Downloads · 30 days
0
r2o
KonstantinosKK/r2o
r2o is a machine learning model from KonstantinosKK. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
PyTorch implementation of R2O from "Refine and Represent: Region-to-Object Representation Learning" (Gokul et al., 2022).
Access
Public
Updated Jun 19, 2025
Repo size
618 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.tar516 MB · 83%
At a glance
- License
- mit
- Access
- Public
- Created
- Jun 19, 2025
- Updated
- Jun 19, 2025
- SHA
- ed2d0c05
Model card
From the Hugging Face model README
R2O PyTorch
PyTorch implementation of R2O from "Refine and Represent: Region-to-Object Representation Learning" (Gokul et al., 2022).
Pretrained Weights
We provide R2O ResNet-50 weights pretrained on ImageNet-1K for 300 epochs:
| Format | Download | Use Case |
|---|---|---|
| Original | r2o_resnet50_imagenet300.pth | Direct loading |
| Torchvision | r2o_resnet50_imagenet300_torchvision.pth | MMSegmentation |
| Detectron2 | r2o_resnet50_imagenet300_d2.pkl | Detectron2 |
Usage
See GitHub repo for how to use weights.
Citing this work
@misc{gokul2022refine,
title = {Refine and Represent: Region-to-Object Representation Learning},
author = {Gokul, Akash and Kallidromitis, Konstantinos and Li, Shufan and Kato, Yusuke and Kozuka, Kazuki and Darrell, Trevor and Reed, Colorado J},
journal={arXiv preprint arXiv:2208.11821},
year = {2022}
}
- License
- mit
- Created
- Jun 19, 2025
- Updated
- Jun 19, 2025