Description
This RDR contains pretrained checkpoints for the ICLR 2024 paper "CrIBo: Self-Supervised Learning via Cross-Image Object-Level Bootstrapping". These checkpoints are vision transformer backbones (ViT-S/16 and ViT-B/16) trained on ImageNet-1k and/or COCO. Please refer to README_rdr.md for loading the checkpoints.
Resources
| Name | Format | Description | Link |
|---|