Dataset · zzliang
GRIT: region-grounded image-text pairs
zzliang/GRIT
Large-scale corpus of image-text pairs where caption phrases are grounded to corresponding image regions.
What's inside
GRIT is a large-scale Grounded Image-Text pairs corpus built on image-text pairs from COYO-700M and LAION-2B. It extracts text fragments (noun phrases and referring expressions) and links them to image regions. Size is 10M to 100M examples; modalities are images, tabular data, and text, language is English.
What you can do with it
- Train a text-to-image model with phrase-to-region grounding
- Fine-tune an object detector using text descriptions
- Evaluate visual grounding and zero-shot classification
- Tasks
- Text → image, Image → text, Object detection, Zero shot classification
- Languages
- English
- Size
- 10M–100M rows
- Downloads this month
- 8.4K
- Likes
- 170
Models trained on it
- segmind/SSD-1BText → image 25.4K
- segmind/Segmind-VegaText → image 5.3K
- nnethercott/llava-v1.5-7b-gpt4OCR-hf-GGUF_Q4_K_MText generation 417
- nnethercott/llava-v1.5-7b-gpt4OCR-hf-GGUF_Q2_KText generation 271
- remiai3/ssd-1bText → image 158
- kp-forks/SSD-1BText → image 108
- PrunaAI/Segmind-Vega-smashedText → image 44
- thingthatis/SSD-1BText → image 39
How to load it
from datasets import load_dataset
ds = load_dataset("zzliang/GRIT")