Hyper3-CLIP: Hierarchy-Conditioned Hyperbolic Vision-Language Training
Hyper3-CLIP is presented, a hierarchy-conditioned hyperbolic VLM that combines global, local, and global-local contrastive learning with query-conditioned visual pooling and 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 hierarch...
Matin Mahmood, Antonio Rueda-Toicen, Mohamed ElBassat et al.
· 0 citations