Introduction
Links:
Visual Domain Adaptation Challenge:
- Feature Level
- align the features extracted from the networks across the sourse and the target domains. (Unsupervised: no labeled target samples)
- typically, minimize some measure of the distance between the source and the target feature distribution,
- maximum mean discrepency:
- Correlation distance
- adversarial discriminator accuracy
- Limitaions:
- align marginal distributions does not enforce any semantic consistency. (e.g. car->bicycle) If the feature distributions are quite different??
- higher levels of a deep representation can fail to model aspects of low-level appearance variance lose some low-level/local feature/information
- Pixel/Frame Level : Generative
- similar distribution alignment. Translate the source data to the style of a target domain. similar distribution alignment: If the feature distributions are quite different??
- Unsupervised methods:
- Limiation:
- small image sizes and limited domain shifts;
- controlled enveironment;
- may not preserve content: crucial semantic information may be lost
- Multilevel
Discriminator:
- cannot distinguish the segmentation result between source and target
How to use the images only with the view point changes
- The distributiion of the features are very different from each other
- Also, scale is different.
- The categories of source and target are not exactly same.