**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.

Please enter a description about the method here

Enabling Retrain-free Deep Neural Network Pruning using Surrogate Lagrangian Relaxation

HiSD

Image-to-image Translation via Hierarchical Style Disentanglement

Image Scale Augmentation is an augmentation technique where we randomly pick the short size of a image within a dimension range. One use case of this augmentation technique is in object detectiont asks.

Source	Image-to-image Translation via Hierarchical Style Disentanglement
Year	2000
Data Source	CC BY-SA - https://paperswithcode.com