AKRMap: Adaptive Kernel Regression for Trustworthy Visualization of Cross-Modal Embeddings

Yilin Ye, Junchao Huang, Xingchen Zeng, Jiazhi Xia, Wei Zeng
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:71979-71997, 2025.

Abstract

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-ye25d, title = {{AKRM}ap: Adaptive Kernel Regression for Trustworthy Visualization of Cross-Modal Embeddings}, author = {Ye, Yilin and Huang, Junchao and Zeng, Xingchen and Xia, Jiazhi and Zeng, Wei}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {71979--71997}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/ye25d/ye25d.pdf}, url = {https://proceedings.mlr.press/v267/ye25d.html}, abstract = {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.} }
Endnote
%0 Conference Paper %T AKRMap: Adaptive Kernel Regression for Trustworthy Visualization of Cross-Modal Embeddings %A Yilin Ye %A Junchao Huang %A Xingchen Zeng %A Jiazhi Xia %A Wei Zeng %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-ye25d %I PMLR %P 71979--71997 %U https://proceedings.mlr.press/v267/ye25d.html %V 267 %X 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.
APA
Ye, Y., Huang, J., Zeng, X., Xia, J. & Zeng, W.. (2025). AKRMap: Adaptive Kernel Regression for Trustworthy Visualization of Cross-Modal Embeddings. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:71979-71997 Available from https://proceedings.mlr.press/v267/ye25d.html.

Related Material