Disentangling Mean Embeddings for Better Diagnostics of Image Generators
This work addresses a critical problem for researchers and practitioners in computer vision by providing more nuanced diagnostics for image generation models, though it appears incremental as it builds on existing embedding and similarity techniques.
The paper tackles the challenge of evaluating image generators by proposing a method to disentangle mean embeddings into pixel clusters, enabling quantification of cluster-wise contributions to overall performance and enhancing explainability for identifying model misbehavior in specific regions.
The evaluation of image generators remains a challenge due to the limitations of traditional metrics in providing nuanced insights into specific image regions. This is a critical problem as not all regions of an image may be learned with similar ease. In this work, we propose a novel approach to disentangle the cosine similarity of mean embeddings into the product of cosine similarities for individual pixel clusters via central kernel alignment. Consequently, we can quantify the contribution of the cluster-wise performance to the overall image generation performance. We demonstrate how this enhances the explainability and the likelihood of identifying pixel regions of model misbehavior across various real-world use cases.