cs.CVNov 13, 2026

Provable Cross-Modal Transfer of Hierarchical Concept Structure in CLIP Embeddings

Authors: Nghia Nguyen, Tianjiao Ding, Lachlan Ewen MacDonald, René Vidal

Organizations: University of Pennsylvania

Abstract

Contrastive vision-language models such as CLIP are trained to align images and text, not to represent taxonomies. Yet empirical studies show that CLIP embeddings exhibit hierarchical structure aligned with the hierarchy of semantic concepts. A theoretical characterization of why such hierarchy emerges from a non-hierarchical objective remains open. In this paper, we formalize this phenomenon as Hierarchical Angular Separation (HAS), a geometric property whereby each non-leaf concept embedding is more similar to its descendants than to off-branch concepts. Empirically, we show that HAS holds approximately in raw images and randomly initialized CLIP image embeddings, while in text embeddings it holds approximately only after contrastive learning. To theoretically explain this asymmetry, we analyze an unconstrained features model in which the image embeddings are fixed and only the text embeddings are trained. At the global minimizer, the text-side HAS violation percentage at each node is at most the image-side HAS violation and near-violation percentage. The key mechanism is the hierarchical co-occurrence structure of image-text pairs, which biases text embeddings toward root-centered image prototypes. For a linear contrastive loss, we derive a closed-form solution that makes this mechanism explicit. We extend the analysis to the InfoNCE loss and establish analogous guarantees under sufficient regularization. Synthetic experiments validate the theory and show that HAS is transferred even beyond the regimes covered by our analysis.

Figures & tables

Appendix figures & tables18 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Mar 26, 2026

Explaining, Verifying, and Aligning Semantic Hierarchies in Vision-Language Model Embeddings

Vision-language model (VLM) encoders such as CLIP enable strong retrieval and zero-shot classification in a shared image-text embedding space, yet the semantic organization of this space is rarely inspected. We present a post-hoc framework to explain, verify, and align the semantic hierarchies induced by a VLM over a given set of child classes. First, we extract a binary hierarchy by agglomerative clustering of class centroids and name internal nodes by dictionary-based matching to a concept bank. Second, we quantify plausibility by comparing the extracted tree against human ontologies using efficient tree- and edge-level consistency measures, and we evaluate utility via explainable hierarchical tree-traversal inference with uncertainty-aware early stopping (UAES). Third, we propose an ontology-guided post-hoc alignment method that learns a lightweight embedding-space transformation, using UMAP to generate target neighborhoods from a desired hierarchy. Across 13 pretrained VLMs and 4 image datasets, our method finds systematic modality differences: image encoders are more discriminative, while text encoders induce hierarchies that better match human taxonomies. Overall, the results reveal a persistent trade-off between zero-shot accuracy and ontological plausibility and suggest practical routes to improve semantic alignment in shared embedding spaces.
Aug 29, 2026

Hyper3-CLIP: Hierarchy-Conditioned Hyperbolic Vision-Language Training

CLIP-like vision-language models (VLMs) trained with contrastive objectives learn strong global image-text representations, but their Euclidean embeddings and global pooling fail to encode relational structure such as part-whole and parent-child relations. Hyperbolic VLMs address this gap with entailment-based objectives, and text-conditioned variants improve fine-grained alignment through sentence- and phrase-level queries. However, these two lines of work remain separate: hyperbolic VLMs use static image and region features, while query-conditioned methods lack hierarchical geometric structure. We present Hyper3-CLIP, a hierarchy-conditioned hyperbolic VLM that combines global, local, and global-local contrastive learning with query-conditioned visual pooling. To train the model, we construct lightweight query hierarchies from text, comprising full captions, sentence fragments, localized part descriptions, and extracted phrases. Each query conditions the pooling of visual patches, and the resulting representations support image-text, whole-part, and parent-child entailment losses. Query-conditioned pooling is active only during training. Hyper3-CLIP improves R@5 and R@10 retrieval on COCO and Flickr, as well as multi-label classification on VOC and COCO, while remaining competitive on hierarchy metrics. We also audit zero-shot prompt sensitivity under fixed prompt regimes and study the effect of the localized GRIT part budget used during training. Code is available at https://github.com/Hyper3Labs/hyper3-clip.
Feb 19, 2026

Canonicalizing Multimodal Contrastive Representation Learning

As models and data scale, independently trained networks often induce analogous notions of similarity. But, matching similarities is weaker than establishing an explicit correspondence between the representation spaces, especially for multimodal models, where consistency must hold not only within each modality, but also for the learned image-text coupling. We therefore ask: given two independently trained multimodal contrastive models (with encoders (f,g)(f, g) and (f~,g~)(\widetilde{f},\widetilde{g})) -- trained on different distributions and with different architectures -- does a systematic geometric relationship exist between their embedding spaces? If so, what form does it take, and does it hold uniformly across modalities? In this work, we show that across model families such as CLIP, SigLIP, and FLAVA, this geometric relationship is well approximated by an orthogonal map (up to a global mean shift), i.e., there exists an orthogonal map QQ where Q⊤Q=IQ^\top Q = I such that f~(x)≈Qf(x)\widetilde{f}(x)\approx Q f(x) for paired images xx. Strikingly, the same QQ simultaneously aligns the text encoders i.e., g~(y)≈Qg(y)\widetilde{g}(y)\approx Q g(y) for texts yy. Theoretically, we prove that if the multimodal kernel agrees across models on a small anchor set i.e. ⟨f(x),g(y)⟩≈⟨f~(x),g~(y)⟩\langle f(x), g(y)\rangle \approx \langle \widetilde{f}(x), \widetilde{g}(y)\rangle, then the two models must be related by a single orthogonal map QQ and the same QQ maps images and text across models. More broadly, this finding enables backward-compatible model upgrades, avoiding costly re-embedding, and has implications for the privacy of learned representations. Our project page: https://canonical-multimodal.github.io/