Explaining Similarity in Vision-Language Encoders with Weighted Banzhaf Interactions

Baniecki, Hubert; Muschalik, Maximilian ; Fumagalli, Fabian ; Hammer, Barbara ; Hüllermeier, Eyke und Biecek, Przemyslaw (December 2025): Explaining Similarity in Vision-Language Encoders with Weighted Banzhaf Interactions. 39th Conference on Neural Information Processing Systems (NeurIPS 2025), San Diego, CA, USA, 2.- 7. December 2025. Advances in Neural Information Processing Systems. Vol. 38 San Diego, CA, USA:

Abstract

Language–image pre-training (LIP) enables the development of vision–language models capable of zero-shot classification, localization, multimodal retrieval, and semantic understanding. Various explanation methods have been proposed to visualize the importance of input image–text pairs on the model’s similarity outputs. However, popular saliency maps are limited by capturing only first-order attributions, overlooking the complex cross-modal interactions intrinsic to such encoders. We introduce faithful interaction explanations of LIP models (FIXLIP) as a unified approach to decomposing the similarity in vision–language encoders. FIXLIP is rooted in game theory, where we analyze how using the weighted Banzhaf interaction index offers greater flexibility and improves computational efficiency over the Shapley interaction quantification framework. From a practical perspective, we propose how to naturally extend explanation evaluation metrics, such as the pointing game and area between the insertion/deletion curves, to second-order interaction explanations. Experiments on the MS COCO and ImageNet-1k benchmarks validate that second-order methods, such as FIXLIP, outperform first-order attribution methods. Beyond delivering high-quality explanations, we demonstrate the utility of FIXLIP in comparing different models, e.g. CLIP vs. SigLIP-2.

• Item Type: Conference or Workshop Item (Paper)
• Faculties: Mathematics, Computer Science and Statistics > Computer Science > Artificial Intelligence and Machine Learning
• Subjects: 000 Computer science, information and general works > 004 Data processing computer science
• Place of Publication: San Diego, CA, USA
• DFG: Gefördert durch die Deutsche Forschungsgemeinschaft (DFG) - 438445824