Understanding the origins of enhanced reactivity of supported, subnanometer in size, metal oxide clusters is challenging due to the scarcity of methods capable to extract atomic-level information from the experimental data. Due to both the sensitivity of X-ray absorption near edge structure (XANES) spectroscopy to the local geometry around metal ions and reliability of theoretical spectroscopy codes for modeling XANES spectra, supervised machine learning approach has become a powerful tool for extracting structural information from the experimental spectra. Here, we present the application of this method to grazing incidence XANES spectra of size-selective Cu oxide clusters on flat support, measured in operando conditions of the methanation reaction. We demonstrate that the convolution neural network can be trained on theoretical spectra and utilized to “invert” experimental XANES data to obtain structural descriptors—the Cu–Cu coordination numbers. As a result, we were able to distinguish between different structural motifs (Cu2O-like and CuO-like) of Cu oxide clusters, transforming in reaction conditions, and reliably evaluate average cluster sizes, with important implications for the understanding of structure, composition, and function relationships in catalysis.

Convolutional neural network (CNN) has achieved remarkable success in the field of fundus images due to its powerful feature learning ability. Computer-aided diagnosis can obtain information with reference value for doctors in clinical diagnosis or screening through proper processing and analysis of fundus images. However, most of the previous studies have focused on the detection of a certain fundus disease, and the simultaneous diagnosis of multiple fundus diseases still faces great challenges. We propose a multi-label classification ensemble model of fundus images based on CNN to directly detect one or more fundus diseases in the retinal fundus images. Every single model consists of two parts. The first part is a feature extraction network based on EfficientNet, and the second part is a custom classification neural network for multi-label classification problems. Finally, the output probabilities of different models are fused as the final recognition result. And it was trained and tested on the data set provided by ODIR 2019 (Peking University International Competition on Ocular Disease Intelligent Recognition). The experimental results show that our model can be trained on fewer data sets and get good results.

No abstract

Current face detectors utilize anchors to frame a multitask learning problem which combines classification and bounding box regression. Effective anchor design and anchor matching strategy enable face detectors to localize faces under large pose and scale variations. However, we observe that more than 80% correctly predicted bounding boxes are regressed from the unmatched anchors (the IoUs between anchors and target faces are lower than a threshold) in the inference phase. It indicates that these unmatched anchors perform excellent regression ability, but the existing methods neglect to learn from them. In this paper, we propose an Online High-quality Anchor Mining Strategy (HAMBox), which explicitly helps outer faces compensate with high-quality anchors. Our proposed HAMBox method could be a general strategy for anchor-based singlestage face detection. Experiments on various datasets, including WIDER FACE, FDDB, AFW and PASCAL Face, demonstrate the superiority of the proposed method. Furthermore, our team win the championship on the Face Detection test track of WIDER Face and Pedestrian Challenge 2019. We will release the codes with PaddlePaddle.

Recursive neural network is one of the most successful deep learning models for natural language processing due to the compositional nature of text. The model recursively composes the vector of a parent phrase from those of child words or phrases, with a key component named composition function. Although a variety of composition functions have been proposed, the syntactic information has not been fully encoded in the composition process. We propose two models, Tag Guided RNN (TG-RNN for short) which chooses a composition function according to the part-ofspeech tag of a phrase, and Tag Embedded RNN/RNTN (TE-RNN/RNTN for short) which learns tag embeddings and then combines tag and word embeddings together. In the fine-grained sentiment classification, experiment results show the proposed models obtain remarkable improvement: TG-RNN/TE-RNN obtain remarkable improvement over baselines, TE-RNTN obtains the second best result among all the top performing models, and all the proposed models have much less parameters/complexity than their counterparts.