We present a summary of the domain adaptive cascade R-CNN method for mitosis detection of digital histopathology images. By comprehensive data augmentation and adapting existing popular detection architecture, our proposed method has achieved an F1 s
core of 0.7500 on the preliminary test set in MItosis DOmain Generalization (MIDOG) Challenge at MICCAI2021.
The drivers behind regional differences of SARS-CoV-2 spread on finer spatio-temporal scales are yet to be fully understood. Here we develop a data-driven modelling approach based on an age-structured compartmental model that compares 116 Austrian re
gions to a suitably chosen control set of regions to explain variations in local transmission rates through a combination of meteorological factors, non-pharmaceutical interventions and mobility. We find that more than 60% of the observed regional variations can be explained by these factors. Decreasing temperature and humidity, increasing cloudiness, precipitation and the absence of mitigation measures for public events are the strongest drivers for increased virus transmission, leading in combination to a doubling of the transmission rates compared to regions with more favourable weather. We conjecture that regions with little mitigation measures for large events that experience shifts toward unfavourable weather conditions are particularly predisposed as nucleation points for the next seasonal SARS-CoV-2 waves.
We carry out the first lattice QCD derivation of the mixing energy and the mixing angle of the pseudoscalar charmonium and glueball on gauge ensembles with $N_f=2$ degenerate dynamical charm quarks. The mixing energy is determined to be $47(7)$ MeV,
which seems insensitive to charm quark masses. By the assumption that $X(2370)$ is predominantly a pseudoscalar glueball, the mixing angle is approximately $4.3(5)^circ$, which results in a $+3.9(5)$ MeV mass shift of the ground state pseudoscalar charmonium. In the mean time, the mixing can raise the total width of the pseudoscalar charmonium by approximately 7 MeV, which explains to some extent the relative large total width of the $eta_c$ meson. Resultantly, the branching fraction of $eta_cto gammagamma$ can be understood in this $cbar{c}$-glueball framework. On the other hand, the seemingly discrepancy of the theoretical predictions and the experimental results of the partial width of $J/psitogammaeta_c$ cannot be alleviated by the $cbar{c}$-glueball mixing picture yet, which demands future precise experimental measurements of this partial width.
Weyl points are the degenerate points in three-dimensional momentum space with nontrivial topological phase, which are usually realized in classical system with structure and symmetry designs. Here we proposed a one-dimensional layer-stacked photonic
crystal using anisotropic materials to realize ideal type-II Weyl points without structure designs. The topological transition from two Dirac points to four Weyl points can be clearly observed by tuning the twist angle between layers. Besides, on the interface between the photonic type-II Weyl material and air, gappless surface states have also been demonstrated in an incomplete bulk bandgap. By breaking parameter symmetry, these ideal type-II Weyl points at the same frequency would transform into the non-ideal ones, and exhibit topological surface states with single group velocity. Our work may provide a new idea for the realization of photonic Weyl points or other semimetal phases by utilizing naturally anisotropic materials.
Cross-modal retrieval aims to enable flexible retrieval experience by combining multimedia data such as image, video, text, and audio. One core of unsupervised approaches is to dig the correlations among different object representations to complete s
atisfied retrieval performance without requiring expensive labels. In this paper, we propose a Graph Pattern Loss based Diversified Attention Network(GPLDAN) for unsupervised cross-modal retrieval to deeply analyze correlations among representations. First, we propose a diversified attention feature projector by considering the interaction between different representations to generate multiple representations of an instance. Then, we design a novel graph pattern loss to explore the correlations among different representations, in this graph all possible distances between different representations are considered. In addition, a modality classifier is added to explicitly declare the corresponding modalities of features before fusion and guide the network to enhance discrimination ability. We test GPLDAN on four public datasets. Compared with the state-of-the-art cross-modal retrieval methods, the experimental results demonstrate the performance and competitiveness of GPLDAN.
We propose a deep switching state space model (DS$^3$M) for efficient inference and forecasting of nonlinear time series with irregularly switching among various regimes. The switching among regimes is captured by both discrete and continuous latent
variables with recurrent neural networks. The model is estimated with variational inference using a reparameterization trick. We test the approach on a variety of simulated and real datasets. In all cases, DS$^3$M achieves competitive performance compared to several state-of-the-art methods (e.g. GRU, SRNN, DSARF, SNLDS), with superior forecasting accuracy, convincing interpretability of the discrete latent variables, and powerful representation of the continuous latent variables for different kinds of time series. Specifically, the MAPE values increase by 0.09% to 15.71% against the second-best performing alternative models.
We propose a Molecular Hypergraph Convolutional Network (MolHGCN) that predicts the molecular properties of a molecule using the atom and functional group information as inputs. Molecules can contain many types of functional groups, which will affect
the properties the molecules. For example, the toxicity of a molecule is associated with toxicophores, such as nitroaromatic groups and thiourea. Conventional graph-based methods that consider the pair-wise interactions between nodes are inefficient in expressing the complex relationship between multiple nodes in a graph flexibly, and applying multi-hops may result in oversmoothing and overfitting problems. Hence, we propose MolHGCN to capture the substructural difference between molecules using the atom and functional group information. MolHGCN constructs a hypergraph representation of a molecule using functional group information from the input SMILES strings, extracts hidden representation using a two-stage message passing process (atom and functional group message passing), and predicts the properties of the molecules using the extracted hidden representation. We evaluate the performance of our model using Tox21, ClinTox, SIDER, BBBP, BACE, ESOL, FreeSolv and Lipophilicity datasets. We show that our model is able to outperform other baseline methods for most of the datasets. We particularly show that incorporating functional group information along with atom information results in better separability in the latent space, thus increasing the prediction accuracy of the molecule property prediction.
We present a novel spectral machine learning (SML) method in screening for pancreatic mass using CT imaging. Our algorithm is trained with approximately 30,000 images from 250 patients (50 patients with normal pancreas and 200 patients with abnormal
pancreas findings) based on public data sources. A test accuracy of 94.6 percents was achieved in the out-of-sample diagnosis classification based on a total of approximately 15,000 images from 113 patients, whereby 26 out of 32 patients with normal pancreas and all 81 patients with abnormal pancreas findings were correctly diagnosed. SML is able to automatically choose fundamental images (on average 5 or 9 images for each patient) in the diagnosis classification and achieve the above mentioned accuracy. The computational time is 75 seconds for diagnosing 113 patients in a laptop with standard CPU running environment. Factors that influenced high performance of a well-designed integration of spectral learning and machine learning included: 1) use of eigenvectors corresponding to several of the largest eigenvalues of sample covariance matrix (spike eigenvectors) to choose input attributes in classification training, taking into account only the fundamental information of the raw images with less noise; 2) removal of irrelevant pixels based on mean-level spectral test to lower the challenges of memory capacity and enhance computational efficiency while maintaining superior classification accuracy; 3) adoption of state-of-the-art machine learning classification, gradient boosting and random forest. Our methodology showcases practical utility and improved accuracy of image diagnosis in pancreatic mass screening in the era of AI.
Audio-visual event localization aims to localize an event that is both audible and visible in the wild, which is a widespread audio-visual scene analysis task for unconstrained videos. To address this task, we propose a Multimodal Parallel Network (M
PN), which can perceive global semantics and unmixed local information parallelly. Specifically, our MPN framework consists of a classification subnetwork to predict event categories and a localization subnetwork to predict event boundaries. The classification subnetwork is constructed by the Multimodal Co-attention Module (MCM) and obtains global contexts. The localization subnetwork consists of Multimodal Bottleneck Attention Module (MBAM), which is designed to extract fine-grained segment-level contents. Extensive experiments demonstrate that our framework achieves the state-of-the-art performance both in fully supervised and weakly supervised settings on the Audio-Visual Event (AVE) dataset.
Ammonia (NH3) is commonly used as group V precursor in gallium nitride (GaN) metalorganic chemical vapor deposition (MOCVD). The high background carbon (C) impurity in MOCVD GaN is related to the low pyrolysis efficiency of NH3, which represents one
of the fundamental challenges hindering the development of high purity thick GaN for vertical high power device applications. This work uses a laser-assisted MOCVD (LA-MOCVD) growth technique to address the high-C issue in MOCVD GaN. Carbon dioxide (CO2) laser with wavelength of 9.219 um was utilized to facilitate NH3 decomposition via resonant vibrational excitation. The LA-MOCVD GaN growth rate (as high as 10 um/hr) shows a strong linear relationship with the trimethylgallium (TMGa) flow rate, indicating high effective V/III ratios and hence efficient NH3 decomposition. Pits-free surface morphology of LA-MOCVD GaN was demonstrated for films with growth rate as high as 8.5 um/hr. The background [C] in LA-MOCVD GaN films decreases monotonically as the laser power increases. A low [C] at 5.5E15 cm-3 was achieved in LA-MOCVD GaN film grown with the growth rate of 4 um/hr. Charge transport characterization of LA-MOCVD GaN films reveals high crystalline quality with room temperature mobility >1000 cm2/Vs. LA-MOCVD growth technique provides an enabling route to achieve high quality GaN epitaxy with low-C impurity and fast growth rate simultaneously. This technique can also be extended for epitaxy of other nitride-based semiconductors.
