Make-A-Scene is a text-to-image method that (i) enables a simple control mechanism complementary to text in the form of a scene, (ii) introduces elements that improve the tokenization process by employing domain-specific knowledge over key image regions (faces and salient objects), and (iii) adapts classifier-free guidance for the transformer use case.

Procrustes

Procrustes registration of two-dimensional statistical shape models without correspondences

Make-A-Scene

Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priors

**Entropy Minimized Ensemble of Adapters**, or **EMEA**, is a method that optimizes the ensemble weights of the pretrained language adapters for each test sentence by minimizing the entropy of its predictions. The intuition behind the method is that a good [adapter](https://paperswithcode.com/method/adapter) weight $\alpha$ for a test input $x$ should make the model more confident in its prediction for $x$, that is, it should lead to lower model entropy over the input

Source	Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priors
Year	2000
Data Source	CC BY-SA - https://paperswithcode.com

Viet-Anh on Software

What is: Make-A-Scene?

Viet-Anh on Software