RO-ViT: Region-aware pre-training for open-vocabulary object detection with vision transformers
Google Research AI blog
AUGUST 28, 2023
In “ RO-ViT: Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers ”, presented at CVPR 2023 , we introduce a simple method to pre-train vision transformers in a region-aware manner to improve open-vocabulary detection. Results We evaluate RO-ViT on the LVIS open-vocabulary detection benchmark.
Let's personalize your content