Bibliography (14):

1. https://github.com/yuvalkirstain/PickScore

2. https://huggingface.co/datasets/yuvalkirstain/pickapic_v1

3. https://huggingface.co/yuvalkirstain/PickScore_v1

4. CLIP: Connecting Text and Images: We’re introducing a neural network called CLIP which efficiently learns visual concepts from natural language supervision. CLIP can be applied to any visual classification benchmark by simply providing the names of the visual categories to be recognized, similar to the ‘zero-shot’ capabilities of GPT-2 and GPT-3

5. https://laion.ai/blog/laion-5b/

6. Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models

7. Microsoft COCO: Common Objects in Context

8. Classifier-Free Diffusion Guidance

9. TensorFlow Research Cloud (TRC): Accelerate your cutting-edge machine learning research with free Cloud TPUs

10. A deep architecture for unified esthetic prediction

11. Amazon Reviews: Image-based Recommendations on Styles and Substitutes

12. Rank-Smoothed Pairwise Learning In Perceptual Quality Assessment

13. Fine-Tuning GPT-2 from Human Preferences

14. Wikipedia Bibliography:

    1. Fréchet inception distance