The main goal of this paper is to devise a bias mitigation method for biased concepts An ideal inclusive T2I model yields results with evenly distributed sensitive attributes across all attribute classes, e.g., 50% male and 50% female in gender, when no attribute-related instructions are provided. A crucial aspect of a fair model is its ability to generate inclusive outcomes without direct instruction regarding the target attribute class. Besides, users' unawareness of potential biases related to a target concept should be respected.
Therefore, we argue that a good de-biasing algorithm should:
- Achieve fairer results without explicit specification of the target attribute class during generation.
- Require no prior knowledge of the original bias distribution associated with the concept (e.g., the doctor concept is stereotypically biased towards males).
![](static/images/framework.png)
Framework of our proposed adaptive inclusive token for text-to-image generation. The blue color indicates frozen weights, and the green color indicates trainable weights. Left: single training stage. Right: details of text model with adaptive mapping network. The adaptive inclusive token is concept-specific. TokenIDs are for illustration only.