Aukey Technology Co., Ltd

Wuhan University

Huawei Technologies Co., Limited

Shenzhen Fanttik Technology

Bo Du

Huiyue Ze

Xiaomin Zhong

Mingkai Li

Huahui Zheng

Liangpei Zhang

Haizhuan Lu

Bingkun Duan

Peng Liu

Di Wang

Xiaowei Yin

Chao Zhang

Shisuo Ye

Yuanping Zhong

Zheng Wang

Zongzhi Gao

Rongzhi Chen

Fangyi Liu

Xiaoya Zheng

Mang Ye

Guangcun He

Jiaqi Yang

Chen Wu

Weilin Zhang

Yonghao Xu

Xiaoyang Guo

Juhua Liu

Yutian Lin

Lifang'an Xiao

Shenlong Yang

Lili Zhu

Qihuang Zhong

Hangtian Hou

Disclosed are a resonator and a manufacturing method thereof, a filter, and an electronic device. The resonator includes a substrate, a Bragg reflection layer, and a piezoelectric layer that are sequentially stacked. A first electrode is disposed on a surface that is of the piezoelectric layer and that faces the Bragg reflection layer, a second electrode is disposed on a surface that is of the piezoelectric layer and that is away from the Bragg reflection layer, a border ring is disposed on a surface that is of the second electrode and that is away from the piezoelectric layer, and the resonator has a first resonance region and a second resonance region corresponding to the border ring.

Resonator and manufacturing method thereof, filter, and electronic device

Circuit board

Disclosed in the present invention is hyperspectral image classification method based on context-rich networks. The method comprises a training stage and a prediction stage, wherein the training stage comprises image pre-processing, sample selection and network training. Firstly, performing normalization on a hyperspectral image, and then randomly selecting an appropriate proportion of marked samples from each category to generate a label map, and performing training by using the designed network; in the prediction stage, directly inputting the whole image into the trained network and obtaining a final classification result. By means of the present invention, data pre-processing, feature extraction, the process of context-rich information capturing, and classification are taken into comprehensive consideration in the whole flow; and the classification of a hyperspectral image is realized by means of constructing an end-to-end network.

Hyperspectral image classification method based on context-rich networks

This invention proposes a pedestrian re-identification method based on virtual samples, comprising following steps: s) obtaining virtual persons generated by game engine, and generating the virtual samples with person labels by fusing a background of a target dataset and a pose of real persons through a multi-factor variational generation network; s) rendering the generated virtual samples according to lighting conditions; s) sampling the rendered virtual samples according to person attributes of target dataset; s) constructing a training dataset according to virtual samples obtained by sampling to train a pedestrian re-identification model, and verifying identification effect of the trained model. The present invention uses a virtual image generation framework that integrates translation-rendering-sampling to narrow the distribution between virtual images and real images as much as possible to generate virtual samples, and conduct person re-identification model training, which can be effectively and effectively applied to pedestrian datasets in real scenes.

Pedestrian re-identification method based on virtual samples

A person re-identification method based on a perspective-guided multi-adversarial attention is provided. The deep convolutional neural network includes a feature learning module, a multi-adversarial module, and a perspective-guided attention mechanism module. The multi-adversarial module is followed by a global pooling layer and a perspective discriminator after each stage of a basic network of the feature learning module. The perspective-guided attention mechanism module is an attention map generator and the perspective discriminator. The training of the deep convolutional neural network includes learning of the feature learning module, learning of the multi-adversarial module, and learning of the perspective-guided attention mechanism module. The proposed method uses the trained deep convolutional neural network to extract features of the testing images, and using an Euclidean distance to perform feature matching on images in a query set and images in a gallery set.

Person re-identification method based on perspective-guided multi-adversarial attention

The invention discloses an attention-based joint image and feature adaptive semantic segmentation method. First, the image adaptation procedure is used to transform the source domain image Xto a target-domain-like image Xwith an appearance similar with the target domain image X, to reduce the domain gap between the source domain and the target domain at the image appearance level; then using the feature adaptation procedure to align the features between Xand Xin the semantic prediction space and the image generation space, respectively, to extract the domain-invariant features, to reduce the domain difference between Xand X. In addition, the present invention introduces an attention module in the feature adaptation procedure to help the feature adaptation procedure pay more attention to image regions worthy of attention. Finally, combining the image adaptation procedure and the feature adaptation procedure in the end-to-end manner. The present invention effectively solves the problem of domain gap existing in the cross-modal image semantic segmentation, improves the performance of the semantic segmentation model, and achieves the optimal effect in multiple public data sets.

Attention-based joint image and feature adaptive semantic segmentation method

A hyperspectral remote sensing image classification method based on a self-attention context network is provided. The method constructs a spatial dependency between pixels in a hyperspectral remote sensing image by self-attention learning and context encoding, and learns global context features. For adversarial attacks in the hyperspectral remote sensing data, the proposed method has higher security and reliability to better meet the requirements of safe, reliable, and high-precision object recognition in Earth observation.

Hyperspectral remote sensing image classification method based on self-attention context network

Disclosed is a method for classifying hyperspectral images on the basis of an adaptive multi-scale feature extraction model, the method comprising: establishing a framework comprising the two parts of a scale reference network and a feature extraction network, introducing a condition gate mechanism into the scale reference network, performing determination step-by-step by means of three groups of modules, inputting features into a corresponding scale extraction network, deep mining rich information contained in a hyperspectral remote sensing image, effectively combining features of different scales, improving a classification effect, and generating a fine classification result map.

Method for classifying hyperspectral images on basis of adaptive multi-scale feature extraction model

Growing community of inventors

Shenzhen, China

Bo Du