Data

Tools

Indexes

Applications

Experiments

Open Source Science

https://github.com/compvis/unsupervised-part-segmentation

Code for GCPR 2020 Oral : "Unsupervised Part Discovery by Unsupervised Disentanglement"

https://github.com/compvis/unsupervised-part-segmentation

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 (7.6%) to scientific vocabulary

Keywords

birds computer-vision cub gcpr humans image-segmentation machine-learning paper pytorch tensorflow unsupervised
Last synced: 5 months ago · JSON representation

Repository

Code for GCPR 2020 Oral : "Unsupervised Part Discovery by Unsupervised Disentanglement"

Basic Info
Statistics
  • Stars: 34
  • Watchers: 6
  • Forks: 4
  • Open Issues: 1
  • Releases: 0
Topics
birds computer-vision cub gcpr humans image-segmentation machine-learning paper pytorch tensorflow unsupervised
Created over 5 years ago · Last pushed over 5 years ago
Metadata Files
Readme

README.md

Unsupervised Part Discovery by Unsupervised Disentanglement

Code accompanying the GCPR 2020 paper

Unsupervised Part Discovery by Unsupervised Disentanglement
Sandro Braun, Patrick Esser, Björn Ommer

teaser
arXiv | BibTeX | Project Page

Table of Contents

Requirements

A suitable conda environment named braun20parts can be created and activated with:

bash conda env create -f environment.yaml conda activate braun20parts

Clone the repo with all it's submodules

bash git clone --recursive -j8 git@github.com:CompVis/unsupervised-part-segmentation.git

Training

  1. For running experiments into the respective subfolders deepfashion, cub and pennaction.
  2. Experiments can be run using edflow.

edflow -t xxx/<config.yaml>

Data

  • The CUB dataset is the same as in Lorenz19, but we manually added semantic part segmentations and added them in the repo.

Evaluation

  1. baseline models with pretrained checkpoints on all datasets can be found in folder baselines
  2. evaluation scripts and notebooks can be found in folder evaluation

Pretrained Models

pretrained models can be found in the respective folder, under train/checkpoints

BibTex

@inproceedings{braun2020parts, title={Unsupervised Part Discovery by Unsupervised Disentanglement}, author={Braun, Sandro and Esser, Patrick and Ommer, Bj{\"o}rn}, booktitle={Proceedings of the German Conference on Computer Vision}, year={2020} }

Owner

  • Name: CompVis - Computer Vision and Learning LMU Munich
  • Login: CompVis
  • Kind: organization
  • Email: assist.mvl@lrz.uni-muenchen.de
  • Location: Germany

Computer Vision and Learning research group at Ludwig Maximilian University of Munich (formerly Computer Vision Group at Heidelberg University)

GitHub Events

Total
Last Year

Issues and Pull Requests

Last synced: over 1 year ago

All Time
  • Total issues: 2
  • Total pull requests: 0
  • Average time to close issues: about 16 hours
  • Average time to close pull requests: N/A
  • Total issue authors: 2
  • Total pull request authors: 0
  • Average comments per issue: 0.5
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 1
  • Pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Issue authors: 1
  • Pull request authors: 0
  • Average comments per issue: 0.0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
  • XiaoqianRuan1 (1)
  • theRealSuperMario (1)
Pull Request Authors
Top Labels
Issue Labels
Pull Request Labels

Dependencies

environment.yaml pypi
  • absl-py ==0.9.0
  • albumentations ==0.4.3
  • altair ==4.0.1
  • appdirs ==1.4.3
  • aspy.yaml ==1.3.0
  • astor ==0.8.1
  • astroid ==2.3.3
  • attrs ==19.3.0
  • backcall ==0.1.0
  • bandit ==1.6.2
  • base58 ==2.0.0
  • black ==19.10b0
  • bleach ==3.1.0
  • blinker ==1.4
  • boto3 ==1.11.9
  • botocore ==1.14.9
  • cachetools ==4.0.0
  • cfgv ==2.0.1
  • chainer ==7.1.0
  • chardet ==3.0.4
  • click ==7.0
  • configparser ==4.0.2
  • coverage ==5.0.3
  • cycler ==0.10.0
  • cython ==0.29.21
  • decorator ==4.4.1
  • defusedxml ==0.6.0
  • deprecation ==2.1.0
  • docker-pycreds ==0.4.0
  • docutils ==0.15.2
  • edflow ==dev
  • entrypoints ==0.3
  • enum-compat ==0.0.3
  • fastnumbers ==3.0.0
  • filelock ==3.0.12
  • flake8 ==3.7.9
  • future ==0.18.2
  • gast ==0.2.2
  • gitdb2 ==2.0.6
  • gitpython ==3.0.5
  • google-auth ==1.11.0
  • google-auth-oauthlib ==0.4.1
  • google-pasta ==0.1.8
  • gql ==0.2.0
  • graphql-core ==1.1
  • grpcio ==1.26.0
  • h5py ==2.10.0
  • identify ==1.4.10
  • idna ==2.8
  • imageio ==2.6.1
  • imgaug ==0.2.6
  • importlib-metadata ==1.4.0
  • ipykernel ==5.1.4
  • ipython ==7.11.1
  • ipython-genutils ==0.2.0
  • ipywidgets ==7.5.1
  • isort ==4.3.21
  • jedi ==0.16.0
  • jinja2 ==2.11.0
  • jmespath ==0.9.4
  • joblib ==0.16.0
  • jsonschema ==3.2.0
  • jupyter-client ==5.3.4
  • jupyter-core ==4.6.1
  • keras-applications ==1.0.8
  • keras-preprocessing ==1.1.0
  • kiwisolver ==1.1.0
  • latentparts2 ==0.1
  • lazy-object-proxy ==1.4.3
  • markdown ==3.1.1
  • markupsafe ==1.1.1
  • matplotlib ==3.1.2
  • mccabe ==0.6.1
  • mistune ==0.8.4
  • more-itertools ==8.1.0
  • nbconvert ==5.6.1
  • nbformat ==5.0.4
  • networkx ==2.4
  • nodeenv ==1.3.4
  • nose ==1.3.7
  • notebook ==6.0.3
  • nvidia-ml-py3 ==7.352.0
  • oauthlib ==3.1.0
  • opencv-python ==4.1.2.30
  • opt-einsum ==3.1.0
  • packaging ==20.0
  • pandas ==0.25.3
  • pandocfilters ==1.4.2
  • parso ==0.6.0
  • pathspec ==0.7.0
  • pathtools ==0.1.2
  • pbr ==5.4.4
  • pexpect ==4.8.0
  • pickleshare ==0.7.5
  • pluggy ==0.13.1
  • prometheus-client ==0.7.1
  • promise ==2.3
  • prompt-toolkit ==3.0.3
  • protobuf ==3.11.2
  • psutil ==5.6.7
  • ptyprocess ==0.6.0
  • pudb ==2019.2
  • py ==1.8.1
  • pyasn1 ==0.4.8
  • pyasn1-modules ==0.2.8
  • pycocotools ==2.0
  • pycodestyle ==2.5.0
  • pydeck ==0.2.1
  • pydensecrf ==1.0rc2
  • pyflakes ==2.1.1
  • pygments ==2.5.2
  • pylint ==2.4.4
  • pyparsing ==2.4.6
  • pyrsistent ==0.15.7
  • pytest ==5.3.4
  • pytest-cov ==2.8.1
  • pytest-cover ==3.0.0
  • pytest-coverage ==0.0
  • pytest-mpl ==0.11
  • python-dateutil ==2.8.0
  • pytz ==2019.3
  • pywavelets ==1.1.1
  • pyyaml ==5.3
  • pyzmq ==18.1.1
  • regex ==2020.1.8
  • requests ==2.22.0
  • requests-oauthlib ==1.3.0
  • rope ==0.16.0
  • rsa ==4.0
  • s3transfer ==0.3.2
  • scikit-image ==0.16.2
  • scikit-learn ==0.23.1
  • scipy ==1.4.1
  • seaborn ==0.10.0
  • send2trash ==1.5.0
  • sentry-sdk ==0.14.1
  • shortuuid ==0.5.0
  • sklearn ==0.0
  • smmap2 ==2.0.5
  • stevedore ==1.31.0
  • streamlit ==0.53.0
  • subprocess32 ==3.5.4
  • supermariopy ==0.1
  • tensorboard ==1.14.0
  • tensorboardx ==2.1
  • tensorflow-estimator ==1.14.0
  • tensorflow-gpu ==1.14.0
  • termcolor ==1.1.0
  • terminado ==0.8.3
  • testpath ==0.4.4
  • threadpoolctl ==2.1.0
  • toml ==0.10.0
  • toolz ==0.10.0
  • torch ==1.4.0
  • tornado ==5.1.1
  • tqdm ==4.41.1
  • traitlets ==4.3.3
  • typed-ast ==1.4.1
  • typing-extensions ==3.7.4.1
  • tzlocal ==2.0.0
  • urllib3 ==1.25.8
  • urwid ==2.1.0
  • validators ==0.14.2
  • virtualenv ==16.7.9
  • voc-utils ==0.0
  • wandb ==0.8.26
  • watchdog ==0.10.0
  • wcwidth ==0.1.8
  • webcolors ==1.10
  • webencodings ==0.5.1
  • werkzeug ==0.16.1
  • widgetsnbextension ==3.5.1
  • wrapt ==1.11.2
  • zipp ==2.0.0
requirements.txt pypi
  • Click ==7.0
  • Cython ==0.29.21
  • GitPython ==3.0.5
  • Jinja2 ==2.11.0
  • Keras-Applications ==1.0.8
  • Keras-Preprocessing ==1.1.0
  • Markdown ==3.1.1
  • MarkupSafe ==1.1.1
  • Pillow ==6.2.2
  • PyWavelets ==1.1.1
  • PyYAML ==5.3
  • Pygments ==2.5.2
  • Send2Trash ==1.5.0
  • Werkzeug ==0.16.1
  • absl-py ==0.9.0
  • albumentations ==0.4.3
  • altair ==4.0.1
  • appdirs ==1.4.3
  • aspy.yaml ==1.3.0
  • astor ==0.8.1
  • astroid ==2.3.3
  • attrs ==19.3.0
  • backcall ==0.1.0
  • bandit ==1.6.2
  • base58 ==2.0.0
  • beautifulsoup4 ==4.8.2
  • black ==19.10b0
  • bleach ==3.1.0
  • blinker ==1.4
  • boto3 ==1.11.9
  • botocore ==1.14.9
  • cachetools ==4.0.0
  • certifi ==2019.11.28
  • cfgv ==2.0.1
  • chainer ==7.1.0
  • chardet ==3.0.4
  • configparser ==4.0.2
  • coverage ==5.0.3
  • cycler ==0.10.0
  • decorator ==4.4.1
  • defusedxml ==0.6.0
  • deprecation ==2.1.0
  • docker-pycreds ==0.4.0
  • docutils ==0.15.2
  • entrypoints ==0.3
  • enum-compat ==0.0.3
  • fastnumbers ==3.0.0
  • filelock ==3.0.12
  • flake8 ==3.7.9
  • future ==0.18.2
  • gast ==0.2.2
  • gitdb2 ==2.0.6
  • google-auth ==1.11.0
  • google-auth-oauthlib ==0.4.1
  • google-pasta ==0.1.8
  • gql ==0.2.0
  • graphql-core ==1.1
  • grpcio ==1.26.0
  • h5py ==2.10.0
  • identify ==1.4.10
  • idna ==2.8
  • imageio ==2.6.1
  • imgaug ==0.2.6
  • importlib-metadata ==1.4.0
  • ipykernel ==5.1.4
  • ipython ==7.11.1
  • ipython-genutils ==0.2.0
  • ipywidgets ==7.5.1
  • isort ==4.3.21
  • jedi ==0.16.0
  • jmespath ==0.9.4
  • joblib ==0.16.0
  • jsonschema ==3.2.0
  • jupyter-client ==5.3.4
  • jupyter-core ==4.6.1
  • kiwisolver ==1.1.0
  • lazy-object-proxy ==1.4.3
  • matplotlib ==3.1.2
  • mccabe ==0.6.1
  • mistune ==0.8.4
  • mkl-fft ==1.0.15
  • mkl-random ==1.1.0
  • mkl-service ==2.3.0
  • more-itertools ==8.1.0
  • nbconvert ==5.6.1
  • nbformat ==5.0.4
  • networkx ==2.4
  • nodeenv ==1.3.4
  • nose ==1.3.7
  • notebook ==6.0.3
  • numpy ==1.18.1
  • nvidia-ml-py3 ==7.352.0
  • oauthlib ==3.1.0
  • olefile ==0.46
  • opencv-python ==4.1.2.30
  • opt-einsum ==3.1.0
  • packaging ==20.0
  • pandas ==0.25.3
  • pandocfilters ==1.4.2
  • parso ==0.6.0
  • pathspec ==0.7.0
  • pathtools ==0.1.2
  • pbr ==5.4.4
  • pexpect ==4.8.0
  • pickleshare ==0.7.5
  • pluggy ==0.13.1
  • prometheus-client ==0.7.1
  • promise ==2.3
  • prompt-toolkit ==3.0.3
  • protobuf ==3.11.2
  • psutil ==5.6.7
  • ptyprocess ==0.6.0
  • pudb ==2019.2
  • py ==1.8.1
  • pyasn1 ==0.4.8
  • pyasn1-modules ==0.2.8
  • pycodestyle ==2.5.0
  • pydeck ==0.2.1
  • pyflakes ==2.1.1
  • pylint ==2.4.4
  • pyparsing ==2.4.6
  • pyrsistent ==0.15.7
  • pytest ==5.3.4
  • pytest-cov ==2.8.1
  • pytest-cover ==3.0.0
  • pytest-coverage ==0.0
  • pytest-mpl ==0.11
  • python-dateutil ==2.8.0
  • pytz ==2019.3
  • pyzmq ==18.1.1
  • regex ==2020.1.8
  • requests ==2.22.0
  • requests-oauthlib ==1.3.0
  • rope ==0.16.0
  • rsa ==4.0
  • s3transfer ==0.3.2
  • scikit-image ==0.16.2
  • scikit-learn ==0.23.1
  • scipy ==1.4.1
  • seaborn ==0.10.0
  • sentry-sdk ==0.14.1
  • shortuuid ==0.5.0
  • six ==1.13.0
  • sklearn ==0.0
  • smmap2 ==2.0.5
  • soupsieve ==1.9.5
  • stevedore ==1.31.0
  • streamlit ==0.53.0
  • subprocess32 ==3.5.4
  • tensorboard ==1.14.0
  • tensorboardX ==2.1
  • tensorflow-estimator ==1.14.0
  • tensorflow-gpu ==1.14.0
  • termcolor ==1.1.0
  • terminado ==0.8.3
  • testpath ==0.4.4
  • threadpoolctl ==2.1.0
  • toml ==0.10.0
  • toolz ==0.10.0
  • torch ==1.4.0
  • torchvision ==0.5.0
  • tornado ==5.1.1
  • tqdm ==4.41.1
  • traitlets ==4.3.3
  • typed-ast ==1.4.1
  • typing-extensions ==3.7.4.1
  • tzlocal ==2.0.0
  • urllib3 ==1.25.8
  • urwid ==2.1.0
  • validators ==0.14.2
  • virtualenv ==16.7.9
  • voc-utils ==0.0
  • wandb ==0.8.26
  • watchdog ==0.10.0
  • wcwidth ==0.1.8
  • webcolors ==1.10
  • webencodings ==0.5.1
  • widgetsnbextension ==3.5.1
  • wrapt ==1.11.2
  • zipp ==2.0.0