CODI: Improving Self-Supervised Vision Transformers with Cross Distillation
arXiv:2610.30639v1 Announce Type: new Abstract: Self-supervised Vision Transformers learn strong image-level representations, but their patch-level representations can be unreliable for dense prediction. We study this mismatch and find that the class token concentrates global semantics on a small n…
Read the full story at arXiv cs.CV ↗
Timeline · 1 report
- 2026-10-23 04:00 · arXiv cs.CV
CODI: Improving Self-Supervised Vision Transformers with Cross Distillation