CoViT: Instance-Correspondence Contrastive Learning for Vision Transformer

CoViT introduces a self‑supervised framework that enhances Vision Transformers with instance‑aware representations by leveraging geometry‑guided contrastive learning. It refines attention maps to generate instance masks and constructs triplets that mine the hardest intra‑ and inter‑instance examples, driving a contrastive loss that reduces intra‑instance variance while increasing inter‑instance margins. The method yields consistent AP gains of over 2 points on instance‑level tasks without requiring extra decoders or labels.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

• llms
• rag
• computer-vision