- Notifications
You must be signed in to change notification settings - Fork143
Taskonomy: Disentangling Task Transfer Learning [Best Paper, CVPR2018]
License
NotificationsYou must be signed in to change notification settings
StanfordVL/taskonomy
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
This repository contains:
- pretrained models (task bank) [PyTorch + TensorFlow].
- dataset
- reference code
- task affinity analyses and results
for the the following paper:
Taskonomy: Disentangling Task Transfer Learning (CVPR 2018, Best Paper Award)
Amir Zamir, Alexander Sax*, William Shen*, Leonidas Guibas, Jitendra Malik, Silvio Savarese.
| TASK BANK | DATASET |
|---|---|
Thetaskbank folder contains information about our pretrained models, and scripts to download them. There are sample outputs, and links to live demos. | Thedata folder contains information and statistics about the dataset, some sample data, andinstructions for how to download the full dataset. |
 |  |
| Task affinity analyses and results | Website |
|---|---|
| This folder contains the raw and normalized data used for measuring task affinities. | The webpage of the project with links to assets and demos. |
 |  |
If you find the code, models, or data useful, please cite this paper:
@inproceedings{zamir2018taskonomy, title={Taskonomy: Disentangling Task Transfer Learning}, author={Zamir, Amir R and Sax, Alexander and and Shen, William B and Guibas, Leonidas and Malik, Jitendra and Savarese, Silvio}, booktitle={2018 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, year={2018}, organization={IEEE}}