RelateAnything: Real-Time Open-Vocabulary Relation Prediction From Any Inputs
Open-vocabulary detection accepts any class list at inference, and promptable segmentation returns regions without class names: the taxonomy has left the model and become an input. Relation prediction has not. Scene-graph models are still trained and evaluated on the 50 or 56 predicates of one annotation style, their relation head conditioned on object labels and so tied to one detector. Three obstacles explain this, none primarily modelling: no relation corpus is both free-text and verified, a label-conditioned architecture cannot accept a vocabulary it was not trained on, and the standard metric rewards agreement with the training corpus, so a larger vocabulary scores as a regression. W...
| Authors | Maëlic Neau |
|---|---|
| Primary category | cs.CV |
| Published | 11 September 2026 |
| Last updated at source | 11 September 2026 |
Models and datasets referencing this paper
- maelic/RA-4MDataset
- maelic/relsgg-vits16plusModel
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.