Data

Tools

Indexes

Applications

Experiments

Open Source Science

https://github.com/bravegroup/psps

Pointly-supervised panoptic segmentation

https://github.com/bravegroup/psps

Science Score: 10.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ○
    CITATION.cff file
  • ○
    codemeta.json file
  • ○
    .zenodo.json file
  • ○
    DOI references
  • ✓
    Academic publication links
    Links to: arxiv.org
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (9.0%) to scientific vocabulary
Last synced: 10 months ago · JSON representation

Repository

Pointly-supervised panoptic segmentation

Basic Info
  • Host: GitHub
  • Owner: BraveGroup
  • License: apache-2.0
  • Language: Python
  • Default Branch: master
  • Size: 1.42 MB
Statistics
  • Stars: 25
  • Watchers: 4
  • Forks: 1
  • Open Issues: 1
  • Releases: 0
Created almost 4 years ago · Last pushed over 2 years ago
Metadata Files
Readme License

README.md

Pointly-Supervised Panoptic Segmentation (ECCV 2022 Oral)

Panoptic segmentation with a single point label per target! [paper]

Here are all the codes to reproduce the results. We are still cleaning them and will update later.

The code is based on the implementation of Panoptic SegFormer.

The point labels used in the paper can be downloaded here.

Install

  1. Install common prerequisties: Python, PyTorch, CUDA, etc.
  2. Install mmcv. This work is tested with mmcv up to version 1.7.1.
  3. Install other requirements: bash pip install -r requirements.txt
  4. Install the custom pydijkstra package: bash cd PSPS/py-dijkstra/pydijkstra python setup.py install --user

Note that the panopticapi has risk of memory leakage, as been discussed in this issue. The solution is to add a workers.close() in panopticapi/evaluation.py/pq_compute_multi_core before the function return.

Prepare Dataset

  • Pascal VOC
1. Download the [Pascal VOC dataset](http://host.robots.ox.ac.uk/pascal/VOC/voc2012/).
2. Download the point labels [here](https://drive.google.com/drive/folders/19qBN_da_icbXvMFjlFtz4y24CN2MAvXB?usp=sharing).
3. Organize the dataset by the following structure:
    ```
    PSPS/data/voc
    ├── JPEGImages
    │   ├── 20xx_xxxxxx.jpg
    │   └──     ...
    │
    └── Panoptic        
        ├── voc_panoptic_train_aug.json
        ├── voc_panoptic_val.json
        │
        ├── voc_panoptic_train_aug_1pnt_uniform
        │   ├── 20xx_xxxxxx.png
        │   └──     ...
        │
        └── voc_panoptic_val
            ├── 20xx_xxxxxx.png
            └──     ...
    ```

  • MS COCO

    ...

Train & Test

Please find the example_run.sh for details.

TODO

  • [ ] clean code
  • [x] update README.md

Owner

  • Name: BraveGroup
  • Login: BraveGroup
  • Kind: organization

GitHub Events

Total
Last Year

Dependencies

py-dijkstra/pydijkstra/setup.py pypi
requirements.txt pypi
  • panopticapi master
  • pybind11 *
  • pycocotools *
  • scikit-image *
  • scikit-learn *
  • shapely *
  • terminaltables *
  • timm *