University of Electronic Science and Technology of China

Chongqing University

Star Institute of Intelligent Systems

Dibi (chongqing) Intelligent Technology Research Institute Co., Ltd.

Southwest University

Chongqing University, Star Institute of Intelligent Systems, Db (chongqing) Intelligent Technology Research Institute Co., Ltd.

Rui Li

Yongduan Song

Feng Yang

Jian Zhang

Zhengtao Yu

Shichun Wang

Shengtao Pan

Siyu Li

Yiwen Zhang

Jie Hou

Hang Li

Hualing Zhu

Zhenlun Li

Laosheng Wu

Qin Chen

Caishi He

Shihao Pu

Haoyuan Zhong

Xinmin Liu

Hongyu Xia

The present disclosure discloses an adaptive high-precision compression method and system based on a convolutional neural network model, and belongs to the fields of artificial intelligence, computer vision, and image processing. According to the method of the present disclosure, coarse-grained pruning is performed on a neural network model by using a differential evolution algorithm first, and the coarse-grained space is quickly searched through an entropy importance criterion and an objective function with good guidance to obtain a near-optimal neural network structure. Then fine-grained search space is built on the basis of an optimal individual obtained from the coarse-grained search, and fine-grained pruning is performed on the neural network model by a differential evolution algorithm to obtain a network model with an optimal structure. Finally, the performance of the optimal model is restored by using a multi-teacher multi-step knowledge distillation network to reach the precision of an original model.

Adaptive high-precision compression method and system based on convolutional neural network model

Embodiments of the present disclosure provide a quantitative method and system for attention based on a line-of-sight estimation neural network, which improves the stability and training efficiency of the line-of-sight estimation neural network. A few-sample learning method is applied to training of the line-of-sight estimation neural network, which improves generalization performance of the line-of-sight estimation neural network. A nonlinear division method for small intervals of angles of the line of sight is provided, which reduces an estimation error of the line-of-sight estimation neural network. Eye opening and closing detection is added to avoid the line-of-sight estimation error caused by an eye closing state. A method for solving a landing point of the line of sight is provided, which has high environmental adaptability and can be quickly used in actual deployment.

Quantitative analysis method and system for attention based on line-of-sight estimation neural network

The present disclosure relates to a method for recognizing facial expressions based on adversarial elimination. First, a facial expression recognition network is built based on a deep convolutional neural network. On a natural facial expression data set, the facial expression recognition network is trained through a loss function to make facial expression features easier to distinguish. Then some key features of input images are actively eliminated by using an improved confrontation elimination method to generate a new data set to train new networks with different weight distributions and feature extraction capabilities, forcing the network to perform expression classification discrimination based on more features, which reduces the influence of interference factors such as occlusion on the network recognition accuracy rate, and improving the robustness of the facial expression recognition network. Finally, the final expression classification predicted results are obtained by using network integration and a relative majority voting method.

Method for recognizing facial expressions based on adversarial elimination

A system and process for determining and analyzing surface property parameters of a substance based on kinetic method is provided. The system comprises a sample processing system and a detection system. The sample processing system includes a reactor (), a collector for liquid to be tested (), and a container for liquid to be tested (). The detection system includes a detecting electrode (), a concentration and activity operator, a kinetic data processor, a surface property operation module, and a result output module. The process comprises: having the substance to be tested to be treated with an electrolyte solution, measuring activity of liquid to be tested upon reaction at a pre-set time interval, and processing with the kinetic data processor and the surface property operation module, so as to obtain surface property parameters of the substance to be tested. The present invention adopts kinetic method of ion exchange to overcome the issues associated with long reaction equilibrium time, not easy to determine equilibrium and not easy to accurately determine the value of m. Five parameters of the substance surface property can be calculated with only intercept and gradient of the linear regression equation obtained from the kinetic data, and the total amount of surface charge can also be directly determined.

System and process for determining and analysing surface property parameters of substance based on kinetic method

Growing community of inventors

Chongqing, China

Rui Li