AKRMap: Adaptive Kernel Regression for Trustworthy Visualization of Cross-Modal Embeddings
This work addresses the need for better visualization tools for interpreting cross-modal embeddings in multi-modal models, though it is incremental as it builds on existing dimensionality reduction techniques.
The paper tackles the problem of visualizing cross-modal embeddings by introducing AKRMap, a dimensionality reduction technique that learns kernel regression of metric landscapes to generate more accurate and trustworthy visualizations, outperforming existing methods in quantitative experiments.
Cross-modal embeddings form the foundation for multi-modal models. However, visualization methods for interpreting cross-modal embeddings have been primarily confined to traditional dimensionality reduction (DR) techniques like PCA and t-SNE. These DR methods primarily focus on feature distributions within a single modality, whilst failing to incorporate metrics (e.g., CLIPScore) across multiple modalities. This paper introduces AKRMap, a new DR technique designed to visualize cross-modal embeddings metric with enhanced accuracy by learning kernel regression of the metric landscape in the projection space. Specifically, AKRMap constructs a supervised projection network guided by a post-projection kernel regression loss, and employs adaptive generalized kernels that can be jointly optimized with the projection. This approach enables AKRMap to efficiently generate visualizations that capture complex metric distributions, while also supporting interactive features such as zoom and overlay for deeper exploration. Quantitative experiments demonstrate that AKRMap outperforms existing DR methods in generating more accurate and trustworthy visualizations. We further showcase the effectiveness of AKRMap in visualizing and comparing cross-modal embeddings for text-to-image models. Code and demo are available at https://github.com/yilinye/AKRMap.