https://github.com/compvis/deep_unsupervised_posets
Deep Unsupervised Similarity Learning using Partially Ordered Sets (CVPR17)
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 (6.8%) to scientific vocabulary
Repository
Deep Unsupervised Similarity Learning using Partially Ordered Sets (CVPR17)
Basic Info
Statistics
- Stars: 2
- Watchers: 4
- Forks: 1
- Open Issues: 0
- Releases: 0
Metadata Files
README.md
Deep Unsupervised Similarity Learning Using Partially Ordered Sets (CVPR 2017)
Accepted at CVPR 2017
"Deep Unsupervised Similarity Learning Using Partially Ordered Sets"
Miguel A. Bautista* , Artsiom Sanakoyeu* , Björn Ommer.
- Paper: https://arxiv.org/abs/1704.02268
- GT labels for Olympic Sports dataset: olympicsportsretrieval/data
- Evaluation script for Olympic Sports dataset: calculaterocauc.py
- Baseline HOG-LDA similarity matrices for Olympic Sports: similaritieshoglda.tar.zip (11.5 Gb)
Tensorflow models for Olympic Sports dataset trained with our approach
All models were trained from scratch without Imagenet pretraining and without any supervision.
- The model trained on all frames from Olympic sports dataset: olympicsportsallcatconvnetscratchstrip.ckpt
- Using the same method we finetuned the previous model for each sport independently w/o any supervision (we again used only grouping and posets that we build without GT information).
Single models for each sport: olympicsportsmodelsfromscratch
Requirements
- Python 2.7
- Tensorflow r1.*
Example
Example how to load models: exampleloadnetworks.ipynb.
If you find this code or data useful for your research, please cite
@inproceedings{UnsupSimPosets2017,
title={Deep Unsupervised Similarity Learning using Partially Ordered Sets}
author={Bautista, Miguel A and Sanakoyeu, Artsiom and Ommer, Bj{\"o}rn},
booktitle={The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
year={2017}
}
Owner
- Name: CompVis - Computer Vision and Learning LMU Munich
- Login: CompVis
- Kind: organization
- Email: assist.mvl@lrz.uni-muenchen.de
- Location: Germany
- Website: https://ommer-lab.com/
- Repositories: 33
- Profile: https://github.com/CompVis
Computer Vision and Learning research group at Ludwig Maximilian University of Munich (formerly Computer Vision Group at Heidelberg University)