Method and apparatus for training image segmentation model, computer device, and storage medium

A device for training an image segmentation model, comprising a memory for storing instructions and a processor in communication with the memory, wherein the processor is configured to execute the instructions to cause the device to:

• train an initial image segmentation model by using source domain samples, to obtain a pre-trained image segmentation model, the source domain samples comprising a source domain image and a standard segmentation result of the source domain image;
• extract a predicted segmentation result of the source domain image and a predicted segmentation result of a target domain image by using the pre-trained image segmentation model;
• train a first discriminator by using the predicted segmentation result of the source domain image and the predicted segmentation result of the target domain image, the first discriminator being used for discriminating whether an inputted segmentation result is from a source domain or a target domain;
• train a second discriminator by using the predicted segmentation result of the source domain image and the standard segmentation result of the source domain image, the second discriminator being used for discriminating whether the inputted segmentation result is the predicted segmentation result or the standard segmentation result;
• and
• iteratively train the pre-trained image segmentation model according to a loss function of the pre-trained image segmentation model, a first adversarial loss function of the first discriminator, and a second adversarial loss function of the second discriminator, until convergence, to obtain a trained image segmentation model.

A non-transitory storage medium for storing computer readable instructions, the computer readable instructions, when executed by a processor to predict an attribute of a target object based on machine learning, causing the processor to:

• train an initial image segmentation model by using source domain samples, to obtain a pre-trained image segmentation model, the source domain samples comprising a source domain image and a standard segmentation result of the source domain image;
• extract a predicted segmentation result of the source domain image and a predicted segmentation result of a target domain image by using the pre-trained image segmentation model;
• train a first discriminator by using the predicted segmentation result of the source domain image and the predicted segmentation result of the target domain image, the first discriminator being used for discriminating whether an inputted segmentation result is from a source domain or a target domain;
• train a second discriminator by using the predicted segmentation result of the source domain image and the standard segmentation result of the source domain image, the second discriminator being used for discriminating whether the inputted segmentation result is the predicted segmentation result or the standard segmentation result;
• and
• iteratively train the pre-trained image segmentation model according to a loss function of the pre-trained image segmentation model, a first adversarial loss function of the first discriminator, and a second adversarial loss function of the second discriminator, until convergence, to obtain a trained image segmentation model.