Summary of Measuring Diversity in Co-creative Image Generation, by Francisco Ibarrola and Kazjon Grace
Measuring Diversity in Co-creative Image Generation
by Francisco Ibarrola, Kazjon Grace
First submitted to arxiv on: 6 Mar 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Computation and Language (cs.CL); Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper proposes a new method to assess the diversity of images generated by co-creative systems. The authors argue that existing approaches have limitations, such as requiring ground-truth knowledge or being impractical to compute. They introduce an alternative based on entropy of neural network encodings, which is easy to calculate and does not require prior knowledge. The method is tested on two pre-trained networks, showing how the choice affects the notion of diversity evaluated. This has implications for ideation in interactive systems, model evaluation, and broader applications within computational creativity. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps us understand how to measure the variety of images made by computers that work with people. Right now, there’s no clear way to do this. The authors suggest a new method that is easy to use and doesn’t need prior information about what the computer should be generating. They test their idea on two types of networks and show how it can help us understand diversity better. This has big implications for making ideas in interactive systems, evaluating models, and more. |
Keywords
* Artificial intelligence * Neural network
