Hierarchical Style Disentanglement, or HiSD, aims to disentangle different styles in image-to-image translation models. It organizes the labels into a hierarchical structure, where independent tags, exclusive attributes, and disentangled styles are allocated from top to bottom. To make the styles identified to the tags and attributes, the authors carefully redesign the modules, phases, and objectives.
Source: Image-to-image Translation via Hierarchical Style DisentanglementPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Disentanglement | 1 | 25.00% |
Image-to-Image Translation | 1 | 25.00% |
Multimodal Unsupervised Image-To-Image Translation | 1 | 25.00% |
Translation | 1 | 25.00% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |