Benchmark

RO-ViT: Region-aware pre-training for open-vocabulary ...

RO‑ViT proposes a region-aware pretraining scheme for vision transformers that uses cropped positional embeddings and focal loss to better align image–text pretraining with region-level object detection. Developers building open‑vocabulary detectors can reuse these ideas—plus the released code—to boost novel‑class detection without changing model capacity, especially when fine‑tuning ViT backbones on detection datasets. ([ai.googleblog.com](https://ai.googleblog.com/2023/08/ro-vit-region-aware-pre-training-for.html))