TiDAL: Learning Training Dynamics for Active Learning

Accepted to ICCV 2023
https://arxiv.org/abs/2210.06788
This repository is the official implementation by the authors.
Watch our poster, slides, or the 5 minute video presentation of this paper for more details.

Prerequisites:

Install required Python packages

pip install requirements.txt

To train the model(s) and evaluate in the paper, run this command:

python main.py -d cifar10 -i 1 -m TiDAL -q Entropy

Name		Name	Last commit message	Last commit date
Latest commit History 5 Commits
data		data
methods		methods
models		models
train_test		train_test
utils		utils
README.md		README.md
config.py		config.py
main.py		main.py
poster.pdf		poster.pdf
requirements.txt		requirements.txt