging near-rigid and non-rigid objects translation tasks. In addition, by taking different exemplars as the ap- pearance references, our method also supports multimodal translation. Project page: https://wywu.github. io/projects/TGaGa/TGaGa.html
Accurate cell-type annotation from spatially resolved single cells is crucial to understand functional spatial biology that is the basis of tissue organization. However, current computational methods ...for annotating spatially resolved single-cell data are typically based on techniques established for dissociated single-cell technologies and thus do not take spatial organization into account. Here we present STELLAR, a geometric deep learning method for cell-type discovery and identification in spatially resolved single-cell datasets. STELLAR automatically assigns cells to cell types present in the annotated reference dataset and discovers novel cell types and cell states. STELLAR transfers annotations across different dissection regions, different tissues and different donors, and learns cell representations that capture higher-order tissue structures. We successfully applied STELLAR to CODEX multiplexed fluorescent microscopy data and multiplexed RNA imaging datasets. Within the Human BioMolecular Atlas Program, STELLAR has annotated 2.6 million spatially resolved single cells with dramatic time savings.
Though much progress has been achieved in single-image 3D human recovery, estimating 3D model for in-the-wild images remains a formidable challenge. The reason lies in the fact that obtaining ...high-quality 3D annotations for in-the-wild images is an extremely hard task that consumes enormous amount of resources and manpower. To tackle this problem, previous methods adopt a hybrid training strategy that exploits multiple heterogeneous types of annotations including 3D and 2D while leaving the efficacy of each annotation not thoroughly investigated. In this work, we aim to perform a comprehensive study on cost and effectiveness trade-off between different annotations. Specifically, we focus on the challenging task of in-the-wild 3D human recovery from single images when paired 3D annotations are not fully available. Through extensive experiments, we obtain several observations: 1) 3D annotations are efficient, whereas traditional 2D annotations such as 2D keypoints and body part segmentation are less competent in guiding 3D human recovery. 2) Dense Correspondence such as DensePose is effective. When there are no paired in-the-wild 3D annotations available, the model exploiting dense correspondence can achieve 92% of the performance compared to a model trained with paired 3D data. We show that incorporating dense correspondence into in-the-wild 3D human recovery is promising and competitive due to its high efficiency and relatively low annotating cost. Our model trained with dense correspondence can serve as a strong reference for future research.
An optical nose chip is developed using surface functionalized mesoporous colloidal photonic crystal beads as elements. The prepared optical nose chip displays excellent discrimination among a very ...wide range of compounds, not only the simplex organic vapors from the different or same chemical family, but also the complex expiratory air from different people.