Rounding out our research hat trick with new insights into interpretable image synthesis!

Our latest work presents a new approach to disentangle image generation performance by decomposing cosine similarity into cluster-level contributions using central kernel alignment. This allows us to quantify how different pixel regions contribute to overall image quality, enabling more fine-grained evaluation and improved explainability of generative models across real-world use cases. Published at the Interpretable AI: Past, Present and Future Workshop at NeurIPS 2024.