Downloads · 30 days
0
j-min/PaintSkills-DETR-R101-DC5
PaintSkills-DETR-R101-DC5 is a object detection model from j-min. Use it when you need objects located in an image.
DETR-R101-DC5 object detector, finetuned on PaintSkills Dataset for visual reasoning skill evaluation of text-to-image generation models.
Downloads · 30 days
0
Access
Public
Updated Dec 1, 2023
Repo size
968 MB
Likes
0
Public
Click a slice to open those files.
.pth243 MB · 100%
From the Hugging Face model README
DETR-R101-DC5 object detector, finetuned on PaintSkills Dataset for visual reasoning skill evaluation of text-to-image generation models.
Please check https://github.com/j-min/DallEval/tree/main/paintskills for the instruction for running skill evaluation with the DETR model.
@inproceedings{Cho2023DallEval,
title = {DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Models},
author = {Jaemin Cho and Abhay Zala and Mohit Bansal},
year = {2023},
booktitle = {ICCV},
}