PoDS is a bottom approach for panoptic out-of-distribution segmentation, where the goal is to predict the semantic segmentation labels of "stuff" classes (e.g., road, sky, and so on), instance segmentation labels of "thing" classes (e.g., car, truck, etc) and out-of-distribution (OOD) objects as a distinct class.
This repository contains the PyTorch implementation of our RA-L'2024 paper Panoptic Out-of-Distribution Segmentation. The repository builds on Detectron2.
If you find this code useful for your research, we kindly ask you to consider citing our papers:
@article{mohan2024panoptic,
title={Panoptic Out-of-Distribution Segmentation},
author={Mohan, Rohit and Kumaraswamy, Kiran and Hurtado, Juana Valeria and Petek, K{\"u}rsat and Valada, Abhinav},
journal={IEEE Robotics and Automation Letters},
year={2024},
publisher={IEEE}
}
- Linux
- Python 3.9
- PyTorch 1.12.1
- CUDA 11
- GCC 7 or 8
IMPORTANT NOTE: These requirements are not necessarily mandatory. However, we have only tested the code under the above settings and cannot provide support for other setups.
Please refer to the installation documentation for detailed instructions.
Please refer to the dataset documentation for detailed instructions.
For detailed instructions on training, evaluation, and inference processes, please refer to the usage documentation.
Pre-trained models can be found in the model zoo.
We have used utility functions from other open-source projects. We espeicially thank the authors of:
For academic usage, the code is released under the GPLv3 license. For any commercial purpose, please contact the authors.