DINORANKCLIP: DINOv3 Distillation and Injection for Vision-Language Pretraining with High-Order Ranking Consistency
arXiv:2605.06592v1 Announce Type: cross
Abstract: Contrastive language-image pretraining (CLIP) suffers from two structural weaknesses: the symmetric InfoNCE loss discards the relative ordering among unmatched in-batch pairs, and global pooling collap…