A semantic segmentation training method and device, electronic equipment, storage medium
A technology of semantic segmentation and training method, applied in the field of image processing, can solve the problems of low intelligence and low efficiency of semantic segmentation training, and achieve the effect of improving intelligence and efficiency
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0071] The present disclosure provides a semantic segmentation training method. figure 1 It is a schematic flowchart of a semantic segmentation training method provided by an embodiment of the present disclosure. Such as figure 1 As shown, it mainly includes the following steps:
[0072] S101. Acquire a source domain segmentation result corresponding to source domain data and a target domain segmentation result corresponding to target domain data according to the semantic segmentation network to be trained.
[0073] In an embodiment of the present disclosure, the semantic segmentation training device is used to train the semantic segmentation network to be trained. According to the semantic segmentation network to be trained, the semantic segmentation training device can obtain the source domain segmentation results corresponding to the source domain data and the target domain data The corresponding target domain segmentation results.
[0074] It should be noted that, in th...
Embodiment 2
[0132] Figure 5 A schematic structural diagram of a semantic segmentation training device provided by an embodiment of the present disclosure. Such as Figure 5 As shown, the semantic segmentation training device includes:
[0133] The obtaining module 501 is used to obtain the source domain segmentation results corresponding to the source domain data and the target domain segmentation results corresponding to the target domain data according to the semantic segmentation network to be trained;
[0134] The calculation module 502 is configured to calculate the target domain segmentation loss function according to the target domain segmentation result; calculate the source domain segmentation loss function according to the source domain segmentation result and the preset hierarchical weight network; wherein, the preset hierarchical weight network comprising at least one layer of weight networks;
[0135] The training module 503 is configured to train the semantic segmentatio...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More