Beyond One-Hot-Encoding: Injecting Semantics to Drive Image Classifiers [Conference Paper] | [arXiv Version]
This is not the code used in the paper but a simple notebook to explain the core concepts.
We assume that you have Python 3.10 and jupyter-lab/jupyter-notebook installed on your system.
- Clone this repository:
git clone https://github.com/S1M0N38/semantic-encodings.git - Move inside the repository:
cd semantic-encodings - Create a virtual environment:
python -m venv venv - Activate the virtual environment:
source venv/bin/activate - Install the dependencies:
python -m pip install -r requirements.txt - Install the kernel:
python -m ipykernel install --user --name=semantic-encodings
We assume that you have followed the installation instructions above.
- Open the notebook:
jupyter-lab semantic-encodings.ipynborjupyter-notebook semantic-encodings.ipynb - Select the kernel:
Kernel -> Change kernel -> semantic-encodings
If you need to uninstall this directory and all libraries installed in the virtual environment, simply remove the semantic-encodings directory (If you have followed the installation, the virtual environment directory is inside semantic-encodings).
Moreover, you need to remove the kernel installed. Run the command jupyter kernelspec uninstall semantic-encodings to remove the kernel.
@article{SemanticsEncPerott2023,
author = {Perotti, Alan and Bertolotto, Simone and Pastor, Eliana and Panisson, Andr\'{e}},
eprint = {2308.00607v1},
month = {8},
primaryclass = {cs.cv},
title = {Beyond One-Hot-Encoding: Injecting Semantics to Drive Image Classifiers},
url = {http://arxiv.org/abs/2308.00607v1},
year = {2023},
}