Do Vision and Language Encoders Represent the World Similarly?
This addresses a fundamental question in multimodal AI about the inherent alignment of vision and language representations, with potential applications in cross-modal tasks without requiring training.
The paper investigates whether uni-modal vision and language encoders represent the world similarly, finding that their representation spaces are semantically similar even without alignment, and proposes graph-matching methods to exploit this for tasks like cross-lingual caption matching and image classification.
Aligned text-image encoders such as CLIP have become the de facto model for vision-language tasks. Furthermore, modality-specific encoders achieve impressive performances in their respective domains. This raises a central question: does an alignment exist between uni-modal vision and language encoders since they fundamentally represent the same physical world? Analyzing the latent spaces structure of vision and language models on image-caption benchmarks using the Centered Kernel Alignment (CKA), we find that the representation spaces of unaligned and aligned encoders are semantically similar. In the absence of statistical similarity in aligned encoders like CLIP, we show that a possible matching of unaligned encoders exists without any training. We frame this as a seeded graph-matching problem exploiting the semantic similarity between graphs and propose two methods - a Fast Quadratic Assignment Problem optimization, and a novel localized CKA metric-based matching/retrieval. We demonstrate the effectiveness of this on several downstream tasks including cross-lingual, cross-domain caption matching and image classification. Code available at github.com/mayug/0-shot-llm-vision.