Method and device for image processing, and computer storage medium
AssigneeBeijing Sensetime Technology Development Co., Ltd.
InventorsXingang Pan, Jianping Shi, Ping Luo, Xiaoou Tang
Life of this patent
Estimating the term…
Abstract
A method and device for image recognition and a storage medium are provided. The method includes: a target image is acquired; feature extraction processing is performed on the target image through convolutional layers in a neural network model to obtain feature maps, and Instance Normalization (IN) and Batch Normalization (BN) processing is performed on the feature maps to obtain a recognition result of the target image; and the recognition result of the target image is output.
Claims17
A method for image recognition, comprising:
- acquiring an image to be recognized;
- performing, through convolutional layers in a neural network model, feature extraction processing on the image to be recognized, to obtain feature maps;
- performing Instance Normalization (IN) processing on a first channel set comprising part of channels corresponding to feature maps output by each convolutional layer in a first convolutional layer set and performing Batch Normalization (BN) processing on a second channel set comprising part of channels corresponding to feature maps output by each convolutional layer in a second convolutional layer set, to obtain a recognition result of the image to be recognized, wherein the first convolutional layer set and the second convolutional layer set are selected from the convolutional layers in the neural network model, and channels comprised in the first channel set are different from channels comprised in the second channel set;
- and
- outputting the recognition result of the image to be recognized.
A computer device, comprising a memory and a processor, wherein the memory is configured to store computer-executable instructions and the processor is configured to run the computer-executable instructions in the memory to implement a method for image recognition comprising:
- acquiring an image to be recognized;
- performing, through convolutional layers in a neural network model, feature extraction processing on the image to be recognized, to obtain feature maps;
- performing Instance Normalization (IN) processing on a first channel set comprising part of channels corresponding to feature maps output by each convolutional layer in a first convolutional layer set and performing Batch Normalization (BN) processing on a second channel set comprising part of channels corresponding to feature maps output by each convolutional layer in a second convolutional layer set, to obtain a recognition result of the image to be recognized, wherein the first convolutional layer set and the second convolutional layer set are selected from the convolutional layers in the neural network model, and channels comprised in the first channel set are different from channels comprised in the second channel set;
- and
- outputting the recognition result of the image to be recognized.
A non-transitory computer-readable storage medium, having stored thereon computer-executable instructions that, when executed by a processor, cause the processor to perform a method for image recognition comprising:
- acquiring an image to be recognized;
- performing, through convolutional layers in a neural network model, feature extraction processing on the image to be recognized, to obtain feature maps;
- performing Instance Normalization (IN) processing on a first channel set comprising part of channels corresponding to feature maps output by each convolutional layer in a first convolutional layer set and performing Batch Normalization (BN) processing on a second channel set comprising part of channels corresponding to feature maps output by each convolutional layer in a second convolutional layer set, to obtain a recognition result of the image to be recognized, wherein the first convolutional layer set and the second convolutional layer set are selected from the convolutional layers in the neural network model, and channels comprised in the first channel set are different from channels comprised in the second channel set;
- and
- outputting the recognition result of the image to be recognized.
Dependencies are inferred from the claim text.